CN114842338A - Wheat stripe rust prediction method and device based on coupling of remote sensing and meteorological data - Google Patents
Wheat stripe rust prediction method and device based on coupling of remote sensing and meteorological data Download PDFInfo
- Publication number
- CN114842338A CN114842338A CN202210508506.8A CN202210508506A CN114842338A CN 114842338 A CN114842338 A CN 114842338A CN 202210508506 A CN202210508506 A CN 202210508506A CN 114842338 A CN114842338 A CN 114842338A
- Authority
- CN
- China
- Prior art keywords
- stripe rust
- wheat
- meteorological
- data
- vegetation index
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 title claims abstract description 195
- 241000209140 Triticum Species 0.000 title claims abstract description 186
- 235000021307 Triticum Nutrition 0.000 title claims abstract description 186
- 238000000034 method Methods 0.000 title claims abstract description 80
- 230000008878 coupling Effects 0.000 title claims abstract description 19
- 238000010168 coupling process Methods 0.000 title claims abstract description 19
- 238000005859 coupling reaction Methods 0.000 title claims abstract description 19
- 201000010099 disease Diseases 0.000 claims abstract description 33
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 33
- 230000001360 synchronised effect Effects 0.000 claims description 39
- 238000012545 processing Methods 0.000 claims description 25
- 238000010586 diagram Methods 0.000 claims description 22
- 238000009826 distribution Methods 0.000 claims description 19
- 238000005286 illumination Methods 0.000 claims description 14
- 238000003860 storage Methods 0.000 claims description 14
- 238000004458 analytical method Methods 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 9
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 8
- 230000000630 rising effect Effects 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 238000009499 grossing Methods 0.000 claims description 6
- 239000003337 fertilizer Substances 0.000 claims description 5
- 241000196324 Embryophyta Species 0.000 abstract description 5
- 239000000575 pesticide Substances 0.000 abstract description 3
- 238000005507 spraying Methods 0.000 abstract description 3
- 238000012706 support-vector machine Methods 0.000 description 18
- 230000008859 change Effects 0.000 description 11
- 238000011160 research Methods 0.000 description 11
- 238000004590 computer program Methods 0.000 description 6
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 238000010832 independent-sample T-test Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 239000002028 Biomass Substances 0.000 description 3
- 238000010219 correlation analysis Methods 0.000 description 3
- 238000011835 investigation Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000003595 spectral effect Effects 0.000 description 3
- 230000004083 survival effect Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000035784 germination Effects 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 208000015181 infectious disease Diseases 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000000049 pigment Substances 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000017260 vegetative to reproductive phase transition of meristem Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 241000221785 Erysiphales Species 0.000 description 1
- 206010061217 Infestation Diseases 0.000 description 1
- 206010028347 Muscle twitching Diseases 0.000 description 1
- 241001123583 Puccinia striiformis Species 0.000 description 1
- 241000415582 Puccinia striiformis f. sp. tritici Species 0.000 description 1
- 206010039509 Scab Diseases 0.000 description 1
- 230000009418 agronomic effect Effects 0.000 description 1
- 239000010242 baoji Substances 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 229930002875 chlorophyll Natural products 0.000 description 1
- 235000019804 chlorophyll Nutrition 0.000 description 1
- ATNHDLDRLWWWCB-AENOIHSZSA-M chlorophyll a Chemical compound C1([C@@H](C(=O)OC)C(=O)C2=C3C)=C2N2C3=CC(C(CC)=C3C)=[N+]4C3=CC3=C(C=C)C(C)=C5N3[Mg-2]42[N+]2=C1[C@@H](CCC(=O)OC\C=C(/C)CCC[C@H](C)CCC[C@H](C)CCCC(C)C)[C@H](C)C2=C5 ATNHDLDRLWWWCB-AENOIHSZSA-M 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000006806 disease prevention Effects 0.000 description 1
- 230000005059 dormancy Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010899 nucleation Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Agronomy & Crop Science (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Animal Husbandry (AREA)
- Primary Health Care (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a wheat stripe rust prediction method and device coupling remote sensing and meteorological data, a sentinel second satellite data is combined with the meteorological data to predict large-range wheat stripe rust, and the prediction method and device are different from the existing prediction of the incidence trend based on the meteorological data, and are more biased to practical application; compared with the existing prediction based on satellite data, the method can predict the occurrence position of the disease with high precision, and can provide precise guidance for actual pesticide spraying and plant protection management; in addition, the remote sensing characteristic extracted based on the phenological information is optimized for the problem that the precision of the model is reduced due to the growth period difference of wheat in actual field management, and compared with the existing remote sensing characteristic based on a single period, the method can provide high-precision prediction index reference for stripe rust.
Description
Technical Field
The application relates to the technical field of crop disease prevention, in particular to a wheat stripe rust prediction method and device based on remote sensing and meteorological data coupling.
Background
The prediction methods of crop diseases mainly comprise two methods: the first method is mainly to predict the occurrence of diseases by using meteorological data, because spores need suitable habitat for survival, germination and infection, and some scholars predict the integral occurrence trend of diseases by analyzing the response relation between habitat factors and diseases and combining a statistical model; the second method is to predict diseases by using remote sensing data, and after the diseases are stressed, the related indexes of the crop growth conditions, such as pigment content, water content, biomass, cell structure and the like, can change, and generally, the indexes of the crop growth conditions can be represented by vegetation indexes calculated by remote sensing images. Therefore, many scholars screen vegetation indexes capable of representing host growth conditions under the stress of diseases by analyzing the relationship between the vegetation indexes and crop diseases, construct prediction models of different diseases and predict the spatial distribution conditions of the diseases, for example, Ruan et al analyzes the change of the growth conditions of wheat under the stress of stripe rust based on multi-temporal Sentiel-2 satellite data, defines the vegetation indexes sensitive to stripe rust in different phenological periods by utilizing a sequence forward selection algorithm, constructs a wheat stripe rust time sequence prediction model by combining with an SVM, successfully predicts the occurrence distribution conditions of the wheat stripe rust in different periods, and the results show the performance of meteorological and remote sensing data in predicting the aspect of crop diseases.
At the present stage, partial scholars try to construct a disease prediction model comprehensively considering the growth conditions and the habitat factors of crops by coupling remote sensing and meteorological data. For example, Zhang et al utilizes a series of vegetation indexes and meteorological features extracted from HJ satellite images and meteorological data to construct a wheat powdery mildew prediction model by combining a Logistic method. Xiao et al successfully constructed a wheat scab prediction model based on vegetation index and meteorological features by using Landsat8 image and meteorological data. The researches indicate that compared with a prediction model constructed based on a single type of characteristics, the vegetation index and meteorological characteristics are combined to effectively improve the accuracy of the prediction model. Thus, these results have prompted us to continue to explore ways in which crop growth status and habitat factors can be combined to predict wheat stripe rust.
