A high-precision soil moisture prediction method based on spatiotemporal convolutional neural network coupling model

Abstract

The present invention relates to the field of soil moisture prediction technology, and discloses a high-precision soil moisture prediction method based on a spatiotemporal convolutional neural network coupling model, comprising the following steps: deploying soil moisture detection equipment equipped with GPS to obtain measured soil moisture data at different depths in a target area, obtaining satellite remote sensing images of the target area, obtaining humidity data for the entire area after correcting the images, and correcting the errors in the remote sensing humidity data using sensors and surface factors. This regional soil moisture dynamic monitoring method based on multi-source data fusion and deep learning avoids the limitations of a single data source by fusing GPS-equipped soil moisture sensors with satellite remote sensing data, and improves soil moisture monitoring accuracy by introducing surface factors to correct remote sensing data. The results show that the early warning and forecast accuracy is no less than 90%. A machine learning model is used to expand the measured data of the humidity sensor and predict humidity changes within a certain time window in the future.

Description

Technical Field

[0001] The present invention belongs to the technical field of soil moisture prediction and forecasting, and in particular relates to a high-precision soil moisture prediction method based on a spatiotemporal convolutional neural network coupling model. Background Art

[0002] Soil moisture is a key factor influencing the occurrence of landslides. Changes in soil moisture directly affect the physical and mechanical properties of the soil. In particular, when precipitation or snowmelt causes soil moisture content to increase, soil cohesion and friction decrease, threatening slope stability. Excessive soil moisture can lead to soil saturation, increasing pore water pressure and weakening the bond between soil particles, ultimately triggering landslides. In actual monitoring, soil moisture is considered a key indicator of landslide precursors. Monitoring changes in soil moisture can help identify potential landslide risks in a timely manner. Therefore, in landslide early warning systems, the proper monitoring and analysis of soil moisture is key to improving landslide warning and protection capabilities. By combining meteorological data with geological conditions, establishing a comprehensive landslide early warning model can more accurately predict the timing of landslides and provide a scientific basis for decision-makers.

[0003] Common monitoring methods include buried soil moisture sensors and satellite remote sensing. Recent advances in remote sensing technology, in particular, have made large-scale soil moisture monitoring more feasible, effectively improving the accuracy of landslide early warnings. First, while buried soil moisture sensors can provide localized, high-precision monitoring data, their density is limited by terrain conditions and economic costs, making it difficult to cover the entire landslide area. Sensor deployment and maintenance are also hampered by factors such as complex terrain and inaccessible transportation. Furthermore, the long-term stability of sensor data is affected by changes in soil physical and chemical properties, necessitating regular calibration and maintenance of the sensors. Furthermore, while remote sensing technology can acquire soil moisture information over a large area, its accuracy is limited by spatial and temporal resolution, making it difficult to achieve the same precision as sensor-derived data. Furthermore, remote sensing monitoring results are subject to external environmental conditions, such as vegetation cover, surface disturbances, and atmospheric conditions. For example, the shading effect of vegetation can lead to biased monitoring data, while atmospheric water vapor and cloud cover can also affect the accuracy of soil moisture inversion. This makes the fusion of remote sensing data with ground-based sensor data a crucial research direction in soil moisture monitoring.

[0004] Future research will focus on combining the strengths of sensors and remote sensing technologies, leveraging data assimilation and multi-source information fusion to organically integrate ground-based monitoring with remote sensing observations. This integration will be crucial in addressing current challenges in soil moisture monitoring accuracy and spatial coverage. This fusion approach will enable a more comprehensive understanding of soil moisture changes prior to landslides, further enhancing landslide monitoring and early warning capabilities.

[0005] In view of this, the present invention is proposed. Summary of the Invention

[0006] The technical problem to be solved by the present invention is to overcome the shortcomings of the existing technology. The present invention provides a high-precision soil moisture prediction method based on a spatiotemporal convolutional neural network coupling model, which has the advantage of high precision in landslide deformation monitoring and solves the problem of single data between GPS ground measured data and InSAR data.

[0007] In order to solve the above technical problems, the basic concept of the technical solution adopted by the present invention is:

[0008] A high-precision soil moisture prediction method based on a spatiotemporal convolutional neural network coupling model comprises the following steps:

[0009] S1: Deploy soil moisture detection equipment equipped with GPS function to the target area to obtain soil moisture measurement data at different depths;

[0010] S2: Obtain remote sensing satellite images of the target area, import surface factors into the deep learning model for training, use the trained learning model to correct the remote sensing images and classify different types of terrain; the specific steps for constructing remote sensing image optimization and extracting features are as follows:

[0011] S2.1: Define the three-dimensional coordinate matrix C = [xyz] of the humidity sensor in the x, y, and z directions, where C is the three-dimensional coordinate quantity and xyz is the coordinate value of the sensor in the north-south, east-west, and vertical directions, respectively;

[0012] S2.2: Define the surface factor matrix E = [SAV] around the humidity sensor deployment point, where E is the surface factor and SAV are the slope, aspect, and vegetation coverage around the deployment point.

[0013] S2.3: In the input layer, the coordinate matrix of the known points and the terrain data are input into the convolutional neural network as a separate feature channel. The remote sensing image optimization matrix is ​​constructed.

[0014] I'=[I,C,E]

[0015] Among them, I' is the enhanced image matrix, I is the original remote sensing image, C is the three-dimensional coordinate matrix of the known points, and E is the terrain information matrix;

[0016] S2.4: Use CNN to extract the spatial features of the target remote sensing image. For the input image I', the feature map is obtained after the convolution operation of the CNN layer. The expression is:

[0017]

[0018] Among them, l represents the number of convolution layers, k represents the number of convolution kernels, is the weight of the kth convolution kernel, * represents the convolution operation, is the bias term, σ is the activation function;

[0019] S2.5: Combine the surface factor matrix E and the spatial feature matrix Perform fusion, fusion module X t The expression is:

[0020]

[0021] Among them, α t is the attention weight of the surface factor;

[0022] S2.6: Build an LSTM model and transform X t Input the LSTM model to extract the temporal features of the target remote sensing image. The LSTM core expression is:

[0023] Determine which information in the memory unit needs to be forgotten. The forget gate expression is:

[0024] f t =ρ(W f ·[h t-1 ,Q t ]+d f )

[0025] Among them, f t is the forgotten information, ρ is the activation function, W f is the weight matrix of the forget gate, h t-1 Indicates the hidden state of the previous moment, Q t Represents the input at the current moment, d f is the bias term of the forget gate;

[0026] Determine what new information needs to be stored in the memory cell. The input gate expression is:

[0027] i t =ρ(W i ·[h t-1 ,Q t ]+d i )

[0028] Among them, Wi is the weight matrix of the input gate, d i is the bias term of the input gate;

[0029] Candidate memory cell states, The expression is:

[0030]

[0031] Among them, W u is the weight matrix of the candidate state, d u is the bias term, and tanh is the activation function;

[0032] Update the memory unit state, U t The expression is:

[0033]

[0034] Among them, U t-1 Indicates the state of the memory unit at the previous moment;

[0035] Determine the hidden state O of the output t , the output gate expression is:

[0036] O t =ε*W O ·[h t-1 ,Q i ]+d O

[0037] Among them, ε represents the activation function of the output gate, W O is the weight matrix of the output gate, d O is the bias term of the output gate;

[0038] h t =O t tanh+U t

[0039] Among them, h t Represents the hidden state output at the current moment;

[0040] S3: Construct improved MPDI and NDVI formulas and use surface factors to correct the soil moisture inversion value of the area. The specific steps of improving NDVI and MPDI are as follows:

[0041] S3.1: Introduce the soil adjustment coefficient L and calculate the improved remote sensing image index SAVI, which is expressed as:

[0042]

[0043] Among them, L is the coefficient obtained by analyzing soil type and texture through field soil sampling, NIR is the reflectance of the near-infrared band, and Red is the reflectance of the red light band;

[0044] S3.2: Introduce the slope S and the slope direction A and calculate the incident angle cos(θ). The expression is:

[0045] cos(θ)=cos(μ)·cos(S)+sin(μ)·sin(S)·cos(A)

[0046] Among them, μ is the solar zenith angle, A is the slope direction, and S is the slope;

[0047] S3.3: Calculate the improved remote sensing image index TSNDVI based on the incident angle value cos(θ). The expression is:

[0048] TSNDVI=SAVI×cos(θ)

