WFV cultivated land surface soil pH rapid spatial mapping method

Abstract

The invention belongs to the field of satellite remote sensing technology and application thereof, and relates to a WFV cultivated land surface soil pH rapid spatial mapping method. The method comprises the following steps: acquiring a WFV sensor image of a Gaofen-1 satellite in a target research area, and acquiring surface reflectance of different wavebands after preprocessing; different geographical climate environment covariant data determined by the method is used as an input variable of a random forest algorithm, an output variable is cultivated land surface soil pH, and cultivated land surface soil pH mapping is realized. According to the method, the application of the Gaofen-1 satellite made in China in digital soil mapping is expanded, manpower, material resources and financial resources can be reduced, and agricultural cultivated land soil acidity and alkalinity monitoring is achieved without on-site sampling and cultivated land destroying targets.

Description

Technical Field

[0001] The invention belongs to the field of satellite remote sensing technology and its application, and in particular relates to a method for rapid spatial mapping of pH value of cultivated land surface soil. Background Art

[0002] Soil organic matter is one of the important indicators for evaluating soil degradation, soil health and soil fertility, and is a key factor affecting crop yields. Therefore, in terms of smart agriculture and sustainable use of agricultural land, it is urgent to quickly and accurately estimate soil organic matter. Traditional spatial mapping methods represented by geostatistics (such as the Kriging method) require field sampling and testing, and often focus on spatial mapping of small-scale, fragmented cultivated land. They are often not applicable to large-scale regional remote sensing mapping. This is because the impact of soil organic matter in agricultural land is affected by multiple factors such as topography, parent material, climate, vegetation and agronomic measures, and the spatial heterogeneity is large. With the development of earth observation technology and the innovation of artificial intelligence algorithms, satellite remote sensing observation methods combined with big data analysis methods have become an important method for quantitative monitoring and mapping of surface environmental parameters in large-scale regions. In previous digital soil mapping studies, Landsat series satellites and Sentinel-2 series satellites were mostly used, while digital soil mapping based on the domestically produced Gaofen-1 satellite was less common.

[0003] Satellite remote sensing mapping of soil organic matter mainly relies on spectral technology to analyze the differences in the physical and chemical properties of different landforms, and the specific differences in spectral characteristics are mainly reflected in the differences in remote sensing reflectance in different spectral bands. Soil organic matter has reflectance spectral characteristics in the visible and near-infrared wavelength ranges, and as the soil organic matter content increases, the soil reflectance decreases, causing the shape of the spectral curve to change, making it impossible to observe the dynamic changes in the pH of farmland soil. Therefore, in large-scale regional soil organic matter remote sensing mapping, it is necessary to construct an inversion algorithm that combines environmental variables and spectral indices based on the background of changing geographical environment, in order to improve the accuracy of large-scale regional soil organic matter remote sensing mapping. Summary of the invention

[0004] The purpose of the present invention is to solve the technical problem that as the soil organic matter content increases, the soil reflectivity decreases, resulting in the shape of the spectral curve also changing, making it impossible to observe the dynamic changes in the pH of farmland soil. A WFV method for rapid spatial mapping of the pH of cultivated land surface soil is provided.

[0005] WFV's method for rapid spatial mapping of soil pH in cultivated land is as follows:

[0006] Step 1: Obtain the WFV sensor image data of the Gaofen-1 satellite (referred to as WFV image);

[0007] Step 2: Preprocess the WFV sensor image of the Gaofen-1 satellite, including orthorectification, radiometric calibration and atmospheric correction;

[0008] Step 3, obtain geographic climate environment covariate data, including 1km spatial resolution soil texture remote sensing products, 1km spatial resolution annual average temperature data, 1km spatial resolution annual average rainfall data, 30m spatial resolution DEM elevation data, spectral index RI2, spectral index RI3, spectral index DI2, spectral index DI3, spectral index NDVI, spectral index RVI, spectral index DVI, spectral index NDI1, spectral index NDI2, spectral index NDI3, spectral index RDVI1, spectral index RDVI2, spectral index RDVI3, spectral index GDVI1 and spectral index GDVI2;

[0009] The soil texture of the 1km spatial resolution is clay, sand or silt;