However, in the actual field management, due to the influence of climate and some agronomic factors, the climate and the stage of wheat at the same period are different, and the change of the crop growth condition caused by the climate and the stage is obvious, which often causes great interference to the change of the crop growth condition caused by disease stress. For example, with the continuous growth of wheat, from the green turning stage to the heading stage, the growth parameters such as the chlorophyll content and the biomass of wheat show a trend of gradually increasing and then gradually decreasing, and the vegetation index reflecting the growth condition of the host wheat also shows a corresponding change. However, most of the existing researches usually default that crops in the same period are in the same phenological stage, and the influence of phenological differences in actual production on the prediction of crop diseases is ignored.
Disclosure of Invention
In view of the problems in the content, the application provides a wheat stripe rust prediction method and device based on coupled remote sensing and meteorological data, based on time sequence remote sensing images and meteorological data, vegetation indexes based on physical and weather information and meteorological features sensitive to stripe rust are extracted, and regional wheat stripe rust prediction is achieved by constructing a wheat stripe rust prediction model combining the vegetation indexes with the meteorological features.
In order to achieve the above object, the present application provides the following technical solutions:
a wheat stripe rust prediction method coupling remote sensing and meteorological data comprises the following steps:
acquiring satellite-ground synchronous observation data of wheat stripe rust in a region to be predicted, sentinel second satellite image data and Chinese meteorological site data;
using the wheat stripe rust satellite-ground synchronous observation data and the sentinel second image data to extract a vegetation index based on the phenological information, wherein the vegetation index based on the phenological information is used for representing the growth condition of wheat under the stress of stripe rust;
extracting meteorological features by using the Chinese meteorological site data, wherein the meteorological features comprise: relative humidity of 12 months, illumination intensity of 1 month, rainfall of 1 month and rainfall of 7 days before the forecast day;
and taking the vegetation index based on the phenological information and the meteorological features as input features, predicting the stripe rust occurrence condition of each pixel by using a wheat stripe rust prediction model, and drawing a stripe rust occurrence distribution diagram to realize the prediction of stripe rust.
A wheat stripe rust prediction device that couples remote sensing and meteorological data, comprising:
the first processing unit is used for acquiring satellite-ground synchronous observation data of the wheat stripe rust in the area to be predicted, sentinel second satellite image data and Chinese meteorological station data;
the second processing unit is used for extracting a vegetation index based on the phenological information by using the wheat stripe rust satellite-ground synchronous observation data and the sentinel second image data, and the vegetation index based on the phenological information is used for representing the growth condition of wheat under the stress of stripe rust;
a third processing unit, configured to extract weather features using the data of the chinese weather site, where the weather features include: relative humidity of 12 months, illumination intensity of 1 month, rainfall of 1 month and rainfall of 7 days at present;
and the fourth processing unit is used for predicting the stripe rust occurrence condition of each pixel by using the vegetation index based on the physical and weather information and the meteorological features as input features and by using a wheat stripe rust prediction model, and drawing a stripe rust occurrence distribution diagram so as to realize the prediction of stripe rust.
A storage medium comprising a stored program, wherein the program, when executed, controls a device on which the storage medium is located to perform a wheat stripe rust prediction method that couples remote sensing and meteorological data as described above.
An electronic device comprising at least one processor, and at least one memory, bus connected with the processor; the processor and the memory complete mutual communication through the bus; the processor is configured to invoke the program instructions in the memory to perform the method for wheat stripe rust prediction coupled with remote sensing and meteorological data as described above.
According to the wheat stripe rust prediction method and device based on coupled remote sensing and meteorological data, firstly, satellite-ground synchronous observation data of wheat stripe rust in an area to be predicted, sentinel second satellite image data and Chinese meteorological site data are obtained; then, using the wheat stripe rust satellite-ground synchronous observation data and the sentinel second image data to extract a vegetation index based on the phenological information, wherein the vegetation index based on the phenological information is used for representing the growth condition of wheat under the stress of stripe rust; and then extracting meteorological features by using the Chinese meteorological site data, wherein the meteorological features comprise: relative humidity of 12 months, illumination intensity of 1 month, rainfall of 1 month and rainfall of 7 days at present; and finally, taking the vegetation index based on the phenological information and the meteorological features as input features, predicting the stripe rust occurrence condition of each pixel by using a wheat stripe rust prediction model, and drawing a stripe rust occurrence distribution diagram to realize the prediction of stripe rust.
The method utilizes the sentinel second satellite data in combination with meteorological data to predict the wheat stripe rust in a large range, and is different from the existing meteorological data-based disease trend prediction, so that the method is more biased to practical application; compared with the existing prediction based on satellite data, the method can predict the occurrence position of the disease with high precision, and can provide precise guidance for actual pesticide spraying and plant protection management. In addition, the remote sensing characteristic extracted based on the phenological information is optimized for the problem that the precision of the model is reduced due to the growth period difference of wheat in actual field management, and compared with the existing remote sensing characteristic based on a single period, the method can provide high-precision prediction index reference for stripe rust.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a wheat stripe rust prediction method based on remote sensing and meteorological data coupling disclosed in an embodiment of the present application;
fig. 2 is a schematic diagram of an overall technical route of a wheat stripe rust prediction method by coupling remote sensing and meteorological data disclosed in an embodiment of the present application;
FIG. 3 is a schematic diagram of experimental area distribution of data acquisition locations disclosed in an embodiment of the present application;
FIG. 4 is a schematic diagram of a prediction result of a wheat jointing stage disclosed in an embodiment of the present application;
FIG. 5 is a graph showing a comparison of (a) index of vegetation extracted based on climatic information and (b) mean and standard deviation of index of vegetation at a single stage after normalization as disclosed in an embodiment of the present application;
FIG. 6 is a schematic diagram illustrating correlation between meteorological features calculated using meteorological features according to an embodiment of the present disclosure;
FIG. 7 is a schematic diagram of a spatial distribution of wheat stripe rust in a research area predicted by a model constructed by combining a vegetation index and meteorological features based on climatic information and an SVM, disclosed in the embodiment of the present application;
fig. 8 is a schematic structural diagram of a wheat stripe rust prediction device coupled with remote sensing and meteorological data according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application.
Detailed Description
Interpretation of terms:
the phenological climate is as follows: the phenomenon that the crops regularly change such as germination, twitching, leaf expanding, flowering, fruiting, leaf falling and dormancy along with seasonal change of the climate is called as the phenology. In wheat, the growth stage (or called as the phenological stage) is reached as the wheat grows and changes the climate. The phenological stage is divided into a seeding stage, a seedling stage, a tillering stage, a wintering stage, a reviving stage, a rising stage, a jointing stage, a heading and flowering stage, a grouting stage and a mature stage.