[0049] S3.4: Improve the soil moisture status MPDI1 based on the soil's water retention and thermal properties, expressed as:

[0050]

[0051] Among them, γ represents the influence weight of soil texture, NIR is the reflectance of the near-infrared band, SWIR is the reflectance of the short-wave infrared band, and Tq is the soil texture coefficient;

[0052] S3.5: Improve the soil moisture status MPDI2 based on the scattering and reflection of light on the surface. The expression is:

[0053] MPDI2=MPDI1·(1+δ·Rou)

[0054] Among them, δ represents the influence weight of surface roughness, and Rou represents the degree of surface roughness;

[0055] S3.6: Because the structure of the vegetation canopy (e.g., canopy height and density) changes the reflective properties of water, the soil moisture status MPDI3 is modified as follows:

[0056] MPDI3=MPDI2·(1+C·Vs)

[0057] Among them, C represents the influence weight of the structure of the vegetation canopy, and Vs represents the canopy structure coefficient;

[0058] S4: Using the measured data from ground sensors to assist in the humidity inversion of remote sensing data, the soil moisture change in the target monitoring area is obtained. The specific steps of using the measured data from ground sensors to assist in the humidity inversion of remote sensing data are as follows:

[0059] S4.1: Replace the humidity value of the pixel corresponding to the measured point in the remote sensing image with the actual humidity value of the measured point;

[0060] S4.2: Construct a regression model based on the measured humidity data and surface factors. The predicted value of the model output is M, which is expressed as:

[0061] M i =φ(P i ,E i )+τ i

[0062] Among them, P i is the humidity at the known measured point, E i is the surface factor matrix, τ i is the error term;

[0063] S4.3: Use the humidity of the nearest measured point to perform interpolation correction and obtain the corresponding interpolation matrix S, which is expressed as:

[0064]

[0065] Among them, S is the humidity value of the non-measured point, n is the number of measured points around the target point, S i is the humidity value corresponding to the measured point, is the calculation weight;

[0066] S4.4: Combine the prediction results of the regression model with the interpolation results to obtain the final corrected humidity value matrix L, which is expressed as:

[0067] L final =Δ·S+(1-Δ)·M

[0068] Among them, L final is the combined humidity estimate, Δ is the weighting coefficient used to balance the regression model and the interpolation results, S is the humidity interpolation value at the current point, and M is the humidity prediction value at the current point;

[0069] S5: Construct an LSTM model to predict the humidity change in the target monitoring area at a future time point. The specific steps of using LSTM to predict the humidity change in the target monitoring area at a future time point are as follows:

[0070] S5.1: Input all attributes of the current point and construct the future input data sequence K, which is expressed as:

[0071] K i ={I,C,E,Tem,Mos}

[0072] Among them, I is the original remote sensing image, C is the three-dimensional coordinate matrix of the known points, E is the terrain information matrix, Tem is the meteorological data, and Mos is the current humidity data;

[0073] S5.2: Input the sequence into the LSTM model trained in the second stage. The humidity at each time step is predicted through the time recursion mechanism of the LSTM model.

[0074] S5.3: Combine surface factors to make the prediction more consistent with the actual humidity value G in the area. The expression is:

[0075]

[0076] in, is the weight calculated based on the surface factor, N is the humidity feature obtained by the LSTM model, and E is the surface factor matrix;

[0077] S5.4: For each prediction step, the LSTM model will update the hidden state h t As the input of the next time step, combined with surface factors and meteorological data, the future humidity value Hv is recursively predicted. The prediction formula is:

[0078]

[0079] in, represents the predicted humidity value at time t+1, and ω(·) represents the prediction layer.

[0080] After adopting the above technical solution, the present invention has the following beneficial effects compared with the prior art. Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described below at the same time:

[0081] This high-precision soil moisture prediction method, based on a spatiotemporal convolutional neural network coupling model, overcomes the limitations of a single data source by fusing measured soil moisture data at different depths with remote sensing data. It utilizes a deep learning model to improve image recognition. Furthermore, a surface factor is introduced to optimize and correct the soil inversion results of remote sensing imagery of the target area, and to capture soil moisture variations in the target area, thereby improving the accuracy of soil moisture monitoring. Results demonstrate an early warning and forecast accuracy of at least 90%. The deep learning model extracts the temporal and spatial characteristics of the target area's moisture data and predicts surface moisture data for a specific time window in the future. This method then constructs a spatiotemporal coupled neural network to recover moisture variations in the target area.

[0082] The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] The drawings described below are only some embodiments. A person skilled in the art can derive other drawings based on these drawings without inventive effort. In the drawings:

[0084] Figure 1 This is a flowchart of a high-precision soil moisture prediction method based on a spatiotemporal convolutional neural network coupling model proposed in the present invention.

[0085] It should be noted that these drawings and textual descriptions are not intended to limit the conceptual scope of the present invention in any way, but rather to illustrate the concept of the present invention for those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0086] The present invention will now be described in further detail with reference to the accompanying drawings.

[0087] See also Figure 1 As shown, in this embodiment, a high-precision soil moisture prediction method based on a spatiotemporal convolutional neural network coupling model is provided, comprising the following steps:

[0088] S1: Deploy soil moisture detection equipment equipped with GPS function to the target area to obtain soil moisture measurement data at different depths;

[0089] S2: Obtain remote sensing satellite images of the target area, import surface factors into the deep learning model for training, use the trained learning model to correct the remote sensing images and classify different types of terrain; the specific steps for constructing remote sensing image optimization and extracting features are as follows:

[0090] S2.1: Define the three-dimensional coordinate matrix C = [xyz] of the humidity sensor in the x, y, and z directions, where C is the three-dimensional coordinate quantity and xyz is the coordinate value of the sensor in the north-south, east-west, and vertical directions, respectively;

[0091] S2.2: Define the surface factor matrix E = [SAV] around the humidity sensor deployment point, where E is the surface factor and SAV are the slope, aspect, and vegetation coverage around the deployment point.

[0092] S2.3: In the input layer, the coordinate matrix of the known points and the terrain data are input into the convolutional neural network as a separate feature channel. The remote sensing image optimization matrix is ​​constructed.

[0093] I'=[I,C,E]

[0094] Among them, I' is the enhanced image matrix, I is the original remote sensing image, C is the three-dimensional coordinate matrix of the known points, and E is the terrain information matrix;

[0095] S2.4: Use CNN to extract the spatial features of the target remote sensing image. For the input image I', the feature map is obtained after the convolution operation of the CNN layer. The expression is:

[0096]

[0097] Among them, l represents the number of convolution layers, k represents the number of convolution kernels, is the weight of the kth convolution kernel, * represents the convolution operation, is the bias term, σ is the activation function;

[0098] S2.5: Combine the surface factor matrix E and the spatial feature matrix Perform fusion, fusion module X t The expression is:

[0099]

[0100] Among them, α t is the attention weight of the surface factor;

[0101] S2.6: Build an LSTM model and transform X t Input the LSTM model to extract the temporal features of the target remote sensing image. The LSTM core expression is:

[0102] Determine which information in the memory unit needs to be forgotten. The forget gate expression is:

[0103] f t =ρ(W f ·[h t-1 ,Q t ]+d f )

[0104] Among them, f t is the forgotten information, ρ is the activation function, W f is the weight matrix of the forget gate, h t-1 Indicates the hidden state of the previous moment, Q t Represents the input at the current moment, d f is the bias term of the forget gate;

[0105] Determine what new information needs to be stored in the memory cell. The input gate expression is:

[0106] i t =ρ(W i ·[h t-1 ,Q t ]+d i )

[0107] Among them, W i is the weight matrix of the input gate, d i is the bias term of the input gate;

[0108] Candidate memory cell states, The expression is:

[0109]

[0110] Among them, W u is the weight matrix of the candidate state, d u is the bias term, and tanh is the activation function;

[0111] Update the memory unit state, U t The expression is:

[0112]

[0113] Among them, U t-1 Indicates the state of the memory unit at the previous moment;

[0114] Determine the hidden state O of the output t , the output gate expression is:

[0115] O t =ε*W O ·[h t-1 ,Q i ]+d O

[0116] Among them, ε represents the activation function of the output gate, W O is the weight matrix of the output gate, d O is the bias term of the output gate;

[0117] h t =O t tanh+U t

[0118] Among them, h t Represents the hidden state output at the current moment;

[0119] S3: Construct improved MPDI and NDVI formulas and use surface factors to correct the soil moisture inversion value of the area. The specific steps of improving NDVI and MPDI are as follows:

[0120] S3.1: Introduce the soil adjustment coefficient L and calculate the improved remote sensing image index SAVI, which is expressed as:

[0121]

[0122] Among them, L is the coefficient obtained by analyzing soil type and texture through field soil sampling, NIR is the reflectance of the near-infrared band, and Red is the reflectance of the red light band;

[0123] S3.2: Introduce the slope S and the slope direction A and calculate the incident angle cos(θ). The expression is:

[0124] cos(θ)=cos(μ)·cos(S)+sin(μ)·sin(S)·cos(A)

[0125] Among them, μ is the solar zenith angle, A is the slope direction, and S is the slope;

[0126] S3.3: Calculate the improved remote sensing image index TSNDVI based on the incident angle value cos(θ). The expression is:

[0127] TSNDVI=SAVI×cos(θ)

[0128] S3.4: Improve the soil moisture status MPDI1 based on the soil's water retention and thermal properties, expressed as:

[0129]

[0130] Among them, γ represents the influence weight of soil texture, NIR is the reflectance of the near-infrared band, SWIR is the reflectance of the short-wave infrared band, and Tq is the soil texture coefficient;

[0131] S3.5: Improve the soil moisture status MPDI2 based on the scattering and reflection of light on the surface. The expression is:

[0132] MPDI2=MPDI1·(1+δ·Rou)

[0133] Among them, δ represents the influence weight of surface roughness, and Rou represents the degree of surface roughness;

[0134] S3.6: Because the structure of the vegetation canopy (e.g., canopy height and density) changes the reflective properties of water, the soil moisture status MPDI3 is modified as follows:

[0135] MPDI3=MPDI2·(1+C·Vs)

[0136] Among them, C represents the influence weight of the structure of the vegetation canopy, and Vs represents the canopy structure coefficient;

[0137] S4: Using the measured data from ground sensors to assist in the humidity inversion of remote sensing data, the soil moisture change in the target monitoring area is obtained. The specific steps of using the measured data from ground sensors to assist in the humidity inversion of remote sensing data are as follows:

[0138] S4.1: Replace the humidity value of the pixel corresponding to the measured point in the remote sensing image with the actual humidity value of the measured point;

[0139] S4.2: Construct a regression model based on the measured humidity data and surface factors. The predicted value of the model output is M, which is expressed as:

[0140] M i =φ(P i ,E i )+τ i

[0141] Among them, P i is the humidity at the known measured point, E i is the surface factor matrix, τ i is the error term;

[0142] S4.3: Use the humidity of the nearest measured point to perform interpolation correction and obtain the corresponding interpolation matrix S, which is expressed as:

[0143]

[0144] Among them, S is the humidity value of the non-measured point, n is the number of measured points around the target point, S i is the humidity value corresponding to the measured point, is the calculation weight;

[0145] S4.4: Combine the prediction results of the regression model with the interpolation results to obtain the final corrected humidity value matrix L, which is expressed as:

[0146] L final =Δ·S+(1-Δ)·M

[0147] Among them, L final is the combined humidity estimate, Δ is the weighting coefficient used to balance the regression model and the interpolation results, S is the humidity interpolation value at the current point, and M is the humidity prediction value at the current point;

[0148] S5: Construct an LSTM model to predict the humidity change in the target monitoring area at a future time point. The specific steps of using LSTM to predict the humidity change in the target monitoring area at a future time point are as follows:

[0149] S5.1: Input all attributes of the current point and construct the future input data sequence K, which is expressed as:

[0150] K i ={I,C,E,Tem,Mos}

[0151] Among them, I is the original remote sensing image, C is the three-dimensional coordinate matrix of the known points, E is the terrain information matrix, Tem is the meteorological data, and Mos is the current humidity data;

[0152] S5.2: Input the sequence into the LSTM model trained in the second stage. The humidity at each time step is predicted through the time recursion mechanism of the LSTM model.

[0153] S5.3: Combine surface factors to make the prediction more consistent with the actual humidity value G in the area. The expression is:

[0154]

[0155] in, is the weight calculated based on the surface factor, N is the humidity feature obtained by the LSTM model, and E is the surface factor matrix;

[0156] S5.4: For each prediction step, the LSTM model will update the hidden state h t As the input of the next time step, combined with surface factors and meteorological data, the future humidity value Hv is recursively predicted. The prediction formula is:

[0157]

[0158] in, represents the predicted humidity value at time t+1, and ω(·) represents the prediction layer.

[0159] This high-precision soil moisture prediction method, based on a spatiotemporal convolutional neural network coupling model, overcomes the limitations of a single data source by fusing measured soil moisture data at different depths with remote sensing data. It utilizes a deep learning model to improve image recognition. Furthermore, a surface factor is introduced to optimize and correct the soil inversion results of remote sensing imagery of the target area, and to capture soil moisture variations in the target area, thereby improving the accuracy of soil moisture monitoring. Results demonstrate an early warning and forecast accuracy of at least 90%. The deep learning model extracts the temporal and spatial characteristics of the target area's moisture data and predicts surface moisture data for a specific time window in the future. This method then constructs a spatiotemporal coupled neural network to recover moisture variations in the target area.

[0160] The present invention is not limited to the above-described embodiments. Any structural changes made under the guidance of the present invention, which have the same or similar technical solutions as the present invention, should be understood to fall within the scope of protection of the present invention. The technologies, shapes, and structural parts not described in detail in the present invention are all well-known technologies.

Claims

1. A high-precision soil moisture prediction method based on a spatiotemporal convolutional neural network coupling model, characterized in that: The following steps are involved: S1: Deploy soil moisture detection equipment equipped with GPS function to the target area to obtain soil moisture measurement data at different depths; S2: Obtain remote sensing satellite images of the target area, import surface factors into the deep learning model for training, and use the trained learning model to correct the remote sensing images and classify different types of terrain; S3: Construct an improved MPDI and NDVI formula and use the surface factor to correct the soil moisture inversion value of the area; S4: Use the measured data from ground sensors to assist in the humidity inversion of remote sensing data to obtain the soil moisture change in the target monitoring area; S5: Build an LSTM model to predict humidity changes in the target monitoring area at future time points; The learning model in step S2 is used to optimize and extract features of remote sensing images. The specific steps are as follows: S2.1: Define the three-dimensional coordinate matrix C = [xyz] of the humidity sensor in the x, y, and z directions, where C is the three-dimensional coordinate quantity and xyz is the coordinate value of the sensor in the north-south, east-west, and vertical directions, respectively. S2.2: Define the surface factor matrix E=[SAV] around the humidity sensor deployment point, where E is the surface factor and SAV are the slope, aspect, and vegetation coverage around the deployment point, respectively. S2.3: In the input layer, the coordinate matrix of the known points and the terrain data are input into the convolutional neural network as an independent feature channel, and the remote sensing image optimization matrix is ​​constructed. ; S2.4: Use CNN to extract the spatial features of the target remote sensing image. , after the convolution operation of the CNN layer, the feature map is obtained ; S2.5: Combine the surface factor matrix E and the spatial feature matrix Perform fusion and generate fusion modules ; S2.6: Build an LSTM model, Input the LSTM model to extract the temporal features of the target remote sensing image; In step S3, the specific steps of improving NDVI and MPDI are as follows: S3.1: Introduce the soil adjustment coefficient L and calculate the improved remote sensing image index SAVI; S3.2: Introduce slope S and slope aspect A to calculate the angle of incidence ; S3.3: According to the incident angle value , calculate the improved remote sensing image index TSNDVI; S3.4: Improve soil moisture conditions based on soil moisture retention and thermal properties ; S3.5: Improve soil moisture conditions based on light scattering and reflection on the ground surface ; S3.6: Improve soil moisture conditions by changing the reflective properties of water due to the structure of the vegetation canopy ; In step S4, the specific steps of using the measured data of the ground sensor to assist the humidity inversion of the remote sensing data are as follows: S4.1: Replace the humidity value of the pixel corresponding to the measured point in the remote sensing image with the actual humidity value of the measured point; S4.2: Construct a regression model based on the measured humidity data and surface factors. The model output is the predicted value M. S4.3: Use the humidity of the nearest measured point to perform interpolation correction and obtain the corresponding interpolation matrix S; S4.4: The prediction results of the regression model are weighted and combined with the interpolation results to obtain the final corrected humidity value matrix L.

2. The method for high-precision soil moisture prediction based on a spatiotemporal convolutional neural network coupling model according to claim 1 is characterized in that: The LSTM model includes: Forget gate module: used to determine which information in the memory unit needs to be forgotten; Input gate module: used to determine what new information needs to be stored in the memory unit; Candidate memory cell state module; Update memory unit status module; Output gate module, used to determine the hidden state of the output; Hidden state output module at the current moment.

3. The high-precision soil moisture prediction method based on the spatiotemporal convolutional neural network coupling model according to claim 2 is characterized in that: The LSTM core expression is: Determine which information in the memory unit needs to be forgotten. The forget gate expression is: in, To forget information, is the activation function, is the weight matrix of the forget gate, represents the hidden state at the previous moment, Represents the input at the current moment, is the bias term of the forget gate; Determine what new information needs to be stored in the memory cell. The input gate expression is: in, is the weight matrix of the input gate, is the bias term of the input gate; Candidate memory cell states, The expression is: in, is the weight matrix of the candidate states, is the bias term, is the activation function; Update the memory cell state, The expression is: in, Indicates the state of the memory unit at the previous moment; Determine the hidden state of the output , the output gate expression is: in, represents the activation function of the input gate, is the weight matrix of the output gate, is the bias term of the output gate; in, Represents the hidden state output at the current moment.

4. The method for high-precision soil moisture prediction based on a spatiotemporal convolutional neural network coupling model according to claim 1, characterized in that: The improved remote sensing image index SAVI is expressed as: Among them, L is the coefficient obtained by analyzing soil type and texture through field soil sampling, NIR is the reflectance of the near-infrared band, and Red is the reflectance of the red light band; Incident angle value , the expression is: in, is the solar zenith angle, A is the slope direction, and S is the slope; The improved remote sensing image index TSNDVI is expressed as: Improve soil moisture conditions , the expression is: in, represents the influence weight of soil texture, NIR is the reflectance of the near infrared band, SWIR is the reflectance of the shortwave infrared band, and Tq is the soil texture coefficient; Improve soil moisture conditions , the expression is: in, Indicates the influence weight of surface roughness, Rou indicates the degree of surface roughness; Improve soil moisture conditions , the expression is: in, represents the influence weight of the structure of the vegetation canopy, represents the canopy structure coefficient.

5. The method for high-precision soil moisture prediction based on a spatiotemporal convolutional neural network coupling model according to claim 1 is characterized in that: The predicted value of the model output is M, which is expressed as: in, is the humidity at the known measured point, is the surface factor matrix, is the error term; The interpolation matrix S is expressed as: Among them, S is the humidity value of the non-measured point, n is the number of measured points around the target point, is the humidity value corresponding to the measured point, is the calculation weight; The final corrected humidity value matrix L is expressed as: in, is the combined estimated humidity value, is the weighted coefficient used to balance the regression model and the interpolation results, S is the humidity interpolation value of the current point, and M is the humidity prediction value of the current point.

6. The method for high-precision soil moisture prediction based on a spatiotemporal convolutional neural network coupling model according to claim 1, characterized in that: In step S5, the specific steps of using LSTM to predict the humidity change in the target monitoring area at a future time point are as follows: S5.1: Input all attributes of the current point and construct the future input data sequence K; S5.2: Input the sequence into the LSTM model trained in the second stage. The humidity at each time step is predicted through the time recursion mechanism of the LSTM model. S5.3: Combine surface factors to make the prediction more consistent with the actual humidity value G in the area; S5.4: For each prediction step, the LSTM model will update the hidden state As the input of the next time step, and combined with surface factors and meteorological data, the future humidity value Hv is recursively predicted.

7. The method for high-precision soil moisture prediction based on a spatiotemporal convolutional neural network coupling model according to claim 6, characterized in that: The future input data sequence K is expressed as: in, is the original remote sensing image, C is the three-dimensional coordinate matrix of the known points, and E is the terrain information matrix. For meteorological data, is the current humidity data; The actual humidity value G is expressed as: in, is the weight calculated based on the surface factor, N is the humidity feature obtained by the LSTM model, and E is the surface factor matrix; Predict the future humidity value Hv, the prediction formula is: in, represents the predicted humidity value at time t+1, Represents the prediction layer.

Images