CN111797186A - Method for inverting COD (chemical oxygen demand) of water body by remote sensing - Google Patents
Method for inverting COD (chemical oxygen demand) of water body by remote sensing Download PDFInfo
- Publication number
- CN111797186A CN111797186A CN202010551807.XA CN202010551807A CN111797186A CN 111797186 A CN111797186 A CN 111797186A CN 202010551807 A CN202010551807 A CN 202010551807A CN 111797186 A CN111797186 A CN 111797186A
- Authority
- CN
- China
- Prior art keywords
- water quality
- water
- remote sensing
- cod
- water body
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 128
- 238000000034 method Methods 0.000 title claims abstract description 32
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 title description 5
- 229910052760 oxygen Inorganic materials 0.000 title description 5
- 239000001301 oxygen Substances 0.000 title description 5
- 239000000126 substance Substances 0.000 title description 5
- 238000012544 monitoring process Methods 0.000 claims abstract description 33
- 238000010801 machine learning Methods 0.000 claims abstract description 14
- 238000005070 sampling Methods 0.000 claims description 38
- 238000011160 research Methods 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 4
- 238000003911 water pollution Methods 0.000 abstract description 4
- 238000012952 Resampling Methods 0.000 abstract description 3
- 238000004422 calculation algorithm Methods 0.000 abstract description 3
- 238000012937 correction Methods 0.000 abstract description 3
- 238000007637 random forest analysis Methods 0.000 abstract description 3
- 238000012706 support-vector machine Methods 0.000 abstract description 3
- 238000013528 artificial neural network Methods 0.000 abstract description 2
- 238000005259 measurement Methods 0.000 abstract description 2
- 238000007781 pre-processing Methods 0.000 abstract 1
- 230000001360 synchronised effect Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 230000007613 environmental effect Effects 0.000 description 3
- 238000002310 reflectometry Methods 0.000 description 3
- 230000003595 spectral effect Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 229930002868 chlorophyll a Natural products 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
- 238000010276 construction Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000004836 empirical method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012851 eutrophication Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000007620 mathematical function Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000002957 persistent organic pollutant Substances 0.000 description 1
- 238000000746 purification Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000005211 surface analysis Methods 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/05—Geographic models
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Remote Sensing (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Computer Graphics (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention relates to the field of water pollution treatment, and discloses a method for inverting COD of a water body by remote sensing, which constructs a water quality parameter inversion model by means of a sentinel No. 2 remote sensing image with high space-time resolution, preprocessing measures such as radiometric calibration, atmospheric correction and resampling and combining with synchronous water body actual measurement data and by utilizing an ArcGIS space analysis tool and a Random Forest (RF) and support vector machine (SVR) Neural Network (NNs) machine learning algorithm, realizes quick determination of COD indexes of the water body, and meets the requirement of monitoring the water quality of a small urban water body.
Description
Technical Field
The invention relates to the field of water pollution treatment, in particular to a method for inverting COD (chemical oxygen demand) of a water body by remote sensing.
Background
Water is an indispensable resource for human and other organisms to live and social sustainable development, and the quality of water influences the quality of human survival and development. With the rapid development of economy, organic pollutants are discharged in large quantities in urban rivers and lakes, the content of organic matters in urban water ecological systems is increased rapidly, and urban water bodies represented by urban inland rivers form serious environmental problems such as water eutrophication and black and odorous water bodies due to the characteristics of small environmental capacity, poor self-purification capacity and the like. At present, for urban water management departments and environmental protection departments, the water monitoring means still mainly takes the traditional 'field water sample collection for laboratory water quality parameter determination'. Although the monitoring method has higher precision, the monitoring method can only know monitoring points and water quality conditions in a limited range, and cannot reflect the space-time change of the ecological environment of a large-area water body. In addition, the traditional water body monitoring method is complex to operate, high in time and economic cost and difficult to achieve real-time monitoring requirements. Although there are many portable water quality monitors on the market at present, some devices can realize real-time monitoring through a data transmission module, but the monitoring indexes of the devices mostly focus on some conventional water quality indexes such as pH, water temperature, conductivity, dissolved oxygen and the like. Indexes capable of better representing urban water pollution, such as COD, are still difficult to realize. Moreover, the monitoring results of these devices can only reflect the water quality conditions at the monitoring points and in a limited range, and the water quality monitoring of large-area water areas cannot be carried out. Based on the above analysis, the existing water quality monitoring method obviously cannot meet the requirements of rapid urban water pollution identification, efficient early warning and scientific management, so that a rapid, convenient, efficient and comprehensive urban water quality monitoring method is urgently needed.