Sentinel II: the sentinel 2 (sentinel two) carries a multispectral imager (MSI), the height is 786km, 13 spectral bands can be covered, and the breadth reaches 290 kilometers. The ground resolution is respectively 10m, 20m and 60m, the revisit period of one satellite is 10 days, the two satellites are complementary, and the revisit period is 5 days. The method is often used for land monitoring, can provide images of vegetation, soil and water coverage, inland waterways, coastal areas and the like, and can also be used for emergency rescue services. The sentinel-2 data is the only data containing three wave bands in the red side range, and is very effective for extracting vegetation health information.
Wheat stripe rust: is an important disease with wide distribution, quick transmission and large harm area in Chinese wheat production, and seriously affects the yield and quality of wheat. In the current year, if the prevention is not timely, the wheat stripe rust can cause yield loss of more than 30 percent and even stop producing. In China, the annual average area of damage of the stripe rust exceeds 400 million hectares, and the annual average yield loss is about 100 million tons.
Vegetation index: according to the spectral characteristics of the vegetation, the satellite spectral bands are combined to form various vegetation indexes. Can effectively characterize the physiological and biochemical parameter change of crops under the stress of diseases. After the wheat is infected with stripe rust, the physiological and biochemical parameters of biomass, pigment content, water content and the like which reflect the growth condition of the wheat can be changed. Typically these changes can be characterized by a vegetation index.
Meteorological features: the survival, propagation and infestation of rust striiformis also require suitable habitat such as temperature, humidity and rainfall. The meteorological features of the key growth period of the wheat are calculated by utilizing the meteorological data, so that the wheat habitat can be represented.
Wheat stripe rust prediction index: aiming at the occurrence and development rule of stripe rust, extracting a vegetation index combination of a key objective period by combining time sequence harmonic analysis and average accumulated temperature for representing the growth condition of wheat; and the meteorological characteristic combination screened out by the characteristic extraction is used for representing the wheat habitat. And constructing a prediction model of the wheat stripe rust by taking the coupling vegetation index and the meteorological characteristics as prediction indexes.
The applicant finds in research that the prediction accuracy is low due to the fact that only meteorological features or remote sensing features are considered in the existing wheat stripe rust prediction method; in addition, most of the existing remote sensing features are extracted by using remote sensing images of a single period, and the influence of the climate difference of wheat in an area range on the prediction of stripe rust is not considered. Therefore, the method and the device for predicting the wheat stripe rust by coupling the remote sensing data with the meteorological data are provided, the remote sensing characteristics are tried to be extracted based on the phenological information while the remote sensing data is coupled with the meteorological data, and the prediction precision of the wheat stripe rust is improved.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, a schematic flow chart of a wheat stripe rust prediction method based on remote sensing and meteorological data coupling provided by the embodiment of the application is shown. As shown in fig. 1, an embodiment of the present application provides a wheat stripe rust prediction method by coupling remote sensing with meteorological data, and the method includes the following steps:
s101: acquiring satellite-ground synchronous observation data of wheat stripe rust in a region to be predicted, sentinel second satellite image data and Chinese meteorological site data;
the overall technical route of the embodiment of the application is shown in fig. 2, the technical scheme shares three types of experimental data, the first type is satellite-ground synchronous observation data of wheat stripe rust, the second type is image data of a sentinel second satellite, and the third type is data of a Chinese meteorological site. The location of the data acquisition is shown in fig. 3.
The star-to-ground synchronous observation data acquisition site of the wheat stripe rust is a wheat planting region in Qishan county of Baoji city of Shanxi province. The Qishan county is located in the Guanzhong plain of Shaanxi province and is a junction zone of overwintering areas and spring circulation areas of the puccinia striiformis f.sp.tritici. The average temperature and precipitation in the county are respectively 6-13 deg.C and 500-700 mm; the low temperature and high humidity environmental conditions increase the risk of stripe rust. Meanwhile, stripe rust is the most prominent wheat disease in this county and occurs severely in 2021. Research area ground survey experiments were conducted at 2021, 4, 17 days. In order to match sample points with the pixel size of the remote sensing image, 10m field blocks are selected as sample points in the range of 20m of consistent wheat growth trend for disease investigation. For each sample point, we investigated and recorded the degree of stripe rust development and its center latitude and longitude. During investigation, 5 samples with the size of 1m × 1m are selected from the four corners and the center of each sample point, 10 leaves are randomly selected from each sample to record the severity of the disease, and finally the average severity of the 5 samples is used as the occurrence degree of the stripe rust of the sample points. The occurrence degree of the stripe rust is determined according to the national standard 'wheat stripe rust prediction technical specification'. Since the mild occurrence of stripe rust is commonly investigated, the disease occurrence degree is divided into two categories of health and morbidity for subsequent research.
The Sentinel second satellite data, the time sequence Sentinel-2 satellite image of wheat growth period (1 month to 6 months) in the study area 2018 and 2021 year is obtained in the embodiment of the application. The data is preprocessed by related software, including preprocessing of radiation correction and atmospheric correction, so that pixel values in the original sentinel second multispectral image are converted into surface reflectivity. Spatial distribution of wheat in a research area is extracted by combining a decision tree with a multi-temporal phenological information method, and meanwhile, the extracted wheat area is subjected to precision verification by using 97 sample points, so that the total verification accuracy rate reaches 98%. The spatial distribution of wheat is shown in FIG. 3.
The meteorological data are from a China meteorological data center, and day-by-day meteorological data of 12 months in the year 2020 and 2021 and 2018 are obtained in the embodiment of the application. The data includes a total of 9 meteorological elements: average Air Temperature (ATEM), maximum air temperature (HTEM), minimum air temperature (LTEM), average ground temperature (AGST), maximum ground temperature (HGST), minimum ground temperature (LGST), number of sunshine hours (SSD), rainfall (PRE), and Relative Humidity (RHU). In order to realize the spatialization of the meteorological data of the station, the meteorological data are subjected to spatial interpolation by using an inverse distance weight method, and the resolution of the spatial interpolation is 10 m.
S102: using the wheat stripe rust satellite-ground synchronous observation data and the sentinel second image data to extract a vegetation index based on the phenological information after normalization, wherein the vegetation index based on the phenological information is used for representing the growth condition of wheat under the stress of stripe rust;
in a specific embodiment, the extracting vegetation index based on phenological information by using the wheat stripe rust satellite-ground synchronous observation data and the sentinel second image data includes:
estimating the jointing stage of the wheat according to the satellite-ground synchronous observation data of the wheat stripe rust by adopting a method of combining time series harmonic analysis with effective accumulated temperature; and extracting a vegetation index based on the phenological information by using the sentinel second image data, wherein the vegetation index based on the phenological information comprises: the vegetation index is normalized, the red-edge normalized vegetation index, the vegetation decay index, the red-edge disease stress index, the triangular vegetation index and the water and fertilizer stress index.
