CN113125383A - Farming land secondary salinization monitoring and early warning method and system based on remote sensing - Google Patents
Farming land secondary salinization monitoring and early warning method and system based on remote sensing Download PDFInfo
- Publication number
- CN113125383A CN113125383A CN202110419468.4A CN202110419468A CN113125383A CN 113125383 A CN113125383 A CN 113125383A CN 202110419468 A CN202110419468 A CN 202110419468A CN 113125383 A CN113125383 A CN 113125383A
- Authority
- CN
- China
- Prior art keywords
- soil
- soil salinity
- early warning
- spectral
- remote sensing
- 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
- 238000009313 farming Methods 0.000 title claims abstract description 73
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000012544 monitoring process Methods 0.000 title claims abstract description 47
- 239000002689 soil Substances 0.000 claims abstract description 257
- 230000003595 spectral effect Effects 0.000 claims abstract description 138
- 238000002310 reflectometry Methods 0.000 claims abstract description 45
- 150000003839 salts Chemical class 0.000 claims abstract description 41
- 238000007781 pre-processing Methods 0.000 claims abstract description 20
- 238000005070 sampling Methods 0.000 claims description 35
- 238000003860 storage Methods 0.000 claims description 17
- 230000004044 response Effects 0.000 claims description 13
- 238000010801 machine learning Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000010219 correlation analysis Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 238000003331 infrared imaging Methods 0.000 claims description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 11
- 239000003673 groundwater Substances 0.000 description 8
- 238000003973 irrigation Methods 0.000 description 6
- 230000002262 irrigation Effects 0.000 description 6
- 238000005457 optimization Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 241000607479 Yersinia pestis Species 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 241000282414 Homo sapiens Species 0.000 description 2
- FAPWRFPIFSIZLT-UHFFFAOYSA-M Sodium chloride Chemical compound [Na+].[Cl-] FAPWRFPIFSIZLT-UHFFFAOYSA-M 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000015556 catabolic process Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000006731 degradation reaction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000012535 impurity Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000010238 partial least squares regression Methods 0.000 description 2
- 239000011780 sodium chloride Substances 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000001131 transforming effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 238000001704 evaporation Methods 0.000 description 1
- 230000008020 evaporation Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000002344 surface layer Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/55—Specular reflectivity
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a farming land secondary salinization monitoring and early warning method and system based on remote sensing, which comprises the following steps: collecting spectral image information and infrared image information of a farming land in a target area; preprocessing the spectral image information and the infrared image information to obtain remote sensing image information of the farming land; acquiring spectral reflectivity, calculating a correlation coefficient of the soil salinity and the spectral data, and introducing a soil salinity estimation model according to the correlation coefficient; estimating the salt content of the soil through the soil salt content estimation model, and grading the secondary salinization according to the salt content of the soil to generate early warning information.
Description
Technical Field
The invention relates to a method for monitoring and early warning of secondary salinization of farming lands, in particular to a method, a system and a readable storage medium for monitoring and early warning of secondary salinization of farming lands based on remote sensing.
Background
With the continuous development of social economy, the contradiction between human beings and the natural environment is increasingly prominent, and the problems of soil environment damage, land degradation and the like become barriers to the development of the human society due to the problems of improper development and utilization of soil and the like. Secondary salinization mainly occurs in arid and semiarid regions with strong evaporation action and serves as a type of land degradation, and the secondary salinization is a process of accumulating salt on the surface layer of cultivated soil due to unreasonable artificial measures. Mainly because the irrigation system is not matched with excessive irrigation and the drainage is blocked to cause the rise of low water level. The unmanned aerial vehicle remote sensing technology can rapidly acquire ground remote sensing information in a large range, can effectively monitor the secondary salinization condition in real time and dynamically, and adopts proper prevention and control measures according to the monitored secondary salinization condition so as to reduce the harm of the secondary salinization and improve the crop yield.
In order to accurately and effectively monitor and early warn secondary salinization of farming lands, a system for monitoring and early warning the secondary salinization of the farming lands by using an unmanned aerial vehicle remote sensing technology needs to be developed, and the system collects remote sensing image information of the farming lands in a target area; acquiring spectral reflectivity, calculating a correlation coefficient of the soil salinity and spectral data, determining a response waveband according to the correlation coefficient, and introducing a soil salinity estimation model; estimating the salt content of the soil through the soil salt content estimation model, and grading the secondary salinization according to the salt content of the soil to generate early warning information. In the implementation process of the system, how to determine the preferential corresponding wave band according to the spectral data and the correlation coefficient of the soil salinity and how to estimate the soil salinity in the target area are all problems which need to be solved urgently.
Disclosure of Invention
In order to solve at least one technical problem, the invention provides a farming land secondary salinization monitoring and early warning method, a farming land secondary salinization monitoring and early warning system and a storage medium based on remote sensing.
