Soil moisture reconstruction method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of geographic information, in particular to a soil moisture reconstruction method and device, computer equipment and a first-level storage medium. Inputting the first resolution waveband data and the second resolution waveband data into a preset waveband resolution reconstruction model for resolution reconstruction to obtain reconstructed resolution waveband data, and resampling the soil attribute data and the topographic data until the resolution of the reconstructed resolution waveband data is reached, obtaining resampled soil attribute data and resampled topographic data; inputting the reconstruction resolution waveband data, the resampled soil attribute data, the resampled topographic data, the geographic position data and the to-be-reconstructed soil moisture data into a preset soil moisture reconstruction model for data reconstruction to obtain reconstructed soil moisture data, and the requirements of multiple fields on high-frequency acquisition of high-resolution soil moisture data are met.

Description

Technical Field

[0001] The present invention relates to the field of geographic information technology, and particularly to a method and device for reconstructing soil moisture, a computer device, and a storage medium. Background Art

[0002] Soil moisture is a physical quantity representing the dryness and wetness of soil and is the life source of terrestrial plants. For terrestrial plants including food crops, precipitation and irrigation need to be converted into soil moisture to be absorbed, and fertilizers applied also need to be absorbed in the form of soil solution. Therefore, soil moisture is often used as a classic index to characterize the degree of drought and plays an indispensable role in the agricultural drought and flood monitoring and early warning system.

[0003] Satellite microwave remote sensing for earth observation is an important way to obtain large-scale and long-time-series soil moisture data products. However, the daily-scale soil moisture data products obtained by inverting the signals of a single satellite generally have null value areas and relatively low spatial resolution (about 25 km), making it difficult to achieve seamless coverage of the high-resolution surface at the daily scale. To improve the data spatial coverage rate, soil moisture inversion data based on the fusion of multi-source satellite microwave data and medium-resolution imaging spectrometer data has emerged. By matching and fusing multiple reliable data sources, a daily-scale soil moisture fusion product with high spatial coverage rate is developed, providing important data references for exploring the spatio-temporal pattern evolution characteristics of the surface water cycle. However, the spatial resolution of most soil moisture inversion data fused by satellite microwave signals is still at the kilometer or even hundreds of meters grid scale, making it difficult to meet the drought and flood monitoring requirements at the regional scale. Summary of the Invention

[0004] Based on this, the object of the present invention is to provide a method and device for reconstructing soil moisture, a computer device, and a storage medium, which can realize super-resolution downscaling of band data based on a band resolution reconstruction model, integrate spatio-temporal information of multiple variables under the guidance of geoscience knowledge, and efficiently capture the non-linear coupling relationship of the spatio-temporal dynamic texture of soil moisture by combining the constructed soil moisture reconstruction model, so as to improve the accuracy of high-resolution reconstruction of soil moisture data and meet the high-frequency acquisition requirements of high-resolution soil moisture data in multiple fields.

[0005] In a first aspect, an embodiment of the present application provides a method for reconstructing soil moisture, including the following steps:

[0006] Obtain multimodal data collected by a multi-band satellite sensor, where the multimodal data includes first-resolution band data, second-resolution band data, soil moisture data to be reconstructed, soil property data, terrain data, and geographical location data;

[0007] Input the first-resolution band data and the second-resolution band data into a preset band-resolution reconstruction model for resolution reconstruction to obtain reconstructed-resolution band data, where the band-resolution reconstruction model is a noise prediction model constructed based on the U-net network structure using the first-resolution band data and the second-resolution band data as training data;

[0008] Resample the soil property data and the terrain data to the resolution of the reconstructed-resolution band data to obtain resampled soil property data and resampled terrain data;

[0009] Input the reconstructed-resolution band data, the resampled soil property data, the resampled terrain data, the geographical location data, and the soil moisture data to be reconstructed into a preset soil moisture reconstruction model for data reconstruction to obtain reconstructed soil moisture data.