In a specific embodiment, after the data required by the technical scheme is obtained, 6 vegetation indexes sensitive to wheat stripe rust stress in the jointing stage are selected to represent the growth condition of wheat under stripe rust stress, and the detailed description of the vegetation indexes is shown in table 1.
TABLE 1 vegetation index for stripe rust prediction
In a specific embodiment, the estimating the wheat jointing stage according to the satellite-ground synchronous observation data of the wheat stripe rust by using the method of combining time series harmonic analysis and effective accumulated temperature includes:
acquiring an NDVI time sequence curve based on the NDVI time sequence images of the previous three years;
smoothing the NDVI time sequence curve by using S-G filtering, and fitting the smoothed NDVI time sequence curve by using a harmonic function;
extracting a green turning period and an elongation period of the first three years and a green turning period of a year to be predicted according to the growth characteristics of wheat, wherein the green turning period is a date when the rising rate of an NDVI (normalized difference vegetation index) time series curve is increased for the first time, and the elongation period is a date when the slope of the NDVI time series curve reaches the maximum value;
calculating the average effective accumulated temperature from the green turning period to the jointing period of the last three years based on the temperature data of the meteorological stations of the last three years, and estimating the jointing period of the wheat based on the temperature data of the meteorological stations of the years to be predicted by taking the effective accumulated temperature as a threshold value.
Then, the wheat jointing stage was estimated using this study using time series harmonic analysis in combination with the effective accumulated temperature method (fig. 4).
i. Based on the NDVI time sequence images from 2018 to 2020, smoothing an original NDVI time sequence curve by using S-G filtering, and fitting the smoothed NDVI time sequence curve by using a harmonic function;
extracting the green returning period and the jointing period in 2018-2020 and the green returning period in 2021 according to the growth characteristics of wheat: the green turning period is the date when the rising rate of the NDVI time sequence curve is increased for the first time; the jointing period is the date when the slope of the NDVI time sequence curve reaches the maximum value;
calculating the average effective accumulated temperature from the green turning period to the jointing period based on the temperature data of the meteorological stations from 2018 to 2020;
and iv, estimating the wheat jointing stage in the year 2021 based on the weather station temperature data in the year 2021 by taking the calculated average effective accumulated temperature from the green turning stage to the jointing stage in the years 2018 to 2020 as a threshold value.
In a specific embodiment, after the date of the wheat jointing stage is obtained, a vegetation index based on the phenological information is extracted by utilizing a time sequence sentinel second image; meanwhile, considering that the proportion of the pixels of day 17 and 3 months accounts for the most in all the pixels in the jointing stage prediction result, the remote sensing image of day 17 and 3 months is selected to calculate 6 vegetation indexes to represent the growth condition of the wheat in a single period.
To compare the response differences of the vegetation index extracted based on the phenological information and the vegetation index extracted in a single period to stripe rust, we normalized the two vegetation indexes and calculated the mean and standard deviation of their corresponding healthy wheat samples and stripe rust infected wheat samples (as in fig. 5, (a) vegetation index extracted based on the phenological information and (b) vegetation index mean and standard deviation in a single period after normalization. The PSRI, NDVI and TVI differences are small for vegetation index features extracted at a single time period. Under the two vegetation index calculation modes, PSRI, REDSI and DWSI show that the mean value of the healthy sample is larger than that of the yellow rust infected sample, and the difference of the vegetation index extracted based on the phenological information is more obvious. Furthermore, NDVI, NDVIre, TVI extracted based on the phenological information showed a normalized value for the healthy samples higher than that of the yellow rust infested samples, while NDVI and NDVIre of a single period showed opposite trends, with no significant difference in TVI. These results indicate that the vegetation index extracted based on the phenological information can effectively eliminate the interference caused by the difference in phenological stages, and better reflect the difference between healthy wheat and stripe rust infected wheat.
S103: extracting meteorological features by using the Chinese meteorological site data, wherein the meteorological features comprise: relative humidity of 12 months, illumination intensity of 1 month, rainfall of 1 month and rainfall of 7 days at present;
in the embodiment of the application, besides the growth condition of the host, the survival, propagation and infection of the puccinia striiformis needs a proper habitat, meteorological data of 12-2 months are selected, and the monthly average value (total 27 meteorological characteristics) of 9 meteorological elements corresponding to each month is respectively calculated to represent the habitat of the wheat in the wintering period. Then, with the ground survey date as the start time (4 months and 17 days), the habitat before the disease occurrence was characterized by calculating the average value (36 meteorological features in total) of 9 meteorological elements under 4 windows, with 1(4 months and 10 days to 4 months and 16 days), 2(4 months and 3 days to 4 months and 16 days), 3(3 months and 27 days to 4 months and 16 days), and 4(3 months and 20 days to 4 months and 16 days) weeks before the start time as the time windows. Finally, 63 meteorological features are calculated as candidate features.
Although the above meteorological features may be related to the occurrence of stripe rust, co-linearity that may exist between these features may affect the accuracy of the prediction model. In order to eliminate the influence and improve the prediction accuracy of the model, candidate features are screened by a correlation analysis and independent sample T test method to determine the optimal meteorological features.
Firstly, calculating the correlation between the candidate characteristics and the stripe rust by using an independent sample T test, and screening out the characteristics showing statistical significance (p value <0.001) by testing the difference between a healthy sample and a stripe rust sample; on the basis, calculating a correlation coefficient (R) between the features by utilizing correlation analysis, and removing the features of which the absolute value of the correlation coefficient between the features is greater than 0.9; finally, the finally reserved meteorological features are used as habitat factors, wherein the result of the independent sample T test is shown in the table 2, and the result of the correlation analysis is shown in the figure 6; finally, 4 meteorological features sensitive to stripe rust are screened, and the relative humidity (RHU _ M12) of 12 months, the light intensity (SSD _ M01) of 1 month, the rainfall (PRE _ M01) of 1 month and the rainfall (PRE _ B07) of 7 days before the forecast day are respectively most suitable for the wheat stripe rust forecast.
TABLE 2 significance of 63 candidate features calculated using independent sample T test
It should be noted that: m12, M01 and M02 respectively represent 12 months, 1 month and 2 months; b07, B14, B21, B28 represent 7, 14, 21, 28 days before the ground survey day, respectively; indicates that there was a significant difference in confidence level of 0.999 between healthy and stripe rust infested wheat (p value less than 0.001).