With the development of remote sensing technology, remote sensing monitoring of water quality becomes possible. From the existing research, the commonly used satellite remote sensing data comprises TM/ETM +, OLI data of Landsat satellite, MODIS data of Terra and Aqua satellite, HRV data of SPOT satellite, LISS data of IRS system, AVHRR data of meteorological satellite NOAA and the like. Among them, TM/ETM + and OLI data have become the most widely used multispectral data in remote sensing monitoring of water quality at present because of their higher spatial resolution and spectral resolution. Scholars at home and abroad develop a great deal of research by using the data, and obtain ideal results in the aspects of estimation of chlorophyll a concentration, suspended matter concentration, yellow substance and transparency. However, the updating period of the data is as long as 16 days, so that the method is not suitable for monitoring and early warning the water quality of small urban water bodies. MODIS data has the advantages of short observation period (1day), high spectral resolution, free global acquisition and the like, and receives more and more attention in water quality monitoring research. However, the spatial resolution is as high as 250 meters, and the urban water area is generally small, so that the method is not suitable for monitoring the urban water quality.
The successful transmission of the high-resolution commercial satellite also provides remote sensing data with higher spatial resolution for water quality monitoring, and the spatial resolution of IKONOS and Quickbird data respectively reaches 1m and 0.61 m. But is limited by the economic cost of data acquisition and is not suitable for daily water quality monitoring. The hyperspectral image can provide a large amount of narrow-band continuous spectrum image data, and richer spectral characteristic data are provided for remote sensing inversion of water quality. However, satellite-borne hyperspectral data (such as Hyperion and CHRIS) belong to experimental data at present. The coverage range of airborne hyperspectral data (such as AVIRIS, CASI, CIS and the like) is small, and the monitoring cost is high. Therefore, the hyperspectral data at the present stage are not suitable for long-term and continuous urban small water quality monitoring.
Disclosure of Invention
Based on the problems, the invention provides a method for inverting COD of a water body by remote sensing, which aims to solve the problems of high cost and low efficiency of the existing monitoring of small urban water body lakes; by introducing machine learning into an empirical method for inverting water quality by remote sensing and training a machine by using the accumulated remote sensing data and water quality parameter data, the machine has the capability of predicting water quality parameters by using the remote sensing data in the future, thereby realizing the rapid determination of COD (chemical oxygen demand) indexes of the water body and meeting the requirement of monitoring the water quality of small urban water bodies.