[0010] In a second aspect, an embodiment of the present application provides a soil moisture reconstruction device, including:

[0011] A data acquisition module, configured to obtain multi-modal data collected by a multi-band satellite sensor, where the multi-modal data includes first-resolution band data, second-resolution band data, soil moisture data to be reconstructed, soil property data, terrain data, and geographical location data;

[0012] A resolution reconstruction module, configured to input the first-resolution band data and the second-resolution band data into a preset band-resolution reconstruction model for resolution reconstruction to obtain reconstructed-resolution band data, where the band-resolution reconstruction model is a noise prediction model constructed based on the U-net network structure using the first-resolution band data and the second-resolution band data as training data;

[0013] A resampling module, configured to resample the soil property data and the terrain data to the resolution of the reconstructed-resolution band data to obtain resampled soil property data and resampled terrain data;

[0014] A soil moisture reconstruction module, configured to input the reconstructed-resolution band data, the resampled soil property data, the resampled terrain data, the geographical location data, and the soil moisture data to be reconstructed into a preset soil moisture reconstruction model for data reconstruction to obtain reconstructed soil moisture data.

[0015] In a third aspect, an embodiment of the present application provides a computer device, including: a processor, a memory, and a computer program stored on the memory and executable on the processor; when the computer program is executed by the processor, the steps of the soil moisture reconstruction method described in the first aspect are implemented.

[0016] Fourthly, an embodiment of the present application provides a storage medium storing a computer program, which when executed by a processor implements the steps of the soil moisture reconstruction method as described in the first aspect.

[0017] In the embodiments of the present application, a soil moisture reconstruction method, device, computer device, and storage medium are provided. Based on a band resolution reconstruction model, super-resolution downscaling of band data is achieved, and spatio-temporal information of multiple variables is integrated under the guidance of geoscience knowledge. Combining with the constructed soil moisture reconstruction model, an efficient capture of the non-linear coupling relationship of the spatio-temporal dynamics texture of soil moisture is carried out, improving the accuracy of high-resolution reconstruction of soil moisture data to meet the high-frequency acquisition requirements of high-resolution soil moisture data in multiple fields.

[0018] For better understanding and implementation, the present invention will be described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A flowchart of the soil moisture reconstruction method provided by an embodiment of the present application;

[0020] Figure 2 A flowchart of the soil moisture reconstruction method provided by another embodiment of the present application;

[0021] Figure 3 A flowchart of S2 in the soil moisture reconstruction method provided by an embodiment of the present application;

[0022] Figure 4 A flowchart of S21 in the soil moisture reconstruction method provided by an embodiment of the present application;

[0023] Figure 5 A flowchart of S22 in the soil moisture reconstruction method provided by an embodiment of the present application;

[0024] Figure 6 A flowchart of S23 in the soil moisture reconstruction method provided by an embodiment of the present application;

[0025] Figure 7 A flowchart of S4 in the soil moisture reconstruction method provided by an embodiment of the present application;

[0026] Figure 8 A structural diagram of the soil moisture reconstruction device provided by an embodiment of the present application;

[0027] Figure 9 A structural diagram of the computer device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] Exemplary embodiments will be described in detail herein, and examples thereof are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0029] The terms used in this application are for the purpose of describing particular embodiments only and are not intended to limit the present application. The singular forms "a", "the", and "said" used in this application and the appended claims are also intended to include the plural forms unless the context clearly dictates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0030] It should be understood that although the terms first, second, third, etc. may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of the present application, the first information may also be referred to as second information, and similarly, the second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when" or "while" or "in response to determining".

[0031] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of a soil moisture reconstruction method provided for an embodiment of the present application. The method includes the following steps:

[0032] S1: Obtain multimodal data collected by a multi-band satellite sensor.

[0033] The execution subject of the soil moisture reconstruction method is a reconstruction device for the soil moisture reconstruction method (hereinafter referred to as the reconstruction device). In an optional embodiment, the reconstruction device may be a computer device, which may be a server, or a server cluster formed by combining multiple computer devices.