S104: and taking the vegetation index based on the phenological information and the meteorological features as input features, predicting the stripe rust occurrence condition of each pixel by using a wheat stripe rust prediction model, and drawing a stripe rust occurrence distribution diagram to realize the prediction of stripe rust.
After the prediction index of the stripe rust is extracted, a wheat stripe rust prediction model is constructed by using a Support Vector Machine (SVM) method and by using a vegetation index and meteorological features (PHVIs + MFs) extracted based on the phenological information as input features, the stripe rust occurrence condition of each pixel is predicted, and a stripe rust occurrence distribution diagram is drawn, so that the stripe rust prediction is realized.
In an embodiment of the application, the method for constructing the wheat stripe rust prediction model includes:
acquiring satellite-ground synchronous observation data of historical wheat stripe rust in an area to be predicted, historical sentinel second satellite image data and historical Chinese meteorological site data;
using the historical wheat stripe rust satellite-ground synchronous observation data and the historical sentinel second image data to extract a historical vegetation index based on the phenological information, wherein the historical vegetation index based on the phenological information is used for representing the growth condition of wheat under the stress of stripe rust;
extracting historical meteorological features by using the historical Chinese meteorological site data, wherein the meteorological features comprise: relative humidity of 12 months, illumination intensity of 1 month, rainfall of 1 month and rainfall of 7 days at present;
and constructing the wheat stripe rust prediction model based on an SVM method by using the historical vegetation index based on the climatic information and the historical meteorological characteristics.
In order to evaluate and compare the performance of the established prediction model, the embodiment of the application also constructs the SVM prediction model by respectively using the Vegetation Index (VIs) extracted based on the single-date image, the vegetation index (PHVIs) extracted based on the phenological information and the vegetation index extracted based on the single-date image and combining with the three feature sets of meteorological features (VIs + MFs). Table 3 shows the confusion matrix of the prediction results of the models, and the results show that the models (VIs + MFs and PHVIs + MFs) constructed by combining the vegetation indexes with meteorological features are superior to the models (VIs and PHVIs) constructed by the vegetation indexes, the overall accuracy is respectively 9.3% and 11.4%, and the Kappa coefficient is respectively 0.185 and 0.227. The results show that the accuracy of the prediction model can be remarkably improved by combining the vegetation index and the meteorological characteristics for predicting the crop diseases. In addition, the overall accuracy and Kappa coefficient of the prediction model constructed using PHVIs are better than those of the prediction model constructed using VIs by 7.2% and 0.144, respectively. The overall accuracy and Kappa coefficient of the prediction model constructed by using PHVIs + MFs are better than those of the prediction model constructed by VIs + MFs, and are respectively higher by 9.3% and 0.186. The results show that the vegetation index extracted based on the phenological information can effectively eliminate the influence of host growth condition change on stripe rust prediction caused by the phenological stage difference of wheat in a research area, and effectively improve the precision of a prediction model.
TABLE 3 confusion matrix of prediction model constructed based on SVM method
In order to verify the role of the SVM method in the construction of the prediction model, the stripe rust prediction model is constructed by combining 4 feature sets (VIs, PHVIs, VIs + MFs and PHVIs + MFs) with a classical Logistic method, a confusion matrix (table 4) of the prediction result is calculated, and the result shows that the Logistic prediction model based on the 4 feature sets presents a change trend consistent with the prediction model built by the SVM, namely in the wheat stripe rust prediction, the combination of the vegetation index and the meteorological feature is superior to a single type of feature. The vegetation index performance extracted based on the phenological information is superior to the vegetation index in a single period.
Table 4. confusion matrix of prediction model constructed based on Logistic method
By comparing table 3 and table 4, it can be seen that the prediction models established by combining the vegetation indexes extracted based on the phenological information with the meteorological features are the best of all models, except that under the same feature input, 4 prediction models established based on the SVM method are superior to the prediction models established based on the Logistic method, and the corresponding overall accuracy is respectively higher by 4.1% (VIs), 4.1% (PHVIs), 2.1% (VIs + MFs), and 4.2% (PHVIs + MFs). Through analysis, the applicant considers that the possible reason is that the support vector machine SVM which takes RBF as a kernel function has excellent performance under the condition of inseparability of linearity, and can capture the nonlinear relation between the occurrence of stripe rust and the vegetation index and meteorological features; meanwhile, the SVM method has good performance in small sample data set.
The above results illustrate the feasibility of using the SVM method provided in the embodiment of the present application to predict crop diseases by combining the vegetation index extracted based on the phenological information and the meteorological features.
In addition, the embodiment of the application predicts the occurrence of wheat stripe rust in the research area at 4 months and 17 days in 2021 by using an optimal prediction model, namely, an SVM prediction model based on PHVIs + MFs (fig. 7, the spatial distribution of wheat stripe rust in the research area is predicted by using a model constructed by combining vegetation index and meteorological features based on climatic information with SVM). The results show that the north boundary occurs more heavily than the south boundary. Researches show that the incidence rate of wheat stripe rust at the late development stage is generally higher than that of wheat at the early development stage, and the prediction result of the growth period shows that the phenological period at the north part is earlier than that at the south part. In addition, stripe rust occurs sporadically in most areas. In the western part of the Guanzhong province of China, stripe rust generally occurs in the stage of spot-ordering in the middle of 4 months, and if the stripe rust is not prevented in time, the stripe rust is epidemic, and large-area damage is caused. The prediction result of the embodiment of the application is highly consistent with the prevalence rule of stripe rust and the field investigation result. These results further prove that the stripe rust prediction method provided by the embodiment of the application has feasibility, and can provide timely and accurate guidance suggestions for plant protection departments, so that a great amount of labor, time and cost are saved.
By combining the experiments, it can be known that the detailed spatial distribution of the wheat stripe rust can be effectively predicted by constructing a prediction model combining the vegetation index based on the phenological information and the meteorological characteristics in the technical scheme of the embodiment of the application, early warning information is provided for farmers and plant protection departments, and a feasible scheme is provided for predicting the wheat stripe rust by combining satellite images and meteorological data.
The method for predicting the wheat stripe rust by coupling remote sensing and meteorological data comprises the steps of firstly, obtaining satellite-ground synchronous observation data of the wheat stripe rust of an area to be predicted, image data of a sentinel second satellite and Chinese meteorological site data; then, using the wheat stripe rust satellite-ground synchronous observation data and the sentinel second image data to extract a vegetation index based on the phenological information, wherein the vegetation index based on the phenological information is used for representing the growth condition of wheat under the stress of stripe rust; and then extracting meteorological features by using the Chinese meteorological site data, wherein the meteorological features comprise: relative humidity of 12 months, illumination intensity of 1 month, rainfall of 1 month and rainfall of 7 days at present; and finally, taking the vegetation index based on the phenological information and the meteorological features as input features, predicting the stripe rust occurrence condition of each pixel by using a wheat stripe rust prediction model, and drawing a stripe rust occurrence distribution diagram to realize the prediction of stripe rust.
