Prediction method of soil calcium carbonate content based on indoor hyperspectral and linear regression

Abstract

The present invention discloses a soil calcium carbonate content prediction method based on indoor hyperspectral and linear regression, including: collecting soil samples and pre-processing; measuring the spectral reflectance data of the soil samples in the 2000-2400nm band; measuring the calcium carbonate content of the soil samples; performing breakpoint correction, detrending and continuum removal processing on the spectral reflectance data of the soil samples in the 2000-2400nm band; selecting the spectral reflectance data of the 2330-2360nm band from the processed data and calculating its maximum absorption depth; based on the calcium carbonate content and the maximum absorption depth, establishing a linear regression model; based on the linear regression model and the spectral reflectance data of the soil samples in the target area, predicting the calcium carbonate content of the soil samples in the target area. The present invention has the characteristics of high efficiency and accuracy, low cost and environmental friendliness, and can provide support for the fields of soil quality assessment, precision agriculture and ecological environment protection.

Description

Technical Field

[0001] The present invention belongs to the technical field of soil remote sensing, and in particular relates to a method for predicting soil calcium carbonate content based on indoor hyperspectral and linear regression. Background Art

[0002] Soil calcium carbonate is the primary component of terrestrial soil carbonates, and its content influences soil physical structure, chemical properties, biochemical processes, soil carbon pool dynamics, and the global carbon cycle. Soil calcium carbonate promotes the formation and stabilization of soil aggregates, altering soil aeration, water permeability, and erosion resistance. It also regulates soil pH, affecting the availability of essential elements for plants. Furthermore, it indirectly influences plant growth by influencing soil enzyme activity and microbial community structure. As a crucial component of the soil inorganic carbon pool, the dynamics of soil calcium carbonate content are closely related to soil aggregate status, microbial activity, and organic matter decomposition, and influences the global greenhouse effect through its participation in the carbon cycle. Therefore, efficient and accurate estimation of soil calcium carbonate content is a crucial component of soil science research. It not only helps improve soil fertility and ecosystem function but also has important implications for accurately calculating soil carbon reserves, understanding carbon cycle mechanisms, and addressing climate change.

[0003] Existing methods for detecting soil calcium carbonate content mainly include: (1) Traditional chemical analysis: mainly including titration and gas volumetric analysis, which has high accuracy, but has the disadvantages of being time-consuming, labor-intensive, costly, complex to operate, and difficult to achieve rapid batch analysis; (2) Spectral analysis: Soil calcium carbonate content estimation based on spectral analysis has the advantages of being fast, cost-effective, environmentally friendly, non-destructive, and reproducible. Its process mainly includes the following steps: first, soil spectral data is collected and noise is removed through preprocessing, then a quantitative relationship model between the spectrum and calcium carbonate content is established, and finally the model is used to predict unknown samples. Among them, commonly used preprocessing methods include: Savitzky-Golay convolution smoothing, first-order differential, second-order differential, and continuum removal; commonly used modeling methods include: partial least squares regression (PLSR), multiple linear regression (MLR), support vector machine regression (SVR) or random forest regression (RFR) and other machine learning methods and neural networks (NN). In addition, some estimation methods will use the competitive adaptive reweighted sampling algorithm (CARS) or the successive projection algorithm (SPA) to screen the characteristic bands before modeling to achieve the purpose of data dimensionality reduction, thereby improving the computational efficiency of the model.

[0004] However, existing modeling methods for hyperspectral analysis of soil calcium carbonate content remain complex. PLSR and MLR require data in the 350-2500 nm band for modeling, resulting in high complexity and cost in acquiring and processing hyperspectral data and establishing models. Even when methods such as CARS and SPA are used to reduce data dimensionality before modeling, the selection process is complex and highly dependent on dataset characteristics, leading to significant variability in screening results across different datasets. Machine learning methods such as SVR and RFR, as well as NN methods, have high time complexity and poor interpretability of the models they create, making it difficult to intuitively explain the physicochemical relationship between spectral features and calcium carbonate content. Furthermore, these methods require high data quality and quantity, and insufficient sample size can easily lead to model overfitting. Summary of the Invention

[0005] Purpose of the Invention: The present invention aims to provide a method for predicting soil calcium carbonate content based on indoor hyperspectral and linear regression. This method, which uses hyperspectral reflectance data from a small number of samples and bands, is efficient, accurate, cost-effective, and environmentally friendly. It can provide scientifically reliable calcium carbonate content data for fields such as soil quality assessment, precision agriculture, and ecological and environmental protection. It can also inform the development of future soil inorganic carbon measurement instruments, promoting the sustainable management and utilization of soil resources.

[0006] Technical solution: The present invention provides a method for predicting soil calcium carbonate content based on indoor hyperspectral and linear regression, comprising the following steps:

[0007] Step 1: Collect soil samples and pre-treat them;

[0008] Step 2: measuring the spectral reflectance data of the soil sample in the 2000-2400 nm band;

[0009] Step 3, determining the calcium carbonate content of the soil sample;

[0010] Step 4: Perform breakpoint correction, detrending, and continuum removal on the spectral reflectance data of the soil sample in the 2000-2400 nm band to obtain processed data;

[0011] Step 5: Select the spectral reflectance data of the 2330-2360nm band from the processed data and calculate its maximum absorption depth;

[0012] Step 6: Based on the calcium carbonate content in step 3 and the maximum absorption depth in step 5, a linear regression model is established, and the linear regression model expression is used as a functional relationship between the maximum absorption depth and the calcium carbonate content;

[0013] Step 7: Based on the linear regression model and the spectral reflectance data of the soil samples in the target area, the calcium carbonate content of the soil samples in the target area is predicted.

[0014] Furthermore, step 1 specifically includes: collecting soil samples, removing debris from the collected soil samples, and allowing the soil samples to air dry naturally to complete the pretreatment of the soil samples.

[0015] Furthermore, step 2 is specifically as follows: measuring the reflectivity of the soil sample in the laboratory using a spectroradiometer, setting the incident angle of the light source to 15° with respect to the vertical direction, the light source to be 20-30 cm away from the sample, and the probe field of view angle to 5°, repeating the measurement 10-20 times for each sample, taking the average value as the reflectivity data, and obtaining the spectral reflectivity data of the soil sample in the 2000-2400 nm band.

[0016] Furthermore, step 4 specifically includes the following steps:

[0017] Step 4.1: Spectral reflectance data R Detrending is performed, and the calculation formula is:

[0018] ;

[0019] in, λ is the wavelength, R dto,λ The wavelength after initial detrending λ The reflectivity at R λ is the wavelength λ The reflectivity at a and b are the intercept and slope obtained by linear regression fitting, R dt,λ is the wavelength λ The reflectivity at the location is detrended.

[0020] Step 4.2: Use the Continuum Removed tool in ENVI software to remove the continuum of the detrended result data to obtain the processed reflectance data. R cr .

[0021] Furthermore, step 5 is specifically as follows: calculate the maximum absorption depth in the 2330-2360nm band, and the calculation formula is:

[0022] ;

[0023] in, H λ is the wavelength λ The maximum absorption depth at R cr,λ is the wavelength λspectral reflectance value after the continuum is removed; λ is the wavelength, ranging from 2330-2360nm.

[0024] Furthermore, step 6 specifically includes the following steps:

[0025] Step 6.1: Use the KS algorithm to divide all sample data sets into modeling sample sets in a ratio of 3:1 to 2:1. T and validation sample set V , specifically:

[0026] First, calculate the Euclidean distance between any two samples in the sample set, according to the calculation formula:

[0027]

[0028] in, for i and j The Euclidean distance between samples, H i and H j Respectively i and j The maximum absorption depth of the sample, y i and y j Respectively i and j Measured values ​​of calcium carbonate content in samples;

[0029] Select the two samples with the farthest Euclidean distance as the modeling sample set T The initial sample is then calculated, and the minimum distance between the remaining samples and the selected samples is then calculated, and the sample with the largest minimum distance is selected to join the modeling sample set. T ; Repeat the above steps until the modeling sample set T The number of samples in the test set reaches a predetermined proportion, and the remaining samples are used as the validation sample set. V ;

[0030] Step 6.2: Modeling sample set T Randomly divide into K subsets, with equal number of samples in each subset; for each round of validation, select one of the subsets as the validation subset Tv , the remaining K-1 subsets are combined as modeling subsets Ts , using the modeling subset Ts The soil calcium carbonate content prediction model was constructed by linear regression method, and the model expression is:

[0031] ;

[0032] in, To model a subset Ts Middle i Preliminary predicted values ​​of calcium carbonate content in soil samples, k 、 C are all rate coefficients. When the predicted value When it is less than 0, the predicted value is corrected to 0 according to the following formula:

[0033]

[0034] in, To model a subset Ts Middle i Final predicted value of calcium carbonate content of soil samples;

[0035] Step 6.3: Use the constructed model to predict the validation subset and calculate the coefficient of determination for this round of validation. R Tv 2 and root mean square error RMSE Tv ;

[0036] Step 6.4, select R Tv 2 Largest and RMSE Tv The smallest round k and C The optimal calibration coefficient was used to establish a linear regression model between the maximum absorption depth and the calcium carbonate content.

[0037] Step 6.5: Apply the linear regression model to the validation sample set and calculate the coefficient of determination for validation. R V 2 , root mean square error RMSE V , mean absolute error MAE V and relative prediction bias RPD V as an evaluation indicator of model accuracy.

[0038] Furthermore, in step 6.3, the coefficient of determination of the round of verification is R Tv 2 and root mean square error RMSE Tv The calculation formula is as follows:

[0039] ;

[0040] Where n is the number of samples in the validation subset, y Tv,i To verify the subset i The measured value of soil calcium carbonate content in each sample, To verify the subset i The predicted value of soil calcium carbonate content for each sample, is the average value of the measured values ​​of soil calcium carbonate content of all samples in the validation subset; R Tv 2 The larger the value, RMSE Tv The smaller the value, the higher the accuracy of the soil calcium carbonate content prediction model.

[0041] Furthermore, in step 6.5, the coefficient of determination of the calculation verification R V 2 , root mean square error RMSE V , mean absolute error MAE V and relative prediction bias RPD V The calculation formula is as follows:

[0042]

[0043] Among them, m is the number of samples in the validation sample set, y V,i To verify the sample set i The measured value of soil calcium carbonate content in each sample, To verify the sample set i The predicted value of soil calcium carbonate content for each sample, To verify the average value of the measured values ​​of soil calcium carbonate content of all samples in the sample set; R V 2 and RPD V The larger the value, RMSE V and MAE V The smaller the value of , the higher the accuracy of the linear regression model between the maximum absorption depth and the calcium carbonate content.

[0044] The present invention further discloses a computer device, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method of the present invention.

[0045] The present invention further discloses a computer-readable storage medium having a computer program / instruction stored thereon, which implements the steps of the method of the present invention when the computer program / instruction is executed by a processor.

[0046] Beneficial Effects: Compared with the existing technology, the present invention has the following significant advantages: The indoor hyperspectral-based soil calcium carbonate content estimation method provided by the present invention achieves rapid and accurate estimation of soil calcium carbonate content, effectively avoiding the large amount of polluting chemical tail liquids involved in traditional chemical analysis methods and the resulting high time and economic costs. It also greatly reduces the number of bands required for spectral analysis, and greatly simplifies the modeling method by using a single linear regression instead of a multivariate nonlinear regression, shortening the estimation time. The present invention is rationally designed and can construct a linear regression model between the maximum absorption depth obtained after soil hyperspectral pretreatment and the soil calcium carbonate content, thereby improving the accessibility of soil calcium carbonate content data. The method is highly feasible, efficient, accurate, low-cost, and environmentally friendly, making it suitable for promotion. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a flow chart of an embodiment of the present invention.

[0048] Figure 2 It is a schematic diagram of the spectrum testing device of the present invention.

[0049] Figure 3 It is a scatter plot of the actual value and predicted value of soil calcium carbonate content in the verification sample set of an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The technical solution of the present invention will be further described below with reference to the accompanying drawings.

[0051] Example

[0052] This embodiment takes the soil calcium carbonate content in the area east of Fangong Dike, Dongtai City, Jiangsu Province as an example. Figure 1 This is a flow chart of an embodiment of the present invention. This example further illustrates the present invention in detail regarding the entire process of sample processing, data preprocessing, calculating the maximum absorption depth, establishing a linear regression model, and establishing a functional relationship between the maximum absorption depth and the calcium carbonate content, as follows:

[0053] The present invention provides a soil calcium carbonate content estimation method based on indoor hyperspectral data, comprising the following steps:

[0054] S1. Collect soil samples from the target area and perform pretreatment;

[0055] S2. Measure the spectral reflectance of the soil sample at 2000-2400 nm;

[0056] S3. Determine the calcium carbonate content of the soil sample;

[0057] S4. Detrending and continuum removal processing is performed on the reflectance data in the 2000-2400 nm band;

[0058] S5. Select the processed data in the 2330-2360 nm band and calculate its maximum absorption depth;

[0059] S6. Establishing a linear regression model based on the maximum absorption depth and calcium carbonate content;

[0060] S7. Establish the functional relationship between maximum absorption depth and calcium carbonate content based on the linear regression model.

[0061] As a preferred embodiment of the present invention, step S1 specifically includes: collecting 110 soil samples that are typical and regionally representative in the study area, removing debris from the samples, and allowing the soil samples to dry naturally to complete the pretreatment of the soil samples.

[0062] As a preferred embodiment of the present invention, step S2 is specifically: in a dark laboratory, use Figure 2 The FieldSpec3 portable optical spectrometer was used to measure soil spectral reflectance data. The spectrometer probe had a 5-degree field of view (B = 2.5°) and was perpendicular to the soil sample. The distance (H) to the soil sample was 15 cm, and the detection radius (R2) was 0.655 cm. The light source was a 50W halogen lamp, located at a 15° angle (A) to the vertical and a distance (L) from the sample of 20-30 cm. The sample container was a small aluminum circular box with a radius (R1) of 2.5 cm and a depth of 1 cm, placed on a black automatic rotating platform. Before measurement, dark current was removed. Absolute reflectance was then obtained using a 40×40 cm diffuse reflectance standard reference plate. During the measurement, the soil sample surface was leveled with a ruler, and the circular box containing the soil sample was placed on the black automatic rotating platform. During each rotation of the circular box, the spectrometer measured 20 spectral curves at equal intervals, and the average value was calculated as the reflectance data. After measuring the spectral data of five soil samples, the spectrometer was recalibrated using a reference white plate to minimize error.

[0063] As a preferred embodiment of the present invention, step S3 specifically involves measuring the calcium carbonate content of the soil sample using a gas volumetric method. This involves adding dilute hydrochloric acid to the soil sample, measuring the volume of carbon dioxide gas generated by the reaction using a gas collection device, and calculating the calcium carbonate content in the soil sample. The calcium carbonate content in the soil in the study area ranged from 1.45 g / kg to 67.97 g / kg, with an average of 34.29 g / kg and a standard deviation of 19.49 g / kg.

[0064] As a preferred embodiment of the present invention, step S4 includes the following sub-steps:

[0065] S4.1. Reflectance data R Detrending is performed according to the calculation formula:

[0066]

[0067] in, λ is the wavelength, R dto,λ The wavelength after initial detrending λ The reflectivity at R λ is the wavelength λ The reflectivity at a and b are the intercept and slope obtained by linear regression fitting, R dt,λ is the wavelength λ The reflectivity at the detrended location is the result of the detrended process. This is because R dto,λ may be less than 0, which will hinder the continuum removal process in S4.2, so it is necessary to R dto,λ The range is adjusted to the non-negative range.

[0068] S4.2. Use the Continuum Removed tool in ENVI Classic 5.6 software to remove the trend of the result data. R dt Perform continuum removal processing to obtain processed reflectivity data R cr .

[0069] As a preferred embodiment of the present invention, step S5 is specifically:

[0070] Calculate the reflectance data after processing in each band of 2000-2400nm R cr,λ The Pearson correlation coefficient with soil calcium carbonate content is calculated according to the formula:

[0071]

[0072] in, r λ is the wavelength λ Pearson correlation coefficient between the processed reflectance data and soil calcium carbonate content; N is the number of data points (N=110); For the wavelength λ Place i Processed reflectance data of samples; is the wavelength λThe average value of the reflectance data of all samples after processing; y i For the i A measurement of soil calcium carbonate content; The Pearson correlation coefficient between the reflectance data after processing at each wavelength of 2000-2400nm and the soil calcium carbonate content was calculated. r , which ranges from -0.911356 to 0.338588, with an average of -0.473652 and a standard deviation of 0.317089. Among them, the Pearson correlation coefficient between the reflectance data of each wavelength in the 2330-2360nm band after processing and the soil calcium carbonate content is r The absolute value is closest to 1, ranging from -0.911356 to -0.859884, with an average of -0.890840 and a standard deviation of 0.012639. This indicates that the processed reflectance data in the 2330-2360 nm band have a significant negative correlation with the soil calcium carbonate content, making this band suitable for predicting calcium carbonate content.

[0073] Select the processed data of the 2330-2360nm band and calculate its maximum absorption depth according to the calculation formula:

[0074]

[0075] in, H λ is the wavelength λ The maximum absorption depth at R cr,λ is the wavelength λ spectral reflectance value after the continuum is removed; λ The wavelength is in the range of 2330-2360nm. The maximum absorption depth of each soil sample is calculated H , which ranges between 0.097827 and 0.444846, with a mean of 0.289283 and a standard deviation of 0.088376.

[0076] As a preferred embodiment of the present invention, step S6 includes the following sub-steps:

[0077] S6.1. Use the KS algorithm to divide all sample data sets into modeling sample sets in a ratio of 8:3. T and validation sample set V , the specific steps are as follows:

[0078] First, calculate the Euclidean distance between any two samples in the sample set, according to the calculation formula:

[0079]

[0080] in, for i and j The Euclidean distance between samples, H i and H j Respectively i and j The maximum absorption depth of the sample, y i and y j Respectively i and j Measured value of calcium carbonate content of each sample (g / kg).

[0081] Then select the two samples with the farthest Euclidean distance as the modeling sample set T The initial sample is then calculated, and the minimum distance between the remaining samples and the selected samples is then calculated, and the sample with the largest minimum distance is selected to join the modeling sample set. T Repeat the above steps until the modeling sample set T The number of samples in the test set reaches a predetermined proportion, and the remaining samples are used as the validation sample set. V .

[0082] S6.2. Modeling sample set T Randomly divide into 5 subsets, each containing 16 samples; for each round of validation, one of the subsets is selected as the validation subset Tv , the remaining four subsets are combined as the modeling subset Ts , using the modeling subset Ts The soil calcium carbonate content prediction model was constructed by linear regression method, and the model expression is:

[0083] ;

[0084] in, To model a subset Ts Middle i Preliminary predicted values ​​of calcium carbonate content in soil samples, k 、 C are all rate coefficients. When the predicted value When it is less than 0, the predicted value is corrected to 0 according to the following formula;

[0085]

[0086] in, To model a subset Ts Middle i Final predicted value of calcium carbonate content of soil samples;

[0087] S6.3. Use the constructed model to predict the validation subset and calculate the coefficient of determination for this round of validation. R Tv 2 , root mean square error RMSE Tv , according to the calculation formula:

[0088]

[0089] Where n is the number of samples in the validation subset (n=16), y Tv,i To verify the subset i Measured value of soil calcium carbonate content of each sample (g / kg), To verify the subset i The predicted value of soil calcium carbonate content for each sample (g / kg), is the average value of the measured soil calcium carbonate content of all samples in the validation subset (g / kg); R Tv 2 The larger the value, RMSE Tv The smaller the value, the higher the accuracy of the soil calcium carbonate content prediction model.

[0090] S6.4. Selection R Tv 2 Largest and RMSE Tv The smallest round k and C The optimal calibration coefficient was used to establish a linear regression model between the maximum absorption depth and the calcium carbonate content.

[0091] S6.5. Apply the linear regression model to the validation sample set and calculate the coefficient of determination for validation. R V 2 , root mean square error RMSE V , mean absolute error MAE V and relative prediction bias RPD V As an evaluation index of model accuracy, according to the calculation formula:

[0092]

[0093] Among them, m is the number of samples in the validation sample set (m=30), y V,i To verify the sample seti Measured value of soil calcium carbonate content of each sample (g / kg), To verify the sample set i The predicted value of soil calcium carbonate content for each sample (g / kg), To verify the average value of the measured soil calcium carbonate content of all samples in the sample set (g / kg); R V 2 and RPD V The larger the value, RMSE V and MAE V The smaller the value, the higher the accuracy of the linear regression model between the maximum absorption depth and the calcium carbonate content.

[0094] In this embodiment, the best round of cross-validation modeling process R Tv 2 =0.8917, RMSE Tv =6.7575g / kg, optimal calibration coefficient k =192.3373, C =-21.8461, the linear regression model expression between the maximum absorption depth and calcium carbonate content is: y =192.3373× H -21.8461. The scatter plot of the actual and predicted values ​​of soil calcium carbonate content in the validation sample set is as follows Figure 3 As shown. The coefficient of determination of the validation sample set R V ² is 0.8452, root mean square error RMSE V The mean absolute error (MAE) is 7.6725 g / kg. V The relative prediction deviation RPD is 6.2541 g / kg. V The value is 2.5853, and all accuracy indicators have reached the expected targets (R²>0.8, RMSE<10g / kg, MAE<10g / kg, RPD>2.0), indicating that the model has good prediction performance, and the process goes to step S7.

[0095] As a preferred embodiment of the present invention, step S7 specifically comprises: using the linear regression model expression obtained in S6.5 as a functional relationship between the maximum absorption depth and the calcium carbonate content, and estimating the soil calcium carbonate content based on the reflectance spectrum data of soil samples with other unknown calcium carbonate contents in the study area.

Claims

1. A soil calcium carbonate content prediction method based on indoor hyperspectral and linear regression, characterized in that: The steps include: Step 1: Collect soil samples and pre-treat them; Step 2: measuring the spectral reflectance data of the soil sample in the 2000-2400 nm band; Step 3, determining the calcium carbonate content of the soil sample; Step 4: Perform breakpoint correction, detrending, and continuum removal on the spectral reflectance data of the soil sample in the 2000-2400 nm band to obtain processed data; Step 5: Select the spectral reflectance data of the 2330-2360nm band from the processed data and calculate its maximum absorption depth; Step 6: Based on the calcium carbonate content in step 3 and the maximum absorption depth in step 5, a linear regression model is established, and the linear regression model expression is used as a functional relationship between the maximum absorption depth and the calcium carbonate content; Step 6 specifically includes the following steps: Step 6.1: Use the KS algorithm to divide all sample data sets into modeling sample sets in a ratio of 3:1 to 2:

1. T and validation sample set V , specifically: First, calculate the Euclidean distance between any two samples in the sample set, according to the calculation formula: in, for i and j The Euclidean distance between samples, H i and H j Respectively i and j The maximum absorption depth of the sample, y i and y j Respectively i and j Measured values ​​of calcium carbonate content in samples; Select the two samples with the farthest Euclidean distance as the modeling sample set T The initial sample is then calculated, and the minimum distance between the remaining samples and the selected samples is then calculated, and the sample with the largest minimum distance is selected to join the modeling sample set. T ; Repeat the above steps until the modeling sample set T The number of samples in the test set reaches a predetermined proportion, and the remaining samples are used as the validation sample set. V ; Step 6.2: Modeling sample set T Randomly divide into K subsets, with equal number of samples in each subset; for each round of validation, select one of the subsets as the validation subset TV , the remaining K-1 subsets are combined as modeling subsets Ts , using the modeling subset Ts The soil calcium carbonate content prediction model was constructed by linear regression method, and the model expression is: ； in, To model a subset Ts Middle i Preliminary predicted values ​​of calcium carbonate content in soil samples, k 、 C are all rate coefficients. When the predicted value When it is less than 0, the predicted value is corrected to 0 according to the following formula; in, To model a subset Ts Middle i Final predicted value of calcium carbonate content of soil samples; Step 6.3: Use the constructed model to predict the validation subset and calculate the coefficient of determination for this round of validation. R Tv 2 and root mean square error RMSE Tv ; Step 6.4, select R Tv 2 Largest and RMSE Tv The smallest round k and C The optimal calibration coefficient was used to establish a linear regression model between the maximum absorption depth and the calcium carbonate content. Step 6.5: Apply the linear regression model to the validation sample set and calculate the coefficient of determination for validation. R V 2 , root mean square error RMSE V , mean absolute error MAE V and relative prediction bias RPD V As an evaluation indicator of model accuracy; Step 7: Based on the linear regression model and the spectral reflectance data of the soil samples in the target area, the calcium carbonate content of the soil samples in the target area is predicted.

2. A soil calcium carbonate content prediction method based on indoor hyperspectral and linear regression according to claim 1, characterized in that, Step 1 specifically includes: collecting soil samples, removing debris from the collected soil samples, allowing the soil samples to air dry naturally, and completing the pretreatment of the soil samples.

3. A soil calcium carbonate content prediction method based on indoor hyperspectral and linear regression according to claim 1, characterized in that: Step 2 is as follows: the reflectivity of the soil sample is measured in the laboratory using a spectroradiometer. The incident angle of the light source is set to 15° with respect to the vertical direction, the light source is 20-30 cm away from the sample, and the probe field of view angle is 5°. Each sample is measured 10-20 times, and the average value is taken as the reflectivity data to obtain the spectral reflectivity data of the soil sample in the 2000-2400 nm band.

4. The method for predicting soil calcium carbonate content based on indoor hyperspectral and linear regression according to claim 1, wherein: Step 4 specifically includes the following steps: Step 4.1: Spectral reflectance data R Detrending is performed, and the calculation formula is: ； in, λ is the wavelength, R dto,λ The wavelength after initial detrending λ The reflectivity at R λ wavelength λ The reflectivity at a and b are the intercept and slope obtained by linear regression fitting, R dt,λ wavelength λ The reflectivity at the location is detrended. Step 4.2: Use the Continuum Removed tool in ENVI software to remove the continuum of the detrended result data to obtain the processed reflectance data. R cr .

5. The method for predicting soil calcium carbonate content based on indoor hyperspectral and linear regression according to claim 4, wherein: Step 5 is to calculate the maximum absorption depth in the 2330-2360nm band using the following formula: ； in, H λ wavelength λ The maximum absorption depth at R cr,λ wavelength λ spectral reflectance value after the continuum is removed; λ is the wavelength, ranging from 2330-2360nm.

6. The method for predicting soil calcium carbonate content based on indoor hyperspectral and linear regression according to claim 1, wherein: In step 6.3, the coefficient of determination of this round of verification is R Tv 2 and root mean square error RMSE Tv The calculation formula is as follows: ； Where n is the number of samples in the validation subset, y Tv,i To verify the subset i The measured value of soil calcium carbonate content in each sample, To verify the subset i The predicted value of soil calcium carbonate content for each sample, is the average value of the measured values ​​of soil calcium carbonate content of all samples in the validation subset; R Tv 2 The larger the value, RMSE Tv The smaller the value, the higher the accuracy of the soil calcium carbonate content prediction model.

7. The method for predicting soil calcium carbonate content based on indoor hyperspectral and linear regression according to claim 1, wherein: In step 6.5, the coefficient of determination of the calculation verification R V 2 , root mean square error RMSE V , mean absolute error MAE V and relative prediction bias RPD V The calculation formula is as follows: Among them, m is the number of samples in the validation sample set, y V,i To verify the sample set i The measured value of soil calcium carbonate content in each sample, To verify the sample set i The predicted value of soil calcium carbonate content for each sample, To verify the average value of the measured values ​​of soil calcium carbonate content of all samples in the sample set; R V 2 and RPD V The larger the value, RMSE V and MAE V The smaller the value of , the higher the accuracy of the linear regression model between the maximum absorption depth and the calcium carbonate content.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory, wherein: The processor executes the computer program to implement the steps of the method according to claim 1.

9. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instructions are executed by a processor, the steps of the method according to claim 1 are implemented.

Images