The invention provides a farming land secondary salinization monitoring and early warning method based on remote sensing, which comprises the following steps:
collecting spectral image information and infrared image information of a farming land in a target area;
preprocessing the spectral image information and the infrared image information to obtain remote sensing image information of the farming land;
acquiring spectral reflectivity, calculating a correlation coefficient of the soil salinity and the spectral data, and introducing a soil salinity estimation model according to the correlation coefficient;
estimating the salt content of the soil through the soil salt content estimation model, and grading the secondary salinization according to the salt content of the soil to generate early warning information.
In the scheme, the unmanned aerial vehicle platform carrying the multispectral remote sensing sensor and the thermal infrared imaging system is adopted for collecting the spectral image information and the infrared image information of the farmland in the target area.
In this scheme, the obtaining of the spectral reflectivity, calculating and obtaining the correlation coefficient of the soil salinity and the spectral data specifically are as follows: image information acquired by an unmanned aerial vehicle is subjected to image filtering preprocessing, sampling points are selected from the image information, an image unit of the sampling points is determined, and spectral reflectivity of each wave band of the image unit is extracted; the concrete formula for calculating the correlation coefficient of the soil salinity and the spectral data is as follows:
wherein R isjRepresenting the correlation coefficient, G, of the soil salinity in the j-th band with the spectral dataijRepresenting the spectral reflectance in the j-th band at the i-th sampling point,
denotes the average value of the spectral reflectance, YiRepresenting the salinity of the soil at the ith sampling point,
the average value of the salt content of the sample soil is shown, and n represents the number of samples.
According to the technical scheme, the optimal response wave band of the soil salinity and the spectral reflectivity is determined by calculating the correlation coefficient of the soil salinity and the spectral data, after the correlation analysis of the spectral reflectivity and the soil salinity of the optimal response wave band is carried out, a machine learning method is utilized, a soil salinity estimation model based on the spectral reflectivity is introduced, the soil salinity estimation model is subjected to error compensation, the prediction effect is improved, and the soil salinity is estimated through the soil salinity estimation model.
In this scheme, carry out error compensation with soil salinity estimation model, specifically do:
predicting and estimating the soil salinity condition of the sampling site through a soil salinity estimation model;
comparing the predicted soil salinity condition with the actual soil salinity condition to obtain a deviation rate;
judging whether the deviation rate is greater than a preset deviation rate threshold value or not;
and if so, generating error compensation information, and correcting the prediction accuracy of the soil salinity estimation model through the error compensation information.
In this scheme, pass through soil salinity estimation model estimate the soil salinity to according to soil salinity carries out the grade division to the secondary salinization and generates early warning information, specifically do:
obtaining remote sensing image information of farming land in a target area;
preprocessing the remote sensing image information, calculating to obtain spectral reflectivity, and estimating the soil salinity condition through the soil salinity estimation model;
generating secondary salinization early warning information of different grades according to the salinity condition of the soil;
and displaying the secondary salinization early warning information in a preset mode.
Wherein the soil salinity condition calculation formula specifically is as follows:
wherein Y represents the salt content of the soil, and Gb，GrRespectively, the spectral reflectivities of the blue and red bands.
The invention also provides a remote sensing-based farming land secondary salinization monitoring and early warning system, which comprises: the remote sensing-based farming land secondary salinization monitoring and early warning method program comprises a memory and a processor, wherein the remote sensing-based farming land secondary salinization monitoring and early warning method program realizes the following steps when executed by the processor:
collecting spectral image information and infrared image information of a farming land in a target area;
preprocessing the spectral image information and the infrared image information to obtain remote sensing image information of the farming land;
acquiring spectral reflectivity, calculating a correlation coefficient of the soil salinity and the spectral data, and introducing a soil salinity estimation model according to the correlation coefficient;
estimating the salt content of the soil through the soil salt content estimation model, and grading the secondary salinization according to the salt content of the soil to generate early warning information.
In the scheme, the unmanned aerial vehicle platform carrying the multispectral remote sensing sensor and the thermal infrared imaging system is adopted for collecting the spectral image information and the infrared image information of the farmland in the target area.
In this scheme, the obtaining of the spectral reflectivity, calculating and obtaining the correlation coefficient of the soil salinity and the spectral data specifically are as follows: image information acquired by an unmanned aerial vehicle is subjected to image filtering preprocessing, sampling points are selected from the image information, an image unit of the sampling points is determined, and spectral reflectivity of each wave band of the image unit is extracted; the concrete formula for calculating the correlation coefficient of the soil salinity and the spectral data is as follows:
wherein R isjRepresenting the correlation coefficient, G, of the soil salinity in the j-th band with the spectral dataijRepresenting the spectral reflectance in the j-th band at the i-th sampling point,
denotes the average value of the spectral reflectance, YiRepresenting the salinity of the soil at the ith sampling point,
the average value of the salt content of the sample soil is shown, and n represents the number of samples.