The sentinel second satellite data is combined with meteorological data to predict the wheat stripe rust in a large range, and the sentinel second satellite data is different from the existing meteorological data-based disease trend prediction, so that the sentinel second satellite data is more suitable for practical application; compared with the existing prediction based on satellite data, the method can predict the occurrence position of the disease with high precision, and can provide precise guidance for actual pesticide spraying and plant protection management. In addition, the remote sensing feature extracted based on the physical and climate information is optimized for the problem that the precision of the model is reduced due to the growth period difference of the wheat in the actual field management, and compared with the existing remote sensing feature based on a single period, the remote sensing feature can provide a high-precision prediction index reference for the stripe rust.
Referring to fig. 8, based on the method for predicting wheat stripe rust by coupling remote sensing and meteorological data disclosed in the above embodiment, the embodiment correspondingly discloses a device for predicting wheat stripe rust by coupling remote sensing and meteorological data, the device comprising:
the first processing unit 801 is used for acquiring satellite-ground synchronous observation data of wheat stripe rust in an area to be predicted, sentinel second satellite image data and national meteorological site data;
the second processing unit 802 is configured to extract a vegetation index based on the phenological information by using the wheat stripe rust satellite-ground synchronous observation data and the sentinel second image data, where the vegetation index based on the phenological information is used for representing the growth condition of wheat under stripe rust stress;
a third processing unit 803, configured to extract meteorological features using the chinese meteorological site data, where the meteorological features include: relative humidity of 12 months, illumination intensity of 1 month, rainfall of 1 month and rainfall of 7 days at present;
and the fourth processing unit 804 is configured to predict the stripe rust occurrence situation of each pixel by using the vegetation index based on the phenological information and the meteorological features as input features, and draw a stripe rust occurrence distribution map to realize the prediction of stripe rust.
Wherein the second processing unit 802 is specifically configured to:
estimating the jointing stage of the wheat according to the satellite-ground synchronous observation data of the wheat stripe rust by adopting a method of combining time series harmonic analysis with effective accumulated temperature;
and extracting a vegetation index based on the phenological information by using the sentinel second image data, wherein the vegetation index based on the phenological information comprises: the vegetation index is normalized, the red-edge normalized vegetation index, the vegetation decay index, the red-edge disease stress index, the triangular vegetation index and the water and fertilizer stress index.
Wherein the second processing unit 802 is further specifically configured to:
based on NDVI time sequence images of the previous three years, an NDVI time sequence curve is obtained;
smoothing the NDVI time sequence curve by using S-G filtering, and fitting the smoothed NDVI time sequence curve by using a harmonic function;
extracting a green turning period and an elongation period of the first three years and a green turning period of a year to be predicted according to the growth characteristics of wheat, wherein the green turning period is a date when the rising rate of an NDVI (normalized difference vegetation index) time series curve is increased for the first time, and the elongation period is a date when the slope of the NDVI time series curve reaches the maximum value;
calculating the average effective accumulated temperature from the green turning period to the jointing period of the last three years based on the temperature data of the meteorological stations of the last three years, and estimating the jointing period of the wheat based on the temperature data of the meteorological stations of the years to be predicted by taking the effective accumulated temperature as a threshold value.
Wherein, the fourth processing unit 804 is further specifically configured to:
acquiring satellite-ground synchronous observation data of historical wheat stripe rust in an area to be predicted, historical sentinel second satellite image data and historical Chinese meteorological site data;
using the historical wheat stripe rust satellite-ground synchronous observation data and the historical sentinel second image data to extract a historical vegetation index based on the phenological information, wherein the historical vegetation index based on the phenological information is used for representing the growth condition of wheat under the stress of stripe rust;
extracting historical meteorological features by using the historical Chinese meteorological site data, wherein the meteorological features comprise: relative humidity of 12 months, illumination intensity of 1 month, rainfall of 1 month and rainfall of 7 days at present;
and constructing the wheat stripe rust prediction model based on an SVM method by using the historical vegetation index based on the climatic information and the historical meteorological characteristics.
The wheat stripe rust prediction device coupled with remote sensing and meteorological data comprises a processor and a memory, wherein the first processing unit, the second processing unit, the third processing unit, the fourth processing unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. The kernel can be set to be one or more than one, the vegetation index based on the phenological information and the meteorological characteristics sensitive to the stripe rust are extracted based on the time sequence remote sensing image and the meteorological data by adjusting the kernel parameters, and the regional wheat stripe rust prediction is realized by constructing a wheat stripe rust prediction model combining the vegetation index with the meteorological characteristics.
The embodiment of the application provides a storage medium, wherein a program is stored on the storage medium, and when the program is executed by a processor, the method for predicting the wheat stripe rust of the coupled remote sensing and meteorological data is realized.
The embodiment of the application provides a processor, wherein the processor is used for running a program, and the program runs to execute the wheat stripe rust prediction method by coupling remote sensing and meteorological data.
An electronic device is provided in the embodiments of the present application, as shown in fig. 9, the electronic device 90 includes at least one processor 901, at least one memory 902 connected to the processor, and a bus 903; the processor 901 and the memory 902 complete communication with each other through the bus 903; the processor 901 is configured to call the program instructions in the memory 902 to execute the method for predicting wheat stripe rust by coupling remote sensing and meteorological data.
The electronic device herein may be a server, a PC, a PAD, a mobile phone, etc.
The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device:
acquiring satellite-ground synchronous observation data of wheat stripe rust in a region to be predicted, sentinel second satellite image data and Chinese meteorological site data;
using the wheat stripe rust satellite-ground synchronous observation data and the sentinel second image data to extract a vegetation index based on the phenological information, wherein the vegetation index based on the phenological information is used for representing the growth condition of wheat under the stress of stripe rust;
extracting meteorological features by using the Chinese meteorological site data, wherein the meteorological features comprise: relative humidity of 12 months, illumination intensity of 1 month, rainfall of 1 month and rainfall of 7 days at present;
and taking the vegetation index based on the phenological information and the meteorological features as input features, predicting the stripe rust occurrence condition of each pixel by using a wheat stripe rust prediction model, and drawing a stripe rust occurrence distribution diagram to realize the prediction of stripe rust.
Wherein, the vegetation index based on the phenological information is extracted by using the wheat stripe rust satellite-ground synchronous observation data and the sentinel second image data, and comprises the following steps:
estimating the jointing stage of the wheat according to the satellite-ground synchronous observation data of the wheat stripe rust by adopting a method of combining time series harmonic analysis with effective accumulated temperature;
and extracting a vegetation index based on the phenological information by using the sentinel second image data, wherein the vegetation index based on the phenological information comprises: the vegetation index is normalized, the red-edge normalized vegetation index, the vegetation decay index, the red-edge disease stress index, the triangular vegetation index and the water and fertilizer stress index.