[0034] In this embodiment, the reconstruction device obtains multimodal data collected by a multi-band satellite sensor. Among them, the multimodal data includes first-resolution band data, second-resolution band data, soil moisture data to be reconstructed, soil property data, terrain data, and geographical location data.

[0035] Specifically, the first-resolution band data uses visible light-near infrared medium-resolution data (data of 7 bands from 1 to 7 in the MCD43A4 band data), with a spatial resolution of 500m×500m and a temporal resolution of daily scale.

[0036] The second-resolution band data uses visible light-near infrared high-resolution data (HLS, data of corresponding bands from 1 to 7 in the Harmonized Landsat Sentinel-2 band data and the MCD43A4 band data), with a spatial resolution of 30m and a temporal resolution of 2-3 days scale.

[0037] The soil moisture data to be reconstructed uses SMAP or Sentinel remote sensing soil moisture data, with a spatial resolution of 3km×3km and a temporal resolution of 12 days scale.

[0038] The soil property data uses the Harmonized World Soil Database (HWSD V2.0), with a spatial resolution of 1km×1km.

[0039] The terrain data uses SRTM terrain data, with a spatial resolution of 30m×30m. The spatial resolution of the geographical location data is 30m×30m.

[0040] S2: Input the first-resolution band data and the second-resolution band data into a preset band resolution reconstruction model for resolution reconstruction to obtain reconstructed resolution band data.

[0041] In this embodiment, the reconstruction device inputs the first-resolution band data and the second-resolution band data into a preset band resolution reconstruction model for resolution reconstruction to obtain reconstructed resolution band data. Among them, the band resolution reconstruction model is a noise prediction model constructed based on the U-net network structure using the first-resolution band data and the second-resolution band data as training data. Specifically, the band resolution reconstruction model is an optimal noise prediction model constructed by using gradient descent and Bayesian parameter optimization methods to determine structural hyperparameters such as the number of the first encoder / decoder, the number and size of two-dimensional convolutional kernels, as well as model training hyperparameters such as the initial learning rate and optimizer.

[0042] Please refer to Figure 2 , Figure 2 which is a schematic flowchart of the soil moisture reconstruction method provided by another embodiment of this application. It further includes step S5, and the step S5 is before step S2, specifically as follows:

[0043] S5: Use the bilinear interpolation method to resample the first-resolution band data, and perform spatio-temporal matching and normalization based on the second-resolution band data and the resampled first-resolution band data to obtain the normalized first-resolution band data and second-resolution band data.

[0044] In this embodiment, the reconstruction device uses the bilinear interpolation method to resample the first-resolution band data, and performs spatio-temporal matching and normalization based on the second-resolution band data and the resampled first-resolution band data to obtain the normalized first-resolution band data and second-resolution band data.

[0045] The band resolution reconstruction model includes a forward diffusion module, a first encoding module, and a decoding module; the first encoding module includes a first convolutional layer and a number of first encoders connected in sequence; the decoder includes a number of decoders connected in sequence and a second convolutional layer. Please refer to Figure 3 , Figure 3 which is a schematic flowchart of S2 in the soil moisture reconstruction method provided by an embodiment of the present application, including steps S21 to S24, specifically as follows:

[0046] S21: Input the normalized first-resolution band data and second-resolution band data into the forward diffusion module for forward diffusion processing to obtain forward diffusion data.

[0047] The forward diffusion module is used to execute the forward process, that is, the diffusion process, which refers to the process of gradually adding Gaussian noise to the original data until the data becomes random noise.

[0048] In this embodiment, the reconstruction device inputs the normalized first-resolution band data and second-resolution band data into the forward diffusion module for forward diffusion processing to obtain forward diffusion data, where the forward diffusion data includes band noise-added data corresponding to a number of diffusion steps to capture the complex relationship between the normalized first-resolution band data and second-resolution band data, so as to improve the accuracy of band data resolution reconstruction.

[0049] Please refer to Figure 4 , Figure 4 which is a schematic flowchart of S21 in the soil moisture reconstruction method provided by an embodiment of the present application, including steps S211 to S212, specifically as follows:

[0050] S211: Construct an image pair according to the normalized first-resolution band data and second-resolution band data, where the image pair includes a first-resolution band image and a second-resolution band image.

[0051] In this embodiment, the reconstruction device constructs an image pair through sliding window cropping based on the normalized first-resolution band data and second-resolution band data, where the image pair includes a first-resolution band image and a second-resolution band image.

[0052] S212: Obtain band-added noise data corresponding to a number of diffusion steps according to the image pair, a preset number of diffusion steps, and a forward diffusion algorithm.

[0053] In this embodiment, the reconstruction device obtains band-added noise data corresponding to a number of diffusion steps according to the image pair, a preset number of diffusion steps, and a forward diffusion algorithm, achieving the effect of multi-step diffusion, ensuring the stability of the band-added noise data during the diffusion process, saving system resources, and improving the execution efficiency of the diffusion process. The band-noisy image conversion algorithm is as follows:

[0054]

[0055] In the formula, x t is the band-added noise data corresponding to the t-th diffusion step, is the Gaussian noise-related parameter corresponding to the t-th diffusion step, β i is the variance corresponding to the i-th diffusion step, y HR is the second-resolution band image, x LR is the first-resolution band image, and ∈ is a random noise parameter conforming to a Gaussian distribution.

[0056] S22: Input the forward diffusion data into the first convolutional layer for convolutional processing to obtain a first feature array. Use the first feature data as the first input data of the first encoder for encoding processing to obtain sub-band encoded data output by the first encoder. Use the first feature array and the sub-band encoded data output by the first encoder as the first input data of the next first encoder, and repeat the encoding process to obtain sub-band encoded data output by a number of first encoders.

[0057] In this embodiment, the reconstruction device inputs the forward diffusion data into the first convolutional layer for convolutional processing to obtain a first feature array. Use the first feature data as the first input data of the first encoder for encoding processing to obtain sub-band encoded data output by the first encoder. Use the first feature array and the sub-band encoded data output by the first encoder as the first input data of the next first encoder, and repeat the encoding process to obtain sub-band encoded data output by a number of first encoders.

[0058] The first encoder includes a number of first residual blocks connected in sequence and a downsampling layer; the first feature array includes convolution feature data corresponding to a number of diffusion steps; please refer to Figure 5 , Figure 5 which is a schematic flowchart of S22 in the soil moisture reconstruction method provided by an embodiment of the present application, including steps S221 to S222, specifically as follows:

[0059] S221: Input the first input data into the first first residual block, perform residual processing according to the first feature array, sub-band encoding data in the first input data, and a preset residual block algorithm, obtain the intermediate feature array output by the first first residual block, and use the intermediate feature array output by the first first residual block and the first feature array in the first input data as the third input data of the next first residual block, and repeat the residual processing to obtain the intermediate feature data output by the last residual block.

[0060] The residual block algorithm is:

[0061]

[0062] In the formula, L i+1 is the intermediate feature array output by the (i + 1)-th residual block, L i is the intermediate feature array output by the i-th residual block of the first encoder, X is the first feature array, t e is the time encoding array, and the time encoding array includes time encodings obtained by performing Transformer sine position encoding on a number of diffusion steps, is the first non-linear mapping function, representing the non-linear mapping through the Conv2D layer and the Mish activation function, is the second non-linear mapping function, representing the non-linear mapping processed through the FC layer and the ReLU activation function.

[0063] In this embodiment, the reconstruction device inputs the first input data into the first first residual block, performs residual processing according to the first feature array, sub-band encoding data in the first input data, and a preset residual block algorithm, obtains the intermediate feature array output by the first first residual block, and uses the intermediate feature array output by the first first residual block and the first feature array in the first input data as the third input data of the next first residual block, and repeats the residual processing to obtain the intermediate feature data output by the last residual block.

[0064] S222: Input the intermediate feature data output by the last residual block into the downsampling layer for downsampling to obtain the sub-band encoding data output by the first encoder.

[0065] In this embodiment, the reconstruction device inputs the intermediate feature data output by the last residual block into the downsampling layer for downsampling to obtain the subband encoded data output by the first encoder.

[0066] S23: Use the subband encoded data output by the last first encoder as the second input data of the first decoder for decoding to obtain the subband decoded data output by the first decoder. Use the subband decoded data output by the first decoder and the subband encoded data output by the previous decoder as the second input data of the next decoder, and repeat the decoding process to obtain the subband decoded data output by the last first encoder.

[0067] In this embodiment, the reconstruction device uses the subband encoded data output by the last first encoder as the second input data of the first decoder for decoding to obtain the subband decoded data output by the first decoder. Use the subband decoded data output by the first decoder and the subband encoded data output by the previous decoder as the second input data of the next decoder, and repeat the decoding process to obtain the subband decoded data output by the last first encoder.

[0068] The decoder includes a plurality of second residual blocks connected in sequence and an upsampling layer; please refer to Figure 6 , Figure 6 which is a schematic flowchart of S23 in the soil moisture reconstruction method provided by an embodiment of the present application, including step S231, specifically as follows:

[0069] S231: Obtain the subband decoded data output by the first encoder according to the subband decoded data, subband encoded data in the second input data, and a preset decoding algorithm.

[0070] The decoding algorithm is:

[0071] D n = Upsampling(Resblock(Resblock(D n+1 , E n )))

[0072] In the formula, D n is the subband decoded data output by the nth decoder, D n+1 is the subband decoded data output by the (n + 1)th decoder, E n is the subband encoded data output by the nth first encoder, Upsampling(·) is the processing function of the upsampling layer, and Resblock(·) is the processing function of the second residual block.

[0073] In this embodiment, the reconstruction device inputs the sub-band decoded data and sub-band encoded data in the second input data, as well as a preset decoding algorithm, into the first second residual block of the current decoder for residual processing, inputs the result obtained after processing into the next second residual block for residual processing, and inputs the result obtained after processing into the upsampling layer for upsampling to obtain the sub-band decoded data output by the current first encoder.

[0074] S24: Input the sub-band decoded data output by the last first encoder into the second convolutional layer for convolutional processing, and use the result output by the second convolutional layer as the reconstructed resolution band data.

[0075] In this embodiment, the reconstruction device inputs the sub-band decoded data output by the last first encoder into the second convolutional layer for convolutional processing, and uses the result output by the second convolutional layer as the reconstructed resolution band data.

[0076] S3: Resample the soil attribute data and terrain data to the resolution of the reconstructed resolution band data to obtain resampled soil attribute data and resampled terrain data.

[0077] In this embodiment, the reconstruction device resamples the soil attribute data and terrain data to the resolution of the reconstructed resolution band data to obtain resampled soil attribute data and resampled terrain data. Specifically, the reconstruction device combines the reconstructed resolution band data of daily scale and 30m super-resolution reconstruction, and resamples the soil attribute data and terrain data to 30m based on the bilinear interpolation method to be consistent with the spatial resolution of the reconstructed resolution band data, obtaining resampled soil attribute data and resampled terrain data.

[0078] S4: Input the reconstructed resolution band data, resampled soil attribute data, resampled terrain data, geographical location data, and soil moisture data to be reconstructed into a preset soil moisture reconstruction model for data reconstruction to obtain reconstructed soil moisture data.

[0079] The soil moisture reconstruction model is a high-precision fusion model constructed based on a preset deep learning conversion model network structure, adjusting the sample structure using model training accuracy and efficiency, and searching for the optimal solutions of the number of deep network layers, non-linear activation functions, gradient optimization methods, etc. based on the Bayesian optimization method.

[0080] In this embodiment, the reconstruction device inputs the reconstructed resolution band data, resampled soil property data, resampled terrain data, geographical location data, and the soil moisture data to be reconstructed into a preset soil moisture reconstruction model for data reconstruction, and obtains the reconstructed soil moisture data.

[0081] The soil moisture reconstruction model includes a time feature extraction module, a spatial feature extraction module, and a data reconstruction module; the time feature extraction module includes an embedding layer, a second encoding module, a fully connected layer, and a regularization layer; the second encoding module includes a plurality of second encoders connected in sequence; the spatial feature extraction module includes a convolution module, a two-dimensional global average pooling layer, a fully connected layer, and a regularization layer; the convolution module includes a plurality of sub-convolution units, and each sub-convolution unit includes a two-dimensional convolutional layer and a two-dimensional global max pooling layer; the data reconstruction module includes a fully connected layer, an activation layer, and a two-dimensional convolutional layer; please refer to Figure 7 , Figure 7 which is a schematic flowchart of S4 in the soil moisture reconstruction method provided by an embodiment of the present application, including steps S41 to S43, as follows:

[0082] S41: Take the reconstructed resolution band data as a time series dynamic variable, input the time series dynamic variable, the soil moisture data to be reconstructed, and input them into the time feature extraction module. Perform spatial mapping and position encoding according to the embedding layer to obtain mapped encoded data. Input the mapped encoded data into the second encoding module for encoding processing to obtain the encoded data output by the last second encoder. Process the encoded data output by the last second encoder through the fully connected layer and the regularization layer of the time feature extraction module in sequence to obtain time feature data.

[0083] In this embodiment, the reconstruction device takes the reconstructed resolution band data as a time series dynamic variable, inputs the time series dynamic variable, the soil moisture data to be reconstructed, and inputs them into the time feature extraction module. Perform spatial mapping and position encoding according to the embedding layer to obtain mapped encoded data, thereby obtaining high-dimensional feature data.

[0084] The reconstruction device inputs the mapped encoded data into the second encoding module for encoding processing to obtain the encoded data output by the last second encoder. Specifically, the second encoder includes a multi-head temporal attention sublayer (Multi-Head Attention) and a feed-forward connection sublayer (Feed Forward). The reconstruction device uses the mapped encoded data as the input data of the first second encoder of the second encoding module, and processes it through the multi-head temporal attention sublayer and the feed-forward connection sublayer in sequence to obtain the output data of the first second encoder. The output data of the first second encoder is used as the input data of the next second encoder, and the encoding process is repeated to obtain the encoded data output by the last second encoder.

[0085] The reconstruction device processes the encoded data output by the last second encoder through the fully connected layer and the regularization layer of the temporal feature extraction module in sequence to obtain temporal feature data, so as to capture the temporal texture features between the soil moisture data to be reconstructed and the temporal dynamic variables, and improve the accuracy and reliability of soil moisture reconstruction.

[0086] S42: Use the resampled soil property data, resampled terrain data, and geographical location data as temporal static variables, input the temporal static variables and the soil moisture data to be reconstructed into the spatial feature extraction module respectively, perform convolution processing according to several sub-convolution units of the convolution module, and splice the convolution data output by the several sub-convolution units to obtain the first spliced data; process the first spliced data through the two-dimensional global average pooling layer, the fully connected layer, and the regularization layer in sequence to obtain spatial feature data.

[0087] In this embodiment, the reconstruction device uses the resampled soil property data, resampled terrain data, and geographical location data as temporal static variables, inputs the temporal static variables and the soil moisture data to be reconstructed into the spatial feature extraction module respectively, performs convolution processing according to several sub-convolution units of the convolution module, and splices the convolution data output by the several sub-convolution units to obtain the first spliced data.

[0088] The reconstruction device processes the first spliced data through the two-dimensional global average pooling layer, the fully connected layer, and the regularization layer in sequence to obtain spatial feature data, so as to capture the spatial texture features between the soil moisture data to be reconstructed and the temporal static variables, and improve the accuracy and reliability of soil moisture reconstruction.

[0089] S43: Input the time feature data and the spatial feature data into the data reconstruction module respectively. Perform fully connected processing on the time feature data and the spatial feature data according to the fully connected layer. Concatenate the fully connected feature data corresponding to the time feature data and the fully connected feature data corresponding to the spatial feature data output by the fully connected layer to obtain second concatenated data. Process the second concatenated data through the activation layer and the two-dimensional convolutional layer in sequence to obtain the reconstructed soil moisture data.

[0090] In this embodiment, the reconstruction device inputs the time feature data and the spatial feature data into the data reconstruction module respectively. Perform fully connected processing on the time feature data and the spatial feature data according to the fully connected layer. Concatenate the fully connected feature data corresponding to the time feature data and the fully connected feature data corresponding to the spatial feature data output by the fully connected layer to obtain second concatenated data. Process the second concatenated data through the activation layer and the two-dimensional convolutional layer in sequence to obtain the reconstructed soil moisture data.

[0091] Based on the band resolution reconstruction model, achieve super-resolution downscaling of band data, integrate multi-variable spatio-temporal information under the guidance of geoscience knowledge, and combine with the constructed soil moisture reconstruction model to efficiently capture the non-linear coupling relationship of the spatio-temporal dynamics texture of soil moisture, improve the accuracy of high-resolution reconstruction of soil moisture data, so as to meet the high-frequency acquisition requirements of high-resolution soil moisture data in multiple fields.

[0092] Please refer to Figure 8 , Figure 8 FIG. is a schematic structural diagram of a soil moisture reconstruction device provided by an embodiment of the present application. The device can implement all or part of the soil moisture reconstruction device through software, hardware, or a combination of both. The device 8 includes:

[0093] A data acquisition module 81, configured to obtain multi-modal data collected by a multi-band satellite sensor, where the multi-modal data includes first-resolution band data, second-resolution band data, soil moisture data to be reconstructed, soil property data, terrain data, and geographical location data;

[0094] A resolution reconstruction module 82, configured to input the first-resolution band data and the second-resolution band data into a preset band resolution reconstruction model for resolution reconstruction to obtain reconstructed resolution band data, where the band resolution reconstruction model is a noise prediction model constructed based on a U-net network structure using the first-resolution band data and the second-resolution band data as training data;

[0095] A resampling module 83, configured to resample the soil attribute data and the terrain data to the resolution of the reconstructed resolution band data, so as to obtain resampled soil attribute data and resampled terrain data;

[0096] A soil moisture reconstruction module 84, configured to input the reconstructed resolution band data, the resampled soil attribute data, the resampled terrain data, the geographical location data, and the soil moisture data to be reconstructed into a preset soil moisture reconstruction model for data reconstruction, so as to obtain reconstructed soil moisture data.

[0097] In an embodiment of the present application, through a data acquisition module, multi-modal data collected by a multi-band satellite sensor is obtained, where the multi-modal data includes first-resolution band data, second-resolution band data, soil moisture data to be reconstructed, soil attribute data, terrain data, and geographical location data; through a resolution reconstruction module, the first-resolution band data and the second-resolution band data are input into a preset band resolution reconstruction model for resolution reconstruction, so as to obtain reconstructed resolution band data, where the band resolution reconstruction model is a noise prediction model constructed based on a U-net network structure using the first-resolution band data and the second-resolution band data as training data; through a resampling module, the soil attribute data and the terrain data are resampled to the resolution of the reconstructed resolution band data, so as to obtain resampled soil attribute data and resampled terrain data; through a soil moisture reconstruction module, the reconstructed resolution band data, the resampled soil attribute data, the resampled terrain data, the geographical location data, and the soil moisture data to be reconstructed are input into a preset soil moisture reconstruction model for data reconstruction, so as to obtain reconstructed soil moisture data. It is possible to comprehensively consider the influence of terrain data and precipitation data on soil moisture reconstruction, and based on the existing terrain data, precipitation data, and soil moisture reconstruction, establish a regression mapping model between soil moisture and surface parameters, and can achieve high-precision reconstruction of soil moisture reconstruction.

[0098] Please refer to Figure 9 , Figure 9 , which is a schematic structural diagram of a computer device provided in an embodiment of the present application. The computer device 9 includes: a processor 91, a memory 92, and a computer program 93 stored in the memory 92 and executable on the processor 91; the computer device may store multiple instructions, and the instructions are suitable for being loaded and executed by the processor 91 to perform the method steps of the above Figures 1 to 7 shown embodiment. The specific execution process may refer to the specific description of the Figures 1 to 7 shown embodiment, and details are not described herein.

[0099] Among them, the processor 91 may include one or more processing cores. The processor 91 is connected to various parts within the server through various interfaces and lines. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 92, and by invoking the data in the memory 92, it performs various functions of the soil moisture reconstruction device 4 and processes data. Optionally, the processor 91 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 91 may integrate a combination of one or several of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface, application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the touch display screen; the modem is used to process wireless communication. It can be understood that the above-mentioned modem may not be integrated into the processor 91 and may be implemented separately by a single chip.

[0100] Among them, the memory 92 may include a random access memory (RAM) and may also include a read-only memory. Optionally, the memory 92 includes a non-transitory computer-readable storage medium. The memory 92 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 92 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing the operating system, instructions for at least one function (such as touch instructions, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store the data involved in the above-mentioned method embodiments. Optionally, the memory 92 may also be at least one storage device located far from the aforementioned processor 91.

[0101] The embodiment of the present application also provides a storage medium, which can store multiple instructions, and the instructions are suitable for being loaded and executed by a processor to perform the method steps of the above Figures 1 to 7 shown embodiments. The specific execution process can be referred to Figures 1 to 7 the specific description of the shown embodiments and will not be elaborated here.

[0102] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional units and modules according to needs, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated here.

[0103] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0104] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0105] In the embodiments provided by the present invention, it should be understood that the disclosed device / terminal device and method can be implemented in other ways. For example, the device / terminal device embodiments described above are only illustrative. For example, the division of the module or unit is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the device or unit can be in electrical, mechanical or other forms.

[0106] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0107] In addition, in each embodiment of the present invention, each functional unit can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0108] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above method embodiments of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc.

[0109] The present invention is not limited to the above embodiments. If various modifications or deformations of the present invention do not depart from the spirit and scope of the present invention, and if these modifications and deformations are within the scope of the claims of the present invention and equivalent technical scope, then the present invention also intends to include these modifications and deformations.

Claims

1. A soil moisture reconstruction method, characterized in that: The following steps are involved: Obtaining multimodal data collected by a multi-band satellite sensor, wherein the multimodal data includes first resolution band data, second resolution band data, soil moisture data to be reconstructed, soil attribute data, terrain data, and geographic location data; Inputting the first resolution band data and the second resolution band data into a preset band resolution reconstruction model for resolution reconstruction to obtain reconstructed resolution band data, wherein the band resolution reconstruction model is a noise prediction model constructed based on a U-net network structure using the first resolution band data and the second resolution band data as training data; Resampling the soil property data and the terrain data to the resolution of the reconstructed resolution band data to obtain resampled soil property data and resampled terrain data; The reconstructed resolution band data, resampled soil property data, resampled terrain data, geographical location data and soil moisture data to be reconstructed are input into a preset soil moisture reconstruction model for data reconstruction to obtain reconstructed soil moisture data.

2. The soil moisture reconstruction method according to claim 1, characterized in that: The first resolution band data adopts visible light-near infrared medium resolution data; the second resolution band data adopts visible light-near infrared high resolution data; The step of inputting the first resolution band data and the second resolution band data into a preset band resolution reconstruction model for resolution reconstruction and obtaining the reconstructed resolution band data comprises the following steps: The first resolution band data is resampled by using a bilinear interpolation method, and time-space matching and normalization are performed according to the second resolution band data and the resampled first resolution band data to obtain normalized first resolution band data and second resolution band data.

3. The soil moisture reconstruction method according to claim 2, characterized in that: The band resolution reconstruction model includes a forward diffusion module, a first