According to the technical scheme, the optimal response wave band of the soil salinity and the spectral reflectivity is determined by calculating the correlation coefficient of the soil salinity and the spectral data, after the correlation analysis of the spectral reflectivity and the soil salinity of the optimal response wave band is carried out, a machine learning method is utilized, a soil salinity estimation model based on the spectral reflectivity is introduced, the soil salinity estimation model is subjected to error compensation, the prediction effect is improved, and the soil salinity is estimated through the soil salinity estimation model.
In this scheme, carry out error compensation with soil salinity estimation model, specifically do:
predicting and estimating the soil salinity condition of the sampling site through a soil salinity estimation model;
comparing the predicted soil salinity condition with the actual soil salinity condition to obtain a deviation rate;
judging whether the deviation rate is greater than a preset deviation rate threshold value or not;
and if so, generating error compensation information, and correcting the prediction accuracy of the soil salinity estimation model through the error compensation information.
In this scheme, pass through soil salinity estimation model estimate the soil salinity to according to soil salinity carries out the grade division to the secondary salinization and generates early warning information, specifically do:
obtaining remote sensing image information of farming land in a target area;
preprocessing the remote sensing image information, calculating to obtain spectral reflectivity, and estimating the soil salinity condition through the soil salinity estimation model;
generating secondary salinization early warning information of different grades according to the salinity condition of the soil;
and displaying the secondary salinization early warning information in a preset mode.
Wherein the soil salinity condition calculation formula specifically is as follows:
wherein Y represents the salt content of the soil, and Gb，GrRespectively, the spectral reflectivities of the blue and red bands.
The third aspect of the invention also provides a computer readable storage medium, wherein the computer readable storage medium comprises a program of the method for monitoring and early warning the secondary salinization of the farming land based on remote sensing, and when the program of the method for monitoring and early warning the secondary salinization of the farming land based on remote sensing is executed by a processor, the steps of the method for monitoring and early warning the secondary salinization of the farming land based on remote sensing are realized.
The invention discloses a farming land secondary salinization monitoring and early warning method and system based on remote sensing and a readable storage medium, wherein the farming land secondary salinization monitoring and early warning method comprises the following steps: collecting spectral image information and infrared image information of a farming land in a target area; preprocessing the spectral image information and the infrared image information to obtain remote sensing image information of the farming land; acquiring spectral reflectivity, calculating a correlation coefficient of the soil salinity and the spectral data, and introducing a soil salinity estimation model according to the correlation coefficient; estimating the salt content of the soil through the soil salt content estimation model, and grading the secondary salinization according to the salt content of the soil to generate early warning information. Meanwhile, the soil salinity estimation model corrects the model prediction precision through error compensation information, so that the soil salinity condition predicted and estimated by the soil salinity estimation model is closer to the real salinity condition of the soil.
Drawings
FIG. 1 shows a flow chart of a farming land secondary salinization monitoring and early warning method based on remote sensing;
FIG. 2 is a flow chart of a method for error compensation of the soil salinity estimation model according to the present invention;
FIG. 3 illustrates a flow chart of a method of generating early warning information according to salination levels of the present invention;
FIG. 4 shows a block diagram of a farming land secondary salinization monitoring and early warning system based on remote sensing.
Detailed description of the invention
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
FIG. 1 shows a flow chart of the farming land secondary salinization monitoring and early warning method based on remote sensing.
As shown in fig. 1, the invention provides a remote sensing-based farming land secondary salinization monitoring and early warning method in a first aspect, which comprises the following steps:
s102, collecting spectral image information and infrared image information of a farming land in a target area;
s104, preprocessing the spectral image information and the infrared image information to obtain remote sensing image information of the farming land;
s106, obtaining the spectral reflectivity, calculating and obtaining a correlation coefficient of the soil salinity and the spectral data, and introducing a soil salinity estimation model according to the correlation coefficient;
and S108, estimating the salinity of the soil through the soil salinity estimation model, grading the secondary salinization according to the salinity of the soil, and generating early warning information.
The spectral image information and the infrared image information of the farming land in the collected target area adopt an unmanned aerial vehicle platform carrying a multispectral remote sensing sensor and a thermal infrared imaging system; after various flight parameters of the unmanned aerial vehicle are calibrated, a flight route of the unmanned aerial vehicle is preset through route planning software, the flight height of the unmanned aerial vehicle is 100m, a spectral lens is vertically downward, a standard white board is arranged in a target area before spectral acquisition every time, the standard white board is used for correction and optimization, and the acquisition time and the acquisition mode of infrared images are consistent with those of a multispectral system.
The method comprises the steps of collecting soil samples by a five-point sampling method, wherein a sampling unit is 10m x 10m, the sampling depth comprises 0-20cm, placing the collected soil into a specific container, numbering, recording GPS position coordinates of sampling points, taking the sample data as a mean value of five-point sampling, removing impurities from the sampled soil, grinding the sampled soil, preparing a solution, measuring the conductivity of the sampled soil solution by an electrical conductivity method, and calculating the soil salt content of the sampled soil according to the conductivity.
It should be noted that, the obtaining of the spectral reflectivity and the calculating of the correlation coefficient of the obtained soil salinity and the spectral data specifically include: image information acquired by an unmanned aerial vehicle is subjected to image filtering preprocessing, sampling points are selected from the image information, an image unit of the sampling points is determined, and spectral reflectivity of each wave band of the image unit is extracted; the concrete formula for calculating the correlation coefficient of the soil salinity and the spectral data is as follows:
wherein R isjRepresenting the correlation coefficient, G, of the soil salinity in the j-th band with the spectral dataijRepresenting the spectral reflectance in the j-th band at the i-th sampling point,
denotes the average value of the spectral reflectance, YiRepresenting the salinity of the soil at the ith sampling point,
the average value of the salt content of the sample soil is shown, and n represents the number of samples.
The method includes the steps of determining an optimal response waveband of soil salinity and spectral reflectivity by calculating a correlation coefficient of the soil salinity and spectral data, and introducing a soil salinity estimation model based on the spectral reflectivity by using a machine learning method after analyzing the correlation between the spectral reflectivity of the optimal response waveband and the soil salinity, wherein the soil salinity estimation model is constructed by using machine learning methods such as partial least squares regression, support vector machines, back propagation neural networks and extreme learning machines, error compensation is performed on the soil salinity estimation model, the prediction effect is improved, and the soil salinity is estimated by using the soil salinity estimation model.
The method comprises the steps of obtaining a spectral index by combining and transforming spectral reflectances of different wave bands, generating different spectral indexes according to the spectral reflectances to predict and estimate the soil salinity, performing correlation analysis and optimization on the spectral index and the soil salinity of a farming land, and constructing a soil salinity estimation model based on the spectral index by using a machine learning method, wherein the spectral index is calculated by the following specific steps:
wherein Z represents the desired spectral index, and α, β, and μ represent spectral reflectances at wavelengths of 550nm, 680nm, and 800nm, respectively.
FIG. 2 is a flow chart of a method for error compensation of the soil salinity estimation model according to the present invention;
according to the embodiment of the invention, the error compensation is carried out on the soil salinity estimation model, and the method specifically comprises the following steps:
s202, predicting and estimating the soil salinity of the sampling site through a soil salinity estimation model;
s204, comparing the predicted soil salinity condition with the actual soil salinity condition to obtain a deviation rate;
s206, judging whether the deviation rate is larger than a preset deviation rate threshold value or not;
and S208, if the soil salinity estimation model is larger than the preset salinity estimation model, generating error compensation information, and correcting the prediction accuracy of the soil salinity estimation model through the error compensation information.
It should be noted that, by judging the deviation ratio between the predicted soil salinity condition and the actual soil salinity condition, error compensation information is generated, and the interference factors are eliminated from the soil salinity model according to the error compensation information, the correlation between the spectral reflectivity of the partial band and the soil salinity is effectively improved, and the model precision is improved.
FIG. 3 illustrates a flow chart of a method of generating early warning information according to salination levels of the present invention;
according to the embodiment of the invention, the soil salinity is estimated through the soil salinity estimation model, the secondary salinization is graded according to the soil salinity, and early warning information is generated, specifically:
s302, obtaining remote sensing image information of farming land in a target area;
s304, preprocessing the remote sensing image information, calculating to obtain spectral reflectivity, and estimating the soil salinity condition through the soil salinity estimation model;
s306, generating secondary salinization early warning information of different grades according to the salinity condition of the soil;
and S308, displaying the secondary salinization early warning information in a preset mode.
It should be noted that the calculation formula of the soil salinity condition is specifically as follows:
wherein Y represents the salt content of the soil, and Gb，GrRepresenting blue and red wavelength bands, respectivelySpectral reflectance.
The salinization grade of the soil is specifically classified into non-salinized soil with the salinity of less than 0.2%, mild salinization with the salinity of 0.2-0.5%, severe salinization with the salinity of 0.5-1.0%, and saline soil with the salinity of more than 1.0%. After the remote sensing image of the agricultural land in the target area is obtained, the soil salinity is predicted and estimated through a soil salinity estimation model, the reference range is divided through comparing the obtained soil salinity with the soil salinization grade, the soil salinization grade corresponds to the early warning information of the relevant grade, and the early warning information is displayed according to a preset mode.
It should be noted that, according to the embodiment of the present invention, the groundwater monitoring module monitors the groundwater level information in real time, performs early warning according to the monitored groundwater level information, sets the low water level information early warning water level, determines whether the monitored groundwater level information is greater than the early warning water level, and if so, displays the early warning information in a preset manner, and timely checks the irrigation system and the drainage system; in the specific implementation process, regulation and control standards can be set according to the natural climate rule of a target area, the multi-stage underground water level information early warning water level is set, and a flood season or drought season irrigation reference scheme is set.
FIG. 4 shows a block diagram of a farming land secondary salinization monitoring and early warning system based on remote sensing.
The invention also provides a remote sensing-based farming land secondary salinization monitoring and early warning system 4, which comprises: the crop disease and pest monitoring method based on the internet of things comprises a memory 41 and a processor 42, wherein the memory comprises a crop disease and pest monitoring method program based on the internet of things, and when the crop disease and pest monitoring method program based on the internet of things is executed by the processor, the following steps are realized:
collecting spectral image information and infrared image information of a farming land in a target area;
preprocessing the spectral image information and the infrared image information to obtain remote sensing image information of the farming land;
acquiring spectral reflectivity, calculating a correlation coefficient of the soil salinity and the spectral data, and introducing a soil salinity estimation model according to the correlation coefficient;
estimating the salt content of the soil through the soil salt content estimation model, and grading the secondary salinization according to the salt content of the soil to generate early warning information.
The spectral image information and the infrared image information of the farming land in the collected target area adopt an unmanned aerial vehicle platform carrying a multispectral remote sensing sensor and a thermal infrared imaging system; after various flight parameters of the unmanned aerial vehicle are calibrated, a flight route of the unmanned aerial vehicle is preset through route planning software, the flight height of the unmanned aerial vehicle is 100m, a spectral lens is vertically downward, a standard white board is arranged in a target area before spectral acquisition every time, the standard white board is used for correction and optimization, and the acquisition time and the acquisition mode of infrared images are consistent with those of a multispectral system.
The method comprises the steps of collecting soil samples by a five-point sampling method, wherein a sampling unit is 10m x 10m, the sampling depth comprises 0-20cm, placing the collected soil into a specific container, numbering, recording GPS position coordinates of sampling points, taking the sample data as a mean value of five-point sampling, removing impurities from the sampled soil, grinding the sampled soil, preparing a solution, measuring the conductivity of the sampled soil solution by an electrical conductivity method, and calculating the soil salt content of the sampled soil according to the conductivity.
It should be noted that, the obtaining of the spectral reflectivity and the calculating of the correlation coefficient of the obtained soil salinity and the spectral data specifically include: image information acquired by an unmanned aerial vehicle is subjected to image filtering preprocessing, sampling points are selected from the image information, an image unit of the sampling points is determined, and spectral reflectivity of each wave band of the image unit is extracted; the concrete formula for calculating the correlation coefficient of the soil salinity and the spectral data is as follows:
wherein，RjRepresenting the correlation coefficient, G, of the soil salinity in the j-th band with the spectral dataijRepresenting the spectral reflectance in the j-th band at the i-th sampling point,
denotes the average value of the spectral reflectance, YiRepresenting the salinity of the soil at the ith sampling point,
the average value of the salt content of the sample soil is shown, and n represents the number of samples.
The method includes the steps of determining an optimal response waveband of soil salinity and spectral reflectivity by calculating a correlation coefficient of the soil salinity and spectral data, and introducing a soil salinity estimation model based on the spectral reflectivity by using a machine learning method after analyzing the correlation between the spectral reflectivity of the optimal response waveband and the soil salinity, wherein the soil salinity estimation model is constructed by using machine learning methods such as partial least squares regression, support vector machines, back propagation neural networks and extreme learning machines, error compensation is performed on the soil salinity estimation model, the prediction effect is improved, and the soil salinity is estimated by using the soil salinity estimation model.
The method comprises the steps of obtaining a spectral index by combining and transforming spectral reflectances of different wave bands, generating different spectral indexes according to the spectral reflectances to predict and estimate the soil salinity, performing correlation analysis and optimization on the spectral index and the soil salinity of a farming land, and constructing a soil salinity estimation model based on the spectral index by using a machine learning method, wherein the spectral index is calculated by the following specific steps:
wherein Z represents the desired spectral index, and α, β, and μ represent spectral reflectances at wavelengths of 550nm, 680nm, and 800nm, respectively.
It should be noted that, the error compensation is performed on the soil salinity estimation model, specifically:
predicting and estimating the soil salinity condition of the sampling site through a soil salinity estimation model;
comparing the predicted soil salinity condition with the actual soil salinity condition to obtain a deviation rate;
judging whether the deviation rate is greater than a preset deviation rate threshold value or not;
and if so, generating error compensation information, and correcting the prediction accuracy of the soil salinity estimation model through the error compensation information.
It should be noted that, by judging the deviation ratio between the predicted soil salinity condition and the actual soil salinity condition, error compensation information is generated, and the interference factors are eliminated from the soil salinity model according to the error compensation information, the correlation between the spectral reflectivity of the partial band and the soil salinity is effectively improved, and the model precision is improved.
It should be noted that, the estimation of the soil salinity is performed through the soil salinity estimation model, and the secondary salinization is graded according to the soil salinity to generate the early warning information, which specifically includes:
obtaining remote sensing image information of farming land in a target area;
preprocessing the remote sensing image information, calculating to obtain spectral reflectivity, and estimating the soil salinity condition through the soil salinity estimation model;
generating secondary salinization early warning information of different grades according to the salinity condition of the soil;
and displaying the secondary salinization early warning information in a preset mode.
It should be noted that the calculation formula of the soil salinity condition is specifically as follows:
wherein Y represents the salt content of the soil, and Gb，GrRespectively, the spectral reflectivities of the blue and red bands.
The salinization grade of the soil is specifically classified into non-salinized soil with the salinity of less than 0.2%, mild salinization with the salinity of 0.2-0.5%, severe salinization with the salinity of 0.5-1.0%, and saline soil with the salinity of more than 1.0%. After the remote sensing image of the agricultural land in the target area is obtained, the soil salinity is predicted and estimated through a soil salinity estimation model, the reference range is divided through comparing the obtained soil salinity with the soil salinization grade, the soil salinization grade corresponds to the early warning information of the relevant grade, and the early warning information is displayed according to a preset mode.
It should be noted that, according to the embodiment of the present invention, the groundwater monitoring module monitors the groundwater level information in real time, performs early warning according to the monitored groundwater level information, sets the low water level information early warning water level, determines whether the monitored groundwater level information is greater than the early warning water level, and if so, displays the early warning information in a preset manner, and timely checks the irrigation system and the drainage system; in the specific implementation process, regulation and control standards can be set according to the natural climate rule of a target area, the multi-stage underground water level information early warning water level is set, and a flood season or drought season irrigation reference scheme is set.
The third aspect of the invention also provides a computer readable storage medium, wherein the computer readable storage medium comprises a program of the method for monitoring and early warning the secondary salinization of the farming land based on remote sensing, and when the program of the method for monitoring and early warning the secondary salinization of the farming land based on remote sensing is executed by a processor, the steps of the method for monitoring and early warning the secondary salinization of the farming land based on remote sensing are realized.
The invention discloses a farming land secondary salinization monitoring and early warning method and system based on remote sensing and a readable storage medium, wherein the farming land secondary salinization monitoring and early warning method comprises the following steps: collecting spectral image information and infrared image information of a farming land in a target area; preprocessing the spectral image information and the infrared image information to obtain remote sensing image information of the farming land; acquiring spectral reflectivity, calculating a correlation coefficient of the soil salinity and the spectral data, and introducing a soil salinity estimation model according to the correlation coefficient; estimating the salt content of the soil through the soil salt content estimation model, and grading the secondary salinization according to the salt content of the soil to generate early warning information. Meanwhile, the soil salinity estimation model corrects the model prediction precision through error compensation information, so that the soil salinity condition predicted and estimated by the soil salinity estimation model is closer to the real salinity condition of the soil.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all the functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a RAM, a magnetic or optical disk, or various other media that can store program code.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. A farming land secondary salinization monitoring and early warning method based on remote sensing is characterized by comprising the following steps:
collecting spectral image information and infrared image information of a farming land in a target area;
preprocessing the spectral image information and the infrared image information to obtain remote sensing image information of the farming land;
acquiring spectral reflectivity, calculating a correlation coefficient of the soil salinity and the spectral data, and introducing a soil salinity estimation model according to the correlation coefficient;
estimating the salt content of the soil through the soil salt content estimation model, and grading the secondary salinization according to the salt content of the soil to generate early warning information.
2. The remote sensing-based farming land secondary salinization monitoring and early warning method according to claim 1, wherein the collection of farming land spectral image information and infrared image information in the target area adopts an unmanned aerial vehicle platform carrying a multispectral remote sensing sensor and a thermal infrared imaging system.
3. The remote sensing-based farming land secondary salinization monitoring and early warning method according to claim 1, wherein the obtaining of the spectral reflectivity is used for calculating a correlation coefficient between the obtained soil salinity and the spectral data, and specifically comprises the following steps: image information acquired by an unmanned aerial vehicle is subjected to image filtering preprocessing, sampling points are selected from the image information, an image unit of the sampling points is determined, and spectral reflectivity of each wave band of the image unit is extracted; the concrete formula for calculating the correlation coefficient of the soil salinity and the spectral data is as follows:
wherein R isjRepresenting the correlation coefficient, G, of the soil salinity in the j-th band with the spectral dataijRepresenting the spectral reflectance in the j-th band at the i-th sampling point,
denotes the average value of the spectral reflectance, YiRepresenting the salinity of the soil at the ith sampling point,
the average value of the salt content of the sample soil is shown, and n represents the number of samples.
4. The remote sensing-based farming land secondary salinization monitoring and early warning method as claimed in claim 3, wherein the optimal response band of soil salinity and spectral reflectance is determined by calculating the correlation coefficient of soil salinity and spectral data, after the correlation analysis of the spectral reflectance of the optimal response band and the soil salinity is performed, a machine learning method is utilized to introduce a soil salinity estimation model based on the spectral reflectance, the soil salinity estimation model is subjected to error compensation to improve the prediction effect, and the soil salinity is estimated through the soil salinity estimation model.
5. The remote sensing-based farming land secondary salinization monitoring and early warning method according to claim 4, wherein the soil salinity estimation model is subjected to error compensation, and specifically comprises the following steps:
predicting and estimating the soil salinity condition of the sampling site through a soil salinity estimation model;
comparing the predicted soil salinity condition with the actual soil salinity condition to obtain a deviation rate;
judging whether the deviation rate is greater than a preset deviation rate threshold value or not;
and if so, generating error compensation information, and correcting the prediction accuracy of the soil salinity estimation model through the error compensation information.
6. The remote sensing-based farming land secondary salinization monitoring and early warning method according to claim 1, wherein the soil salinity is estimated through the soil salinity estimation model, and the secondary salinization is graded according to the soil salinity to generate early warning information, specifically:
obtaining remote sensing image information of farming land in a target area;
preprocessing the remote sensing image information, calculating to obtain spectral reflectivity, and estimating the soil salinity condition through the soil salinity estimation model;
generating secondary salinization early warning information of different grades according to the salinity condition of the soil;
and displaying the secondary salinization early warning information in a preset mode.
Wherein the soil salinity condition calculation formula specifically is as follows:
wherein Y represents the salt content of the soil, and Gb，GrRespectively, the spectral reflectivities of the blue and red bands.
7. The utility model provides a farming land secondary salinization monitoring and early warning system based on remote sensing which characterized in that, this system includes: the remote sensing-based farming land secondary salinization monitoring and early warning method program comprises a memory and a processor, wherein the remote sensing-based farming land secondary salinization monitoring and early warning method program realizes the following steps when executed by the processor:
collecting spectral image information and infrared image information of a farming land in a target area;
preprocessing the spectral image information and the infrared image information to obtain remote sensing image information of the farming land;
acquiring spectral reflectivity, calculating a correlation coefficient of the soil salinity and the spectral data, and introducing a soil salinity estimation model according to the correlation coefficient;
estimating the salt content of the soil through the soil salt content estimation model, and grading the secondary salinization according to the salt content of the soil to generate early warning information.
8. The remote sensing-based farming land secondary salinization monitoring and early warning system of claim 7, wherein an optimal response band of soil salinity and spectral reflectance is determined by calculating a correlation coefficient of soil salinity and spectral data, after the correlation analysis of the spectral reflectance of the optimal response band and the soil salinity is performed, a machine learning method is utilized to introduce a soil salinity estimation model based on the spectral reflectance, the soil salinity estimation model is subjected to error compensation to improve the prediction effect, and the soil salinity is estimated through the soil salinity estimation model.
9. The remote sensing-based farming land secondary salination monitoring and early warning system of claim 7, wherein the soil salinity is estimated by the soil salinity estimation model, and secondary salination is graded according to the soil salinity to generate early warning information, specifically:
obtaining remote sensing image information of farming land in a target area;
preprocessing the remote sensing image information, calculating to obtain spectral reflectivity, and estimating the soil salinity condition through the soil salinity estimation model;
generating secondary salinization early warning information of different grades according to the salinity condition of the soil;
displaying the secondary salinization early warning information in a preset mode;
wherein the soil salinity condition calculation formula specifically is as follows:
wherein Y represents the salt content of the soil, and Gb，GrRespectively, the spectral reflectivities of the blue and red bands.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises a remote sensing-based farming land secondary salinization monitoring and early warning method program, when the remote sensing-based farming land secondary salinization monitoring and early warning method program is executed by a processor, the steps of the remote sensing-based farming land secondary salinization monitoring and early warning method according to any one of claims 1 to 6 are realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110419468.4A CN113125383A (en) | 2021-04-19 | 2021-04-19 | Farming land secondary salinization monitoring and early warning method and system based on remote sensing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110419468.4A CN113125383A (en) | 2021-04-19 | 2021-04-19 | Farming land secondary salinization monitoring and early warning method and system based on remote sensing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113125383A true CN113125383A (en) | 2021-07-16 |
Family
ID=76778092
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110419468.4A Pending CN113125383A (en) | 2021-04-19 | 2021-04-19 | Farming land secondary salinization monitoring and early warning method and system based on remote sensing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113125383A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023088366A1 (en) * | 2021-11-18 | 2023-05-25 | 浙江大学 | Method for jointly estimating soil profile salinity by using time-series remote sensing image |
| CN116310842A (en) * | 2023-05-15 | 2023-06-23 | 菏泽市国土综合整治服务中心 | Soil saline-alkali area identification and division method based on remote sensing image |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018153143A1 (en) * | 2017-02-22 | 2018-08-30 | 河海大学 | Method for measuring mudflat elevation by remotely sensed water content |
| CN108680509A (en) * | 2018-08-17 | 2018-10-19 | 山东农业大学 | A kind of strand salt marsh area soil salt content evaluation method |
| CN109342337A (en) * | 2018-12-19 | 2019-02-15 | 山东农业大学 | A kind of severe Soluble Salts In Salt-affected Soil acquisition methods, system and device |
| CN110412245A (en) * | 2019-08-07 | 2019-11-05 | 石河子大学 | The research method of soil salinization degree remote sensing monitoring |
| CN112147078A (en) * | 2020-09-22 | 2020-12-29 | 华中农业大学 | Multi-source remote sensing monitoring method for crop phenotype information |
| CN112213287A (en) * | 2020-12-07 | 2021-01-12 | 速度时空信息科技股份有限公司 | Coastal beach salinity inversion method based on remote sensing satellite image |
-
2021
- 2021-04-19 CN CN202110419468.4A patent/CN113125383A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018153143A1 (en) * | 2017-02-22 | 2018-08-30 | 河海大学 | Method for measuring mudflat elevation by remotely sensed water content |
| CN108680509A (en) * | 2018-08-17 | 2018-10-19 | 山东农业大学 | A kind of strand salt marsh area soil salt content evaluation method |
| CN109342337A (en) * | 2018-12-19 | 2019-02-15 | 山东农业大学 | A kind of severe Soluble Salts In Salt-affected Soil acquisition methods, system and device |
| CN110412245A (en) * | 2019-08-07 | 2019-11-05 | 石河子大学 | The research method of soil salinization degree remote sensing monitoring |
| CN112147078A (en) * | 2020-09-22 | 2020-12-29 | 华中农业大学 | Multi-source remote sensing monitoring method for crop phenotype information |
| CN112213287A (en) * | 2020-12-07 | 2021-01-12 | 速度时空信息科技股份有限公司 | Coastal beach salinity inversion method based on remote sensing satellite image |
Non-Patent Citations (2)
| Title |
|---|
| 胡盈盈等: "黄河三角洲春秋两季土壤盐分遥感反演及时空变异研究", 《测绘与空间地理信息》 * |
| 陈实等: "北疆农区土壤盐渍化遥感监测及其时空特征分析", 《地理科学》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023088366A1 (en) * | 2021-11-18 | 2023-05-25 | 浙江大学 | Method for jointly estimating soil profile salinity by using time-series remote sensing image |
| CN116310842A (en) * | 2023-05-15 | 2023-06-23 | 菏泽市国土综合整治服务中心 | Soil saline-alkali area identification and division method based on remote sensing image |
| CN116310842B (en) * | 2023-05-15 | 2023-08-04 | 菏泽市国土综合整治服务中心 | Soil saline-alkali area identification and division method based on remote sensing image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Szabo et al. | Specific features of NDVI, NDWI and MNDWI as reflected in land cover categories | |
| Addink et al. | The importance of scale in object-based mapping of vegetation parameters with hyperspectral imagery | |
| McFarlane et al. | The extent and potential area of salt-affected land in Western Australia estimated using remote sensing and digital terrain models | |
| Sarker et al. | Improved forest biomass estimates using ALOS AVNIR-2 texture indices | |
| Castillo et al. | LIDAR remote sensing for secondary Tropical Dry Forest identification | |
| US20120114185A1 (en) | System and method for inventorying vegetal substance | |
| Cullu | Estimation of the effect of soil salinity on crop yield using remote sensing and geographic information system | |
| Plowright et al. | Assessing urban tree condition using airborne light detection and ranging | |
| CN111784082B (en) | GIS mountain torrent prevention early warning system based on big data | |
| CN113125383A (en) | Farming land secondary salinization monitoring and early warning method and system based on remote sensing | |
| CN111879915B (en) | High-resolution monthly soil salinity monitoring method and system for coastal wetland | |
| CN114926748A (en) | Soybean remote sensing identification method combining Sentinel-1/2 microwave and optical multispectral images | |
| CN108106676A (en) | A kind of monitoring method and device of the crops Spring frost based on remotely-sensed data | |
| CN116385867A (en) | Ecological land block monitoring, identifying and analyzing method, system, medium, equipment and terminal | |
| CN116561509A (en) | Urban vegetation overground biomass accurate inversion method and system considering vegetation types | |
| CN111783288A (en) | Inversion method for soil salinity of yellow river delta based on Landsat8 | |
| Na et al. | Assessing breeding habitat suitability for the endangered red-crowned crane (Grus japonensis) based on multi-source remote sensing data | |
| Moradi et al. | Potential evaluation of visible-thermal UAV image fusion for individual tree detection based on convolutional neural network | |
| CN115271343A (en) | Method and system for monitoring and adjusting decision of crop planting structure in water-deficient area | |
| CN114611699A (en) | Soil moisture downscaling method and device, electronic equipment and storage medium | |
| Huang et al. | Comparing the effects of temporal features derived from synthetic time-series NDVI on fine land cover classification | |
| Pesonen et al. | Effects of auxiliary data source and inventory unit size on the efficiency of sample-based coarse woody debris inventory | |
| Martinez et al. | Multi-sensor approach to leaf area index estimation using statistical machine learning models: A case on mangrove forests | |
| Mohsin et al. | Modelling of stand volume of eucalyptus plantations using worldview-2 imagery in Sabah, Malaysia | |
| CN115993336B (en) | Method for monitoring vegetation damage on two sides of water delivery channel and early warning method |
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 |
Application publication date: 20210716 |
|
| RJ01 | Rejection of invention patent application after publication |