Wherein, the method for estimating the wheat jointing stage according to the satellite-ground synchronous observation data of the wheat stripe rust by adopting the time series harmonic analysis and combining with the effective accumulated temperature comprises the following steps:
acquiring an NDVI time sequence curve based on the NDVI time sequence images of the previous three years;
smoothing the NDVI time sequence curve by using S-G filtering, and fitting the smoothed NDVI time sequence curve by using a harmonic function;
extracting a green turning period and a jointing period of the first three years and a green turning period of a year to be predicted according to the growth characteristics of wheat, wherein the green turning period is the date that the rising rate of an NDVI (normalized difference vegetation index) time sequence curve is increased for the first time, and the jointing period is the date that the slope of the NDVI time sequence curve reaches the maximum value;
calculating the average effective accumulated temperature from the green turning period to the jointing period of the last three years based on the temperature data of the meteorological stations of the last three years, and estimating the jointing period of the wheat based on the temperature data of the meteorological stations of the years to be predicted by taking the effective accumulated temperature as a threshold value.
The construction method of the wheat stripe rust prediction model comprises the following steps:
acquiring satellite-ground synchronous observation data of historical wheat stripe rust in an area to be predicted, historical sentinel second satellite image data and historical Chinese meteorological site data;
using the historical wheat stripe rust satellite-ground synchronous observation data and the historical sentinel second image data to extract a historical vegetation index based on the phenological information, wherein the historical vegetation index based on the phenological information is used for representing the growth condition of wheat under the stress of stripe rust;
extracting historical meteorological features by using the historical Chinese meteorological site data, wherein the meteorological features comprise: relative humidity of 12 months, illumination intensity of 1 month, rainfall of 1 month and rainfall of 7 days at present;
and constructing the wheat stripe rust prediction model based on an SVM method by using the historical vegetation index based on the climatic information and the historical meteorological characteristics.
The present application is described in terms of flowcharts and/or block diagrams of methods, apparatus (systems), computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a device includes one or more processors (CPUs), memory, and a bus. The device may also include input/output interfaces, network interfaces, and the like.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip. The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A wheat stripe rust prediction method coupling remote sensing and meteorological data is characterized by comprising the following steps:
acquiring satellite-ground synchronous observation data of wheat stripe rust in a region to be predicted, sentinel second satellite image data and Chinese meteorological site data;
using the wheat stripe rust satellite-ground synchronous observation data and the sentinel second image data to extract a vegetation index based on the phenological information, wherein the vegetation index based on the phenological information is used for representing the growth condition of wheat under the stress of stripe rust;
extracting meteorological features by using the Chinese meteorological site data, wherein the meteorological features comprise: relative humidity of 12 months, illumination intensity of 1 month, rainfall of 1 month, and rainfall of 7 days before the predicted day;
and taking the vegetation index based on the phenological information and the meteorological features as input features, predicting the stripe rust occurrence condition of each pixel by using a wheat stripe rust prediction model, and drawing a stripe rust occurrence distribution diagram to realize the prediction of stripe rust.
2. The method as claimed in claim 1, wherein the extracting vegetation index based on phenological information using the wheat stripe rust geosynchronous observation data and the sentinel number two image data comprises:
estimating the jointing stage of the wheat according to the satellite-ground synchronous observation data of the wheat stripe rust by adopting a method of combining time series harmonic analysis with effective accumulated temperature;
and extracting a vegetation index based on the phenological information by using the sentinel second image data, wherein the vegetation index based on the phenological information comprises: the vegetation index is normalized, the red-edge normalized vegetation index, the vegetation decay index, the red-edge disease stress index, the triangular vegetation index and the water and fertilizer stress index.
3. The method of claim 2, wherein estimating the wheat jointing stage from the satellite-to-satellite observation of the wheat stripe rust by the method of time-series harmonic analysis combined with effective accumulated temperature comprises:
acquiring an NDVI time sequence curve based on the NDVI time sequence images of the previous three years;
smoothing the NDVI time sequence curve by using S-G filtering, and fitting the smoothed NDVI time sequence curve by using a harmonic function;
extracting a green turning period and an elongation period of the first three years and a green turning period of a year to be predicted according to the growth characteristics of wheat, wherein the green turning period is a date when the rising rate of an NDVI (normalized difference vegetation index) time series curve is increased for the first time, and the elongation period is a date when the slope of the NDVI time series curve reaches the maximum value;
calculating the average effective accumulated temperature from the green turning period to the jointing period of the last three years based on the temperature data of the meteorological stations of the last three years, and estimating the jointing period of the wheat based on the temperature data of the meteorological stations of the years to be predicted by taking the effective accumulated temperature as a threshold value.
4. The method of claim 1, wherein the wheat stripe rust prediction model is constructed by a method comprising:
acquiring satellite-ground synchronous observation data of historical wheat stripe rust in an area to be predicted, historical sentinel second satellite image data and historical Chinese meteorological site data;
using the historical wheat stripe rust satellite-ground synchronous observation data and the historical sentinel second image data to extract a historical vegetation index based on the phenological information, wherein the historical vegetation index based on the phenological information is used for representing the growth condition of wheat under the stress of stripe rust;
extracting historical meteorological features by using the historical Chinese meteorological site data, wherein the meteorological features comprise: relative humidity of 12 months, illumination intensity of 1 month, rainfall of 1 month and rainfall of 7 days at present;
and constructing the wheat stripe rust prediction model based on an SVM method by using the historical vegetation index based on the climatic information and the historical meteorological characteristics.
5. A wheat stripe rust prediction device of coupling remote sensing and meteorological data characterized in that includes:
the first processing unit is used for acquiring satellite-ground synchronous observation data of the wheat stripe rust in the area to be predicted, sentinel second satellite image data and Chinese meteorological station data;
the second processing unit is used for extracting a vegetation index based on the phenological information by using the wheat stripe rust satellite-ground synchronous observation data and the sentinel second image data, and the vegetation index based on the phenological information is used for representing the growth condition of wheat under stripe rust stress;
the third processing unit is used for extracting meteorological features by using the China meteorological site data, and the meteorological features comprise: relative humidity of 12 months, illumination intensity of 1 month, rainfall of 1 month and rainfall of 7 days at present;
and the fourth processing unit is used for predicting the stripe rust occurrence condition of each pixel by using the vegetation index based on the physical and weather information and the meteorological features as input features and by using a wheat stripe rust prediction model, and drawing a stripe rust occurrence distribution diagram so as to realize the prediction of stripe rust.