The invention is realized by the following technical scheme:
a method for inverting COD of water body by remote sensing comprises the following steps,
(1) acquiring water body monitoring data:
uniformly arranging sampling points on the lake surface by adopting a grid method, wherein the density of the sampling points is 0.03 point/km 2; according to the transit time of the sentinel No. 2 satellite, collecting a water sample by using an unmanned ship, wherein the sampling depth is 30-50 cm; collecting a water sample, filling the water sample into a brown bottle, and measuring water quality parameters;
secondly, the weather is required to be clear during sampling, the wind power is less than 3 grades, no cloud exists above the lake surface, and the satellite transit time interval of the sampling time is less than 4 hours;
thirdly, selecting 4 spatial interpolation methods according to data characteristics by using a spatial interpolation tool of ArcGIS10.4 to interpolate the water quality parameters; selecting an optimal interpolation result, and generating 1000 new sampling points in the range of the interpolation result by utilizing a fishernet tool of ArcGIS 10.4;
ensuring that the distance between every 2 sampling points is more than 10 meters in the generation process; respectively extracting water quality parameters to obtain water quality parameter values of 2000 sampling points;
(2) satellite data processing
Extracting pixel values of the remote sensing images by using the water quality parameter values of the sampling points to obtain pixel value data sets of 2000 points, and forming a data set of the research with the water quality parameters of 2000 points; extracting pixel values of the whole lake surface by using a region of interest (ROI) of the whole lake surface as input variables predicted by a machine learning model;
(3) remote sensing inversion water body COD index
Respectively training three machine learning models of RF, SVR and NNs, verifying the performance of the models on a test set by utilizing R2 and RMSE, adjusting the hyper-parameters of the models, and finally determining the optimal model for inverting each water quality parameter; and importing the pixel values of the remote sensing images of all the data sets into the finally determined model, and predicting the water quality parameters corresponding to the pixel values.
As a preferable mode, in step (2), 4 bands with 20m resolution of the image are resampled to be 10m, and 8 water quality parameter sensitive bands with 10m resolution are obtained for water quality parameter inversion. This preferred approach solves the problem that pixels of different grids are not always aligned due to the relative offsets between pixel boundaries that occur for different pixel sizes.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1. the invention adopts the high space-time resolution data of the sentinel No. 2, and provides possibility for monitoring the water quality of the urban small water body compared with the data of TM/ETM +, MODIS and the like. Meanwhile, by means of a geographic information space technical means, a lake water body monitoring sample with a high sample volume is generated on the basis of actually measured water quality parameters, so that the problem that the usually actually measured water quality parameter data of small-sized water bodies in cities are insufficient is solved.
2. In order to further improve the accuracy of remote sensing inversion of COD, the invention enters machine learning algorithms such as random forests, support vector machines, neural networks and the like, trains machines by utilizing the accumulated remote sensing data and water quality parameter data, enables the machines to have the capability of predicting water quality parameters by utilizing the remote sensing data in the future, tries to complete a complex physical analysis process by delivering the complex physical analysis process to the machines, and enables the water quality monitoring process to be simpler and more convenient and more accurate, and the monitoring result is higher in accuracy.
Drawings
Fig. 1 is a distribution diagram of measured water quality parameters of sampling points in the present embodiment;
FIG. 2 is a schematic diagram of a local polynomial interpolation Y in this embodiment;
FIG. 3 is a schematic diagram of inverse distance weight interpolation in the present embodiment;
FIG. 4 is a schematic diagram of a common kriging and simple kriging in this embodiment;
FIG. 5 is a Root Mean Square Error (RMSE) chart of water quality parameters for different interpolation methods in this example;
FIG. 6 is a comparison graph of COD inversion accuracy and three optimization models by three machine learning algorithms;
fig. 7 is a comparison of measured water quality parameters and predicted water quality parameters.
Detailed Description
The following examples are given for further details, but the embodiments of the present invention are not limited thereto:
a method for inverting COD of a water body by remote sensing comprises the following steps:
(1) acquiring water body monitoring data: selecting Bohai dragon lake as a research area, uniformly arranging 20 sampling points on the surface of the Bohai dragon lake by adopting a grid method, wherein the density of the sampling points is 0.03 point/km2. According to transit time of the sentinel second satellite, water sample collection is carried out for 2 times by using the unmanned ship in 20 May and 9 th in 2019 respectively, 40 water samples are collected totally, and the sampling depth is 30-50cm (the sampling point position is shown in figure 1). The weather is clear during sampling, the wind power is less than 3 grades, no cloud exists above the lake surface, and the interval between the sampling time and the satellite transit time is less than 4 hours. Quickly filling the collected water sample into a brown bottle to avoid the sunshine, and sending the water sample to a laboratory as soon as possibleMeasuring water quality parameters; and secondly, selecting 4 spatial interpolation methods according to data characteristics by using a spatial interpolation tool of ArcGIS10.4 to interpolate the water quality parameters. And selecting an optimal interpolation result, and generating 1000 new sampling points in the range of the interpolation result by using a fishernet tool of ArcGIS 10.4. And in the generation process, the distance between every 2 sampling points is ensured to be larger than 10 meters, and 2 sampling points in one pixel are avoided. And respectively extracting water quality parameters to obtain water quality parameter values of 2000 sampling points.
(2) Satellite data processing: firstly, downloading the No. 2 satellite image of the sentinel at the water body monitoring time period, wherein the image is subjected to geometric correction. And (3) carrying out radiometric calibration and atmospheric correction on the image by utilizing sen2cor software released by the sentinel officer to obtain data of the L2A level. Resampling the wave bands by using SNAP (selective non-access point) for water quality parameter inversion, resampling 4 wave bands with 20m resolution ratio to 10m, and obtaining 8 water quality parameter sensitive wave bands with 10m resolution ratio for water quality parameter inversion; ② in ENVI5.5, extracting the region of interest of the project. And extracting pixel values of the image by using the water quality parameter values of the sampling points to obtain a pixel value data set of 2000 points, and forming a data set for the research with the water quality parameters of 2000 points. And extracting pixel values of the whole lake surface by using the interesting regions of the whole lake surface to serve as input variables predicted by the machine learning model.
(3) Remote sensing inversion water COD index: respectively training three machine learning models of RF, SVR and NNs, and utilizing R2And RMSE verifies the performance of the model on the test set, adjusts the hyper-parameters of the model, and finally determines the optimal model for each water quality parameter inversion. And importing the pixel values of the remote sensing images of all the data sets into the finally determined model, and predicting the water quality parameters corresponding to the pixel values.
And (4) analyzing results:
1. water body COD on-site sampling and spatial interpolation result
The atmospheric underlayer reflectivity corresponding to the water quality sampling point No. 5/month 20 and No. 6/month 9 extracted by the ENVI5.5 tool is as follows: atmospheric base reflectance of 20 days 5 months in 2019 and table 2 below: atmospheric underlayer reflectance at 6 months and 9 days in 2019, table 1: atmospheric bottom layer reflectivity of 20 days in 5 months in 2019
Table 2: reflectivity of atmospheric bottom layer in 6/9/2019
And (5) carrying out variation detection on the actually measured water quality parameter by means of the half variation variance cloud and the histogram of ArcGIIS10.4. After the average value is used for replacing the abnormal value, a water quality parameter distribution graph of 40 sampling points in total is generated after 2 times of sampling, and the result is shown in fig. 1. In 2019, 5 months and 20 days, the average value of COD is 17.96mg/L, and the high value is mainly distributed in the eastern part of the lake. In 20 days 6 months in 2019, the average value of COD is increased to 26.86mg/L, and the high values are mainly distributed in the eastern part of the lake.
According to the data characteristics, four methods of local polynomial, inverse distance weight, common kriging and simple kriging are simultaneously selected to carry out spatial interpolation on the COD water sample data. Local polynomial interpolation fits using multiple polynomials located within a specified overlapping neighborhood. The search neighborhood can be defined by size and shape, adjacent element number and sector configuration, bandwidth, space condition number and search neighborhood value are synchronously changed by using exploratory trend surface analysis parameters, and the principle is shown in fig. 2; inverse distance weight interpolation uses a linear weight set of a set of sample points to determine the pixel value, the principle is shown in fig. 3; both the common kriging method and the simple kriging method assume that the distance or direction between sampling points can reflect the spatial correlation that can be used to account for surface variations, and a mathematical function is fitted to a specified number of points or all points within a specified radius to determine the output value for each position, as shown in fig. 4, except that the two interpolation methods use a semi-variogram that is different.
Interpolation accuracy was evaluated using mean error and RMSE, both of which are averages of 20 cross-validations. The mean errors in this study were all very close to 0, with the RMSE shown in figure 5. As can be seen from fig. 5, the spatial interpolation precision of different water quality parameters at the same sampling time is different from the spatial interpolation precision of different sampling times of the same water quality parameter. In 2019, 5, 20 days, the optimal spatial interpolation RMSE of COD is 11.4329 mg/L.
2. Water body COD parameter machine learning model construction
Training RF, SVR, NNS models separately, Using R2And the RMSE tests the performance of the model on the test set, adjusts the parameters of the model according to the test result and finally determines the optimal model of each water quality parameter. And importing the DN data set of the image into each model, and predicting the corresponding water quality parameters. The water quality parameters predicted by the model are compared with the water quality parameters extracted from the spatial interpolation result, and a scatter diagram is obtained as shown in fig. 6. As can be seen from fig. 6, all three machine learning models exhibit better accuracy. R of SVR and NNs2The same is 0.754, but the RMSE of SVR is slightly lower than NNs, and the model precision is better. R of RF2And RMSE reached 0.722 and 4.378mg/L, respectively, which were slightly lower than SVR and NNs. The scattergrams of the COD water quality parameters were all clearly clustered in two distinct regions, with COD and turbidity being 17.45mg/L at 6 months and 9 days significantly lower than 31.70mg/L at 5 months and 20 days.
3. Comparing the model prediction result with the actual measurement result
The measured water quality parameters obtained by two sampling steps and the predicted COD parameters obtained by two steps of spatial interpolation and machine learning model are compared, and the result is shown in FIG. 7. As can be seen from FIG. 7, the measured value of the COD water quality parameter and the predicted result are kept to have a precision which is more consistent with the spatial interpolation and the machine learning model, and R2 and RMSE are respectively 0.731 mg/L and 4.585 mg/L.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (2)
1. A method for inverting COD of a water body by remote sensing comprises the following steps:
(1) acquiring water body monitoring data:
uniformly arranging sampling points on the lake surface by adopting a grid method, wherein the density of the sampling points is 0.03 point/km 2; according to the transit time of the sentinel No. 2 satellite, collecting a water sample by using an unmanned ship, wherein the sampling depth is 30-50 cm; collecting a water sample, filling the water sample into a brown bottle, and measuring water quality parameters;
secondly, the weather is required to be clear during sampling, the wind power is less than 3 grades, no cloud exists above the lake surface, and the satellite transit time interval of the sampling time is less than 4 hours;
thirdly, selecting 4 spatial interpolation methods according to data characteristics by using a spatial interpolation tool of ArcGIS10.4 to interpolate the water quality parameters; selecting an optimal interpolation result, and generating 1000 new sampling points in the range of the interpolation result by utilizing a fishernet tool of ArcGIS 10.4;
ensuring that the distance between every 2 sampling points is more than 10 meters in the generation process; respectively extracting water quality parameters to obtain water quality parameter values of 2000 sampling points;
(2) satellite data processing
Extracting pixel values of the remote sensing images by using the water quality parameter values of the sampling points to obtain pixel value data sets of 2000 points, and forming a data set of the research with the water quality parameters of 2000 points; extracting pixel values of the whole lake surface by using a region of interest (ROI) of the whole lake surface as input variables predicted by a machine learning model;
(3) remote sensing inversion water body COD index
Respectively training three machine learning models of RF, SVR and NNs, verifying the performance of the models on a test set by utilizing R2 and RMSE, adjusting the hyper-parameters of the models, and finally determining the optimal model for inverting each water quality parameter; and importing the pixel values of the remote sensing images of all the data sets into the finally determined model, and predicting the water quality parameters corresponding to the pixel values.
2. The method for remotely inverting the COD of the water body according to claim 1, wherein: in the step (2), 4 wave bands with 20m resolution of the image are resampled to be 10 meters, and 8 water quality parameter sensitive wave bands with 10m resolution are obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010551807.XA CN111797186A (en) | 2020-06-17 | 2020-06-17 | Method for inverting COD (chemical oxygen demand) of water body by remote sensing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010551807.XA CN111797186A (en) | 2020-06-17 | 2020-06-17 | Method for inverting COD (chemical oxygen demand) of water body by remote sensing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111797186A true CN111797186A (en) | 2020-10-20 |
Family
ID=72803366
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010551807.XA Pending CN111797186A (en) | 2020-06-17 | 2020-06-17 | Method for inverting COD (chemical oxygen demand) of water body by remote sensing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111797186A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112464746A (en) * | 2020-11-10 | 2021-03-09 | 清华苏州环境创新研究院 | Water quality monitoring method and system based on satellite images and machine learning |
| CN113324923A (en) * | 2021-06-07 | 2021-08-31 | 郑州大学 | Remote sensing water quality inversion method combining time-space fusion and deep learning |
| CN113466135A (en) * | 2021-06-09 | 2021-10-01 | 汕头大学 | GEE-based seawater quality online inversion monitoring method |
| CN115422309A (en) * | 2022-07-07 | 2022-12-02 | 南京林业大学 | Large-scale forest age remote sensing inversion method based on neural network |
| CN115578644A (en) * | 2022-08-08 | 2023-01-06 | 江苏省水利科学研究院 | Plain water network water hyacinth extraction method and device based on multi-feature machine learning |
| CN116337819A (en) * | 2023-03-27 | 2023-06-27 | 北京智科远达数据技术有限公司 | Inversion method of water body chemical oxygen demand concentration |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101963664A (en) * | 2010-09-28 | 2011-02-02 | 中国科学院东北地理与农业生态研究所 | Microwave remote sensing pixel element decomposing method based on land and water living beings classifying information |
| CN105868533A (en) * | 2016-03-23 | 2016-08-17 | 四川理工学院 | River basin water environment integrated perception and application method based on Internet of Things and 3S technology |
| CN108038351A (en) * | 2017-12-06 | 2018-05-15 | 武汉大学 | A kind of chlorophyll computational methods based on remote sensing image and water ecological model |
| CN108268735A (en) * | 2018-01-29 | 2018-07-10 | 浙江大学 | Soil moisture NO emissions reduction method based on multi-source remote sensing satellite fused data |
-
2020
- 2020-06-17 CN CN202010551807.XA patent/CN111797186A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101963664A (en) * | 2010-09-28 | 2011-02-02 | 中国科学院东北地理与农业生态研究所 | Microwave remote sensing pixel element decomposing method based on land and water living beings classifying information |
| CN105868533A (en) * | 2016-03-23 | 2016-08-17 | 四川理工学院 | River basin water environment integrated perception and application method based on Internet of Things and 3S technology |
| CN108038351A (en) * | 2017-12-06 | 2018-05-15 | 武汉大学 | A kind of chlorophyll computational methods based on remote sensing image and water ecological model |
| CN108268735A (en) * | 2018-01-29 | 2018-07-10 | 浙江大学 | Soil moisture NO emissions reduction method based on multi-source remote sensing satellite fused data |
Non-Patent Citations (1)
| Title |
|---|
| 罗强: "《基于遥感数据的乌梁素海水质参数及湿地演化反演研究》", 《中国优秀博硕士学位论文全文数据库(硕士) 工程科技Ⅰ辑》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112464746A (en) * | 2020-11-10 | 2021-03-09 | 清华苏州环境创新研究院 | Water quality monitoring method and system based on satellite images and machine learning |
| CN112464746B (en) * | 2020-11-10 | 2023-09-12 | 清华苏州环境创新研究院 | Water quality monitoring method and system for satellite image and machine learning |
| CN113324923A (en) * | 2021-06-07 | 2021-08-31 | 郑州大学 | Remote sensing water quality inversion method combining time-space fusion and deep learning |
| CN113324923B (en) * | 2021-06-07 | 2023-07-07 | 郑州大学 | Remote sensing water quality inversion method combining space-time fusion and deep learning |
| CN113466135A (en) * | 2021-06-09 | 2021-10-01 | 汕头大学 | GEE-based seawater quality online inversion monitoring method |
| CN115422309A (en) * | 2022-07-07 | 2022-12-02 | 南京林业大学 | Large-scale forest age remote sensing inversion method based on neural network |
| CN115422309B (en) * | 2022-07-07 | 2023-05-23 | 南京林业大学 | Large-scale forest age remote sensing inversion method based on neural network |
| CN115578644A (en) * | 2022-08-08 | 2023-01-06 | 江苏省水利科学研究院 | Plain water network water hyacinth extraction method and device based on multi-feature machine learning |
| CN115578644B (en) * | 2022-08-08 | 2023-04-18 | 江苏省水利科学研究院 | Plain water network water hyacinth extraction method and device based on multi-feature machine learning |
| CN116337819A (en) * | 2023-03-27 | 2023-06-27 | 北京智科远达数据技术有限公司 | Inversion method of water body chemical oxygen demand concentration |
| CN116337819B (en) * | 2023-03-27 | 2023-10-27 | 北京智科远达数据技术有限公司 | Inversion method of water body chemical oxygen demand concentration |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111797186A (en) | Method for inverting COD (chemical oxygen demand) of water body by remote sensing | |
| CN112905560B (en) | Air pollution prediction method based on multi-source time-space big data deep fusion | |
| Zhang et al. | Simulating the relationship between land use/cover change and urban thermal environment using machine learning algorithms in Wuhan City, China | |
| CN105868533B (en) | Based on Internet of Things and the integrated perception of 3S technology river basin water environment and application method | |
| Yuan | Land‐cover change and environmental impact analysis in the Greater Mankato area of Minnesota using remote sensing and GIS modelling | |
| Zhou et al. | Mapping the concentrations of total suspended matter in Lake Taihu, China, using Landsat‐5 TM data | |
| Liu et al. | Population density and image texture | |
| Tian et al. | Remote sensing retrieval of inland water quality parameters using Sentinel-2 and multiple machine learning algorithms | |
| CN112989692A (en) | Lake eutrophication inversion method based on remote sensing data | |
| CN106501186B (en) | A kind of soil moisture content product NO emissions reduction method | |
| CN103473707A (en) | Method for establishing urban river network water body spectrum library and application | |
| Fu et al. | Spatial downscaling of MODIS Chlorophyll-a using Landsat 8 images for complex coastal water monitoring | |
| CN112926468B (en) | Tidal flat elevation automatic extraction method | |
| CN115356249A (en) | Satellite polarization PM2.5 estimation method and system based on machine learning fusion model | |
| Wang et al. | A ground-based remote sensing system for high-frequency and real-time monitoring of phytoplankton blooms | |
| Chen et al. | A novel multi-source data fusion method based on Bayesian inference for accurate estimation of chlorophyll-a concentration over eutrophic lakes | |
| Duan et al. | Estimation of chlorophyll‐a concentration and trophic states for inland lakes in Northeast China from Landsat TM data and field spectral measurements | |
| CN112329265A (en) | Satellite remote sensing rainfall refinement space estimation method and system | |
| Giesbrecht et al. | Watershed classification predicts streamflow regime and organic carbon dynamics in the Northeast Pacific coastal temperate rainforest | |
| CN116148188A (en) | Air-space-ground integrated lake water quality tracing method, system, equipment and storage medium | |
| Cao et al. | Monitoring the spatial and temporal variations in the water surface and floating algal bloom areas in Dongting Lake using a long-term MODIS image time series | |
| Guo et al. | An enhanced deep learning approach to assessing inland lake water quality and its response to climate and anthropogenic factors | |
| Mohebzadeh et al. | Spatial downscaling of MODIS Chlorophyll-a with machine learning techniques over the west coast of the Yellow Sea in South Korea | |
| Zhang et al. | A new method for calculating water quality parameters by integrating space–ground hyperspectral data and spectral-in situ assay data | |
| CN113469097B (en) | Multi-camera real-time detection method for water surface floaters based on SSD network |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201020 |