[0010] Step 4: The spatial resolution of geographic climate and environmental covariate data was resampled to 16 m;

[0011] Step 5: Random Forest Algorithm:

[0012] Input variables of random forest algorithm: clay, sand, silt, average annual rainfall, average annual temperature, elevation, spectral index RI2, spectral index RI3, spectral index DI2, spectral index DI3, spectral index NDVI, spectral index RVI, spectral index DVI, spectral index NDI1, spectral index NDI2, spectral index NDI3, spectral index RDVI1, spectral index RDVI2, spectral index RDVI3, spectral index GDVI1 and spectral index GDVI2;

[0013] Random forest algorithm output variables: soil pH;

[0014] The spectral index

[0015] RI2=band3 / band2

[0016] RI3=band4 / band1

[0017] DI2=band3-band2

[0018] DI3=band4-band1

[0019] NDVI=(band4-band3) / (band4+band3)

[0020] RVI=band4 / band3

[0021] DVI=band4-band3

[0022] NDI1=(band3-band2) / (band3+band2)

[0023] NDI2=(band4-band1) / (band4+band1)

[0024] NDI3=(band4-band2) / (band4+band2)

[0025]

[0026]

[0027]

[0028]

[0029]

[0030] band1 represents the surface reflectance of band 1 after preprocessing of the WFV sensor image of the Gaofen-1 satellite;

[0031] band2 represents the surface reflectance of band 2 after preprocessing of the WFV sensor image of the Gaofen-1 satellite;

[0032] band3 represents the surface reflectance of band 3 after preprocessing of the WFV sensor image of the Gaofen-1 satellite;

[0033] band4 represents the surface reflectance of band 4 after preprocessing of the WFV sensor image of the Gaofen-1 satellite;

[0034] Step 6: Substitute the model into the preprocessed GF-1 satellite WFV sensor image to achieve remote sensing mapping of regional soil pH spatial distribution.

[0035] The atmospheric correction process of the image data in step 2 adopts FLAASH.

[0036] The input variables of the random forest algorithm described in step 5 are obtained based on a large-scale collection of soil samples and soil pH testing training. The process is as follows:

[0037] a. In the black soil region of Northeast China, 161 soil samples with a surface depth of 0-20 cm were collected, and the latitude and longitude information of each soil sample was recorded. The collected soil samples were then air-dried, ground and sieved, and the soil pH content was obtained using the glass electrode method;

[0038] b. Obtaining the Gaofen-1 satellite WFV sensor image, after the image data preprocessing process described in step 2, extracting the surface reflectance of the Gaofen-1 satellite WFV sensor image of different bands corresponding to each soil sample according to the latitude and longitude information of each soil sample;

[0039] c. The measured soil pH and the corresponding surface reflectance in different bands are used as the calibration data set of the model;

[0040] The surface reflectance in different bands is the surface reflectance in band 1 after preprocessing of the WFV sensor image of the Gaofen-1 satellite from band 1 to band 4;

[0041] d. After steps 3 and 4, obtain geographic climate environment covariate data consistent with the spatial resolution of the Gaofen-1 satellite WFV sensor image:

[0042] e. Based on the measured soil pH and the surface reflectance of different bands of the WFV sensor image of the Gaofen-1 satellite, a random forest inversion model of soil pH was established:

[0043] The linear correlation between the surface reflectance in different bands, the spectral index calculated from the surface reflectance in different bands, the geographic climate environment covariate data and the measured soil pH was analyzed, and the variables related to the measured soil pH were screened out, and finally determined to be clay, sand, silt, average annual rainfall, average annual temperature, elevation, spectral index RI2, spectral index RI3, spectral index DI2, spectral index DI3, spectral index NDVI, spectral index RVI, spectral index DVI, spectral index NDI1, spectral index NDI2, spectral index NDI3, spectral index RDVI1, spectral index RDVI2, spectral index RDVI3, spectral index GDVI1 and spectral index GDVI2;

[0044] The screened variables were used as input variables of the random forest algorithm to establish a soil pH remote sensing inversion model;

[0045] The linear correlation analysis was implemented in SPSS 16.0 software platform, with a significance level of p<0.05 and a confidence level of 0.01 on both sides. The Pearson correlation coefficient r is expressed as follows:

[0046]

[0047] Among them, x i is the measured soil pH value, y i is the surface reflectance of the WFV sensor image of the Gaofen-1 satellite after preprocessing to match the measured soil pH value, and N is the number of samples;

[0048] f. The random forest algorithm is subjected to error verification, and the expression of error verification is as follows:

[0049]

[0050] Where RMSE is the root mean square error, N is the number of samples, and y i is the measured soil pH value, y i ' is the estimated soil pH;

[0051] g. Algorithm test data set linear fit R 2 =0.94, RMSE is 0.29.

[0052] The random forest algorithm described in step 5 is characterized by using the RandomForest package, the number of decision trees ntree is 500, and the number of random variables of the split nodes mtry is 1 / 3 of the input amount. At this time, the value is small and the error in the model is basically stable.

[0053] This method can quickly and quantitatively complete the spatial mapping of the pH of the surface soil of cultivated land in different regions and at different times, and accurately obtain the changes in soil pH. The random forest input variables determined by the method of the present invention are constructed based on the measured soil pH, and the measured soil pH can represent the changes under different soil types and agronomic measures, and is applicable to the spatial mapping of soil pH in Northeast China. The method of the present invention expands the application of my country's domestically produced Gaofen-1 satellite in digital soil mapping, which can reduce manpower, material and financial resources, and destroy the target of cultivated land by non-field sampling, and realize the monitoring of soil acidity and alkalinity of agricultural cultivated land. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 This is the distribution map of soil sample sampling points in Experiment 1;

[0055] Figure 2 This is the calibration diagram of the soil pH inversion model in Experiment 1;

[0056] Figure 3 This is the validation diagram of the soil pH inversion model in Experiment 1;

[0057] Figure 4 It is a schematic diagram of the steps of the WFV method for rapid spatial mapping of pH of cultivated surface soil. DETAILED DESCRIPTION

[0058] The technical solution of the present invention is not limited to the specific implementation modes listed below, but also includes any combination of the specific implementation modes.

[0059] Specific implementation method 1: The WFV method for rapid spatial mapping of pH of cultivated land surface soil in this implementation method is as follows:

[0060] Step 1: Obtain the WFV sensor image data of the Gaofen-1 satellite (referred to as WFV image);

[0061] Step 2: Preprocess the WFV sensor image of the Gaofen-1 satellite, including orthorectification, radiometric calibration and atmospheric correction;

[0062] Step 3, obtain geographic climate environment covariate data, including 1km spatial resolution soil texture remote sensing products, 1km spatial resolution annual average temperature data, 1km spatial resolution annual average rainfall data, 30m spatial resolution DEM elevation data, spectral index RI2, spectral index, spectral index DI2, spectral index DI3, spectral index NDVI, spectral index RVI, spectral index DVI, spectral index NDI1, spectral index NDI2, spectral index NDI3, spectral index RDVI1, spectral index RDVI2, spectral index RDVI3, spectral index GDVI1 and spectral index GDVI2;

[0063] The soil texture of the 1km spatial resolution is clay, sand or silt;

[0064] Step 4: The spatial resolution of geographic climate and environmental covariate data was resampled to 16 m;

[0065] Step 5: Random Forest Algorithm:

[0066] Input variables of random forest algorithm: clay, sand, silt, average annual rainfall, average annual temperature, elevation, spectral index RI2, spectral index RI3, spectral index DI2, spectral index DI3, spectral index NDVI, spectral index RVI, spectral index DVI, spectral index NDI1, spectral index NDI2, spectral index NDI3, spectral index RDVI1, spectral index RDVI2, spectral index RDVI3, spectral index GDVI1 and spectral index GDVI2;

[0067] Random forest algorithm output variables: soil pH;

[0068] The spectral index

[0069] RI2=band3 / band2

[0070] RI3=band4 / band1

[0071] DI2=band3-band2

[0072] DI3=band4-band1

[0073] NDVI=(band4-band3) / (band4+band3)

[0074] RVI=band4 / band3

[0075] DVI=band4-band3

[0076] NDI1=(band3-band2) / (band3+band2)

[0077] NDI2=(band4-band1) / (band4+band1)

[0078] NDI3=(band4-band2) / (band4+band2)

[0079]

[0080]

[0081]

[0082]

[0083]

[0084] band1 represents the surface reflectance of band 1 after preprocessing of the WFV sensor image of the Gaofen-1 satellite;

[0085] band2 represents the surface reflectance of band 2 after preprocessing of the WFV sensor image of the Gaofen-1 satellite;

[0086] band3 represents the surface reflectance of band 3 after preprocessing of the WFV sensor image of the Gaofen-1 satellite;

[0087] band4 represents the surface reflectance of band 4 after preprocessing of the WFV sensor image of the Gaofen-1 satellite;

[0088] Step 6: Substitute the model into the preprocessed GF-1 satellite WFV sensor image to achieve remote sensing mapping of regional soil pH spatial distribution.

[0089] Specific implementation method 2: This implementation method is different from specific implementation method 1 in that the atmospheric correction process of the image data in step 2 adopts FLAASH. The rest is the same as specific implementation method 1.

[0090] Specific implementation method three: This implementation method is different from specific implementation methods one or two in that the input variables of the random forest algorithm in step five are obtained based on a large-scale collection of soil samples and testing of soil pH training. The process is as follows:

[0091] a. In the black soil region of Northeast China, 161 soil samples with a surface depth of 0-20 cm were collected, and the latitude and longitude information of each soil sample was recorded. The collected soil samples were then air-dried, ground and sieved, and the soil pH content was obtained using the glass electrode method;

[0092] b. Obtaining the Gaofen-1 satellite WFV sensor image, after the image data preprocessing process described in step 2, extracting the surface reflectance of the Gaofen-1 satellite WFV sensor image of different bands corresponding to each soil sample according to the latitude and longitude information of each soil sample;

[0093] c. The measured soil pH and the corresponding surface reflectance in different bands are used as the calibration data set of the model;

[0094] The surface reflectance in different bands is the surface reflectance in band 1 after preprocessing of the WFV sensor image of the Gaofen-1 satellite from band 1 to band 4;

[0095] d. After steps 3 and 4, obtain geographic climate environment covariate data consistent with the spatial resolution of the Gaofen-1 satellite WFV sensor image:

[0096] e. Based on the measured soil pH and the surface reflectance of different bands of the WFV sensor image of the Gaofen-1 satellite, a random forest inversion model of soil pH was established:

[0097] The linear correlation between the surface reflectance in different bands, the spectral index calculated from the surface reflectance in different bands, the geographic climate environment covariate data and the measured soil pH was analyzed, and the variables related to the measured soil pH were screened out, and finally determined to be clay, sand, silt, average annual rainfall, average annual temperature, elevation, spectral index RI2, spectral index RI3, spectral index DI2, spectral index DI3, spectral index NDVI, spectral index RVI, spectral index DVI, spectral index NDI1, spectral index NDI2, spectral index NDI3, spectral index RDVI1, spectral index RDVI2, spectral index RDVI3, spectral index GDVI1 and spectral index GDVI2;

[0098] The screened variables were used as input variables of the random forest algorithm to establish a soil pH remote sensing inversion model;

[0099] The linear correlation analysis was implemented in SPSS 16.0 software platform, with a significance level of p<0.05 and a confidence level of 0.01 on both sides. The Pearson correlation coefficient r is expressed as follows:

[0100]

[0101] Among them, x i is the measured soil pH value, y i is the surface reflectance of the WFV sensor image of the Gaofen-1 satellite after preprocessing to match the measured soil pH value, and N is the number of samples;

[0102] f. The random forest algorithm is subjected to error verification, and the expression of error verification is as follows:

[0103]

[0104] Where RMSE is the root mean square error, N is the number of samples, and y i is the measured soil pH value, y i ' is the estimated soil pH;

[0105] g. Algorithm test data set linear fit R 2 =0.94, RMSE is 0.29. Other aspects are the same as those in the first or second embodiment.

[0106] Specific implementation method 4: This implementation method is different from specific implementation methods 1 to 3 in that the random forest algorithm described in step 5 uses the RandomForest package, the number of decision trees ntree is 500, and the number of random variables of the split nodes mtry is 1 / 3 of the input amount, at which time the value is small and the error within the model is basically stable. The rest is the same as specific implementation methods 1 to 3.

[0107] The following experiments were used to verify the effect of the present invention:

[0108] Experiment 1:

[0109] WFV's method for rapid spatial mapping of soil pH in cultivated land is as follows:

[0110] Step 1: Obtain the WFV sensor image data of the Gaofen-1 satellite (referred to as WFV image);

[0111] Step 2: Preprocess the WFV sensor image of the Gaofen-1 satellite, including orthorectification, radiometric calibration and atmospheric correction;

[0112] Step 3, obtain geographic climate environment covariate data, including 1km spatial resolution soil texture remote sensing products, 1km spatial resolution annual average temperature data, 1km spatial resolution annual average rainfall data, 30m spatial resolution DEM elevation data, spectral index RI2, spectral index, spectral index DI2, spectral index DI3, spectral index NDVI, spectral index RVI, spectral index DVI, spectral index NDI1, spectral index NDI2, spectral index NDI3, spectral index RDVI1, spectral index RDVI2, spectral index RDVI3, spectral index GDVI1 and spectral index GDVI2;

[0113] The soil texture of the 1km spatial resolution is clay, sand or silt;

[0114] Step 4: The spatial resolution of geographic climate and environmental covariate data was resampled to 16 m;

[0115] Step 5: Random Forest Algorithm:

[0116] Input variables of random forest algorithm: clay, sand, silt, average annual rainfall, average annual temperature, elevation, spectral index RI2, spectral index RI3, spectral index DI2, spectral index DI3, spectral index NDVI, spectral index RVI, spectral index DVI, spectral index NDI1, spectral index NDI2, spectral index NDI3, spectral index RDVI1, spectral index RDVI2, spectral index RDVI3, spectral index GDVI1 and spectral index GDVI2;

[0117] Random forest algorithm output variables: soil pH;

[0118] The spectral index

[0119] RI2=band3 / band2

[0120] RI3=band4 / band1

[0121] DI2=band3-band2

[0122] DI3=band4-band1

[0123] NDVI=(band4-band3) / (band4+band3)

[0124] RVI=band4 / band3

[0125] DVI=band4-band3

[0126] NDI1=(band3-band2) / (band3+band2)

[0127] NDI2=(band4-band1) / (band4+band1)

[0128] NDI3=(band4-band2) / (band4+band2)

[0129]

[0130]

[0131]

[0132]

[0133]

[0134] band1 represents the surface reflectance of band 1 after preprocessing of the WFV sensor image of the Gaofen-1 satellite;

[0135] band2 represents the surface reflectance of band 2 after preprocessing of the WFV sensor image of the Gaofen-1 satellite;

[0136] band3 represents the surface reflectance of band 3 after preprocessing of the WFV sensor image of the Gaofen-1 satellite;

[0137] band4 represents the surface reflectance of band 4 after preprocessing of the WFV sensor image of the Gaofen-1 satellite;

[0138] Step 6: Substitute the model into the preprocessed GF-1 satellite WFV sensor image to achieve remote sensing mapping of regional soil pH spatial distribution.

[0139] The atmospheric correction process of the image data in step 2 adopts FLAASH.

[0140] The input variables of the random forest algorithm described in step 5 are obtained based on a large-scale collection of soil samples and indoor experimental testing of soil pH training. The process is as follows:

[0141] a. From April 20 to 29, 2023, a total of 68 surface 0-20 cm soil samples were collected in the black soil area of ​​Northeast China during the bare soil period, and the latitude and longitude information of each soil sample was recorded. The collected soil samples were air-dried, ground and sieved in the laboratory, and the soil pH content was obtained using the glass electrode method;

[0142] b. Obtaining the Gaofen-1 satellite WFV sensor image, after the image data preprocessing process described in step 2, extracting the surface reflectance of the Gaofen-1 satellite WFV sensor image of different bands corresponding to each soil sample according to the latitude and longitude information of each soil sample;

[0143] c. The measured soil pH and the corresponding surface reflectance in different bands are used as the calibration data set of the model;

[0144] The surface reflectance in different bands is the surface reflectance in band 1 after preprocessing of the WFV sensor image of the Gaofen-1 satellite from band 1 to band 4;

[0145] d. After steps 3 and 4, obtain geographic climate environment covariate data consistent with the spatial resolution of the Gaofen-1 satellite WFV sensor image:

[0146] e. Based on the measured soil pH and the surface reflectance of different bands of the WFV sensor image of the Gaofen-1 satellite, a random forest inversion model of soil pH was established:

[0147] The linear correlation between the surface reflectance in different bands, the spectral index calculated from the surface reflectance in different bands, the geographic climate environment covariate data and the measured soil pH was analyzed, and the variables related to the measured soil pH were screened out, and finally determined to be clay, sand, silt, average annual rainfall, average annual temperature, elevation, spectral index RI2, spectral index RI3, spectral index DI2, spectral index DI3, spectral index NDVI, spectral index RVI, spectral index DVI, spectral index NDI1, spectral index NDI2, spectral index NDI3, spectral index RDVI1, spectral index RDVI2, spectral index RDVI3, spectral index GDVI1 and spectral index GDVI2;

[0148] The screened variables were used as input variables of the random forest algorithm to establish a soil pH remote sensing inversion model;

[0149] The linear correlation analysis was implemented in SPSS 16.0 software platform, with a significance level of p<0.05 and a confidence level of 0.01 on both sides. The Pearson correlation coefficient r is expressed as follows:

[0150]

[0151] Among them, x i is the measured soil pH value, y i is the surface reflectance of the WFV sensor image of the Gaofen-1 satellite after preprocessing to match the measured soil pH value, and N is the number of samples;

[0152] f. The random forest algorithm is subjected to error verification, and the expression of error verification is as follows:

[0153]

[0154] Where RMSE is the root mean square error, N is the number of samples, and y i is the measured soil pH value, y i ' is the estimated soil pH;

[0155] g. Algorithm test data set linear fit R 2 =0.70, RMSE is 0.63, which meets the internationally accepted quantitative remote sensing inversion accuracy requirements (R 2 >0.45), such as Figure 3 .

[0156] The random forest algorithm described in step 5 uses the RandomForest package, the number of decision trees ntree is 500, and the number of random variables for splitting nodes mtry is 1 / 3 of the input. At this time, the value is small and the error within the model is basically stable.

Claims

1. WFV's method for rapid spatial mapping of pH in the topsoil of cultivated land is characterized by The WFV method for rapid spatial mapping of pH in the cultivated surface soil is as follows: Step 1: Obtain the WFV sensor image data of the Gaofen-1 satellite; Step 2: Preprocess the WFV sensor image of the Gaofen-1 satellite, including orthorectification, radiometric calibration and atmospheric correction; Step 3, obtain geographic climate environment covariate data, including 1km spatial resolution soil texture remote sensing products, 1km spatial resolution annual average temperature data, 1km spatial resolution annual average rainfall data, 30m spatial resolution DEM elevation data, spectral index RI2, spectral index RI3, spectral index DI2, spectral index DI3, spectral index NDVI, spectral index RVI, spectral index DVI, spectral index NDI1, spectral index NDI2, spectral index NDI3, spectral index RDVI1, spectral index RDVI2, spectral index RDVI3, spectral index GDVI1 and spectral index GDVI2; The soil texture of the 1km spatial resolution is clay, sand or silt; Step 4: The spatial resolution of geographic climate and environmental covariate data was resampled to 16 m; Step 5: Random Forest Algorithm: Input variables of random forest algorithm: clay, sand, silt, average annual rainfall, average annual temperature, elevation, spectral index RI2, spectral index RI3, spectral index DI2, spectral index DI3, spectral index NDVI, spectral index RVI, spectral index DVI, spectral index NDI1, spectral index NDI2, spectral index NDI3, spectral index RDVI1, spectral index RDVI2, spectral index RDVI3, spectral index GDVI1 and spectral index GDVI2; Random forest algorithm output variables: soil pH; The spectral index RI2=band3 / band2 RI3=band4 / band1 DI2=band3-band2 DI3=band4-band1 NDVI=(band4-band3) / (band4+band3) RVI=band4 / band3 DVI=band4-band3 NDI1=(band3-band2) / (band3+band2) NDI2=(band4-band1) / (band4+band1) NDI3=(band4-band2) / (band4+band2) band1 represents the surface reflectance of band 1 after preprocessing of the WFV sensor image of the Gaofen-1 satellite; band2 represents the surface reflectance of band 2 after preprocessing of the WFV sensor image of the Gaofen-1 satellite; band3 represents the surface reflectance of band 3 after preprocessing of the WFV sensor image of the Gaofen-1 satellite; band4 represents the surface reflectance of band 4 after preprocessing of the WFV sensor image of the Gaofen-1 satellite; Step 6: Substitute the model into the preprocessed GF-1 satellite WFV sensor image to achieve remote sensing mapping of regional soil pH spatial distribution.

2. The WFV method for rapid spatial mapping of pH of cultivated surface soil according to claim 1, characterized in that The atmospheric correction process of the image data in step 2 adopts FLAASH.

3. The WFV method for rapid spatial mapping of pH of cultivated surface soil according to claim 1, characterized in that The input variables of the random forest algorithm described in step 5 are obtained based on a large-scale collection of soil samples and soil pH testing training. The process is as follows: a. In the black soil region of Northeast China, 68 to 161 soil samples with a surface depth of 0-20 cm were collected, and the longitude and latitude information of each soil sample was recorded. The collected soil samples were then air-dried, ground and sieved, and the soil pH content was obtained using the glass electrode method; b. Obtaining the Gaofen-1 satellite WFV sensor image, after the image data preprocessing process described in step 2, extracting the surface reflectance of the Gaofen-1 satellite WFV sensor image of different bands corresponding to each soil sample according to the latitude and longitude information of each soil sample; c. The measured soil pH and the corresponding surface reflectance in different bands are used as the calibration data set of the model; The surface reflectance in different bands is the surface reflectance in band 1 after preprocessing of the WFV sensor image of the Gaofen-1 satellite from band 1 to band 4; d. After steps 3 and 4, obtain geographic climate environment covariate data consistent with the spatial resolution of the Gaofen-1 satellite WFV sensor image: e. Based on the measured soil pH and the surface reflectance of different bands of the WFV sensor image of the Gaofen-1 satellite, a random forest inversion model of soil pH was established: The linear correlation between the surface reflectance in different bands, the spectral index calculated from the surface reflectance in different bands, the geographic climate environment covariate data and the measured soil pH was analyzed, and the variables related to the measured soil pH were screened out, and finally determined to be clay, sand, silt, average annual rainfall, average annual temperature, elevation, spectral index RI2, spectral index RI3, spectral index DI2, spectral index DI3, spectral index NDVI, spectral index RVI, spectral index DVI, spectral index NDI1, spectral index NDI2, spectral index NDI3, spectral index RDVI1, spectral index RDVI2, spectral index RDVI3, spectral index GDVI1 and spectral index GDVI2; The selected variables were used as input variables of the random forest algorithm to establish a soil pH remote sensing inversion model; The linear correlation analysis was implemented in SPSS 16.0 software platform, with a significance level of p<0.05 and a confidence level of 0.01 on both sides. The Pearson correlation coefficient r is expressed as follows: Among them, x i is the measured soil pH value, y i is the surface reflectance of the WFV sensor image of the Gaofen-1 satellite after preprocessing to match the measured soil pH value, and N is the number of samples; f. The random forest algorithm is subjected to error verification, and the expression of error verification is as follows: Where RMSE is the root mean square error, N is the number of samples, and y i is the measured soil pH value, y i ' is the estimated soil pH; g. Algorithm test data set linear fit R 2 =0.70-0.94, RMSE is 0.29-0.

63.

4. The WFV method for rapid spatial mapping of pH of cultivated land surface soil according to claim 1, characterized in that The random forest algorithm described in step 5 uses the RandomForest package, the number of decision trees ntree is 500, and the number of random variables for splitting nodes mtry is 1 / 3 of the input. At this time, the value is small and the error within the model is basically stable.

Images