6. The apparatus according to claim 5, wherein the second processing unit is specifically configured to:
estimating the jointing stage of the wheat according to the satellite-ground synchronous observation data of the wheat stripe rust by adopting a method of combining time series harmonic analysis with effective accumulated temperature;
and extracting a vegetation index based on the phenological information by using the sentinel second image data, wherein the vegetation index based on the phenological information comprises: the vegetation index is normalized, the red-edge normalized vegetation index, the vegetation decay index, the red-edge disease stress index, the triangular vegetation index and the water and fertilizer stress index.
7. The apparatus according to claim 6, wherein the second processing unit is further configured to:
acquiring an NDVI time sequence curve based on the NDVI time sequence images of the previous three years;
smoothing the NDVI time sequence curve by using S-G filtering, and fitting the smoothed NDVI time sequence curve by using a harmonic function;
extracting a green turning period and an elongation period of the first three years and a green turning period of a year to be predicted according to the growth characteristics of wheat, wherein the green turning period is a date when the rising rate of an NDVI (normalized difference vegetation index) time series curve is increased for the first time, and the elongation period is a date when the slope of the NDVI time series curve reaches the maximum value;
calculating the average effective accumulated temperature from the green turning period to the jointing period of the last three years based on the temperature data of the meteorological stations of the last three years, and estimating the jointing period of the wheat based on the temperature data of the meteorological stations of the years to be predicted by taking the effective accumulated temperature as a threshold value.
8. The apparatus according to claim 5, wherein the fourth processing unit is further configured to:
acquiring satellite-ground synchronous observation data of historical wheat stripe rust in an area to be predicted, historical sentinel second satellite image data and historical Chinese meteorological site data;
using the historical wheat stripe rust satellite-ground synchronous observation data and the historical sentinel second image data to extract a historical vegetation index based on the phenological information, wherein the historical vegetation index based on the phenological information is used for representing the growth condition of wheat under the stress of stripe rust;
extracting historical meteorological features by using the historical Chinese meteorological site data, wherein the meteorological features comprise: relative humidity of 12 months, illumination intensity of 1 month, rainfall of 1 month and rainfall of 7 days at present;
and constructing the wheat stripe rust prediction model based on an SVM method by using the historical vegetation index based on the climatic information and the historical meteorological characteristics.
9. A storage medium comprising a stored program, wherein the program, when executed, controls a device on which the storage medium resides to perform the method of wheat stripe rust prediction coupled with remote sensing and meteorological data of any one of claims 1 to 4.
10. An electronic device comprising at least one processor, and at least one memory, bus connected to the processor; the processor and the memory are communicated with each other through the bus; the processor is configured to invoke program instructions in the memory to perform the method of wheat stripe rust prediction coupled with remote sensing and meteorological data of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210508506.8A CN114842338A (en) | 2022-05-11 | 2022-05-11 | Wheat stripe rust prediction method and device based on coupling of remote sensing and meteorological data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210508506.8A CN114842338A (en) | 2022-05-11 | 2022-05-11 | Wheat stripe rust prediction method and device based on coupling of remote sensing and meteorological data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114842338A true CN114842338A (en) | 2022-08-02 |
Family
ID=82570736
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210508506.8A Pending CN114842338A (en) | 2022-05-11 | 2022-05-11 | Wheat stripe rust prediction method and device based on coupling of remote sensing and meteorological data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114842338A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115965875A (en) * | 2023-03-16 | 2023-04-14 | 德阳稷农农业科技有限公司 | Intelligent monitoring method and system for crop diseases and insect pests |
| CN117557905A (en) * | 2023-11-15 | 2024-02-13 | 杭州沣图科技有限公司 | Remote sensing method for regional wheat stripe rust based on geographic detector |
-
2022
- 2022-05-11 CN CN202210508506.8A patent/CN114842338A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115965875A (en) * | 2023-03-16 | 2023-04-14 | 德阳稷农农业科技有限公司 | Intelligent monitoring method and system for crop diseases and insect pests |
| CN117557905A (en) * | 2023-11-15 | 2024-02-13 | 杭州沣图科技有限公司 | Remote sensing method for regional wheat stripe rust based on geographic detector |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Large-scale crop mapping from multisource remote sensing images in *** earth engine | |
| CN103034910B (en) | Based on the regional scale disease and pest Forecasting Methodology of multi-source information | |
| Cunha et al. | Very early prediction of wine yield based on satellite data from VEGETATION | |
| Zhang et al. | Integrating remotely sensed and meteorological observations to forecast wheat powdery mildew at a regional scale | |
| CN111368736B (en) | Rice refined estimation method based on SAR and optical remote sensing data | |
| CN109711102B (en) | Method for rapidly evaluating crop disaster loss | |
| Kordi et al. | Crop classification based on phenology information by using time series of optical and synthetic-aperture radar images | |
| Conrad et al. | Satellite based calculation of spatially distributed crop water requirements for cotton and wheat cultivation in Fergana Valley, Uzbekistan | |
| CN114842338A (en) | Wheat stripe rust prediction method and device based on coupling of remote sensing and meteorological data | |
| CN111768051B (en) | Wheat scab dynamic early warning method and device | |
| Wang et al. | Integrating remote sensing-based process model with environmental zonation scheme to estimate rice yield gap in Northeast China | |
| Pang et al. | Pixel-level rice planting information monitoring in Fujin City based on time-series SAR imagery | |
| Mumtaz et al. | Analysis of meteorological variations on wheat yield and its estimation using remotely sensed data. A case study of selected districts of Punjab Province, Pakistan (2001-14) | |
| CN116665073A (en) | Corn yield remote sensing estimation method based on multi-source data | |
| CN115062863B (en) | Apple flowering phase prediction method based on crop reference curve and accumulated temperature correction | |
| Park et al. | Integrated model for predicting rice yield with climate change | |
| CN112819227A (en) | County scale winter wheat yield per unit prediction method and system | |
| Kerry et al. | Investigating temporal and spatial patterns of cranberry yield in New Jersey fields | |
| Zhu et al. | Assessment of the world largest afforestation program: success, failure, and future directions | |
| Luintel et al. | Tracking the dynamics of paddy rice cultivation practice through MODIS time series and PhenoRice algorithm | |
| CN107437262B (en) | Crop planting area early warning method and system | |
| CN107491724B (en) | A kind of Spike Differentiation in Winter Wheat phase recognition methods and device | |
| Tsujimoto et al. | Estimation of planting date in paddy fields by time-series MODIS data for basin-scale rice production modeling | |
| Ji et al. | Integrating the temperature vegetation dryness index and meteorology parameters to dynamically predict crop yield with fixed date intervals using an integral regression model | |
| Zhang et al. | Effects of direct heat stress on summer maize and risk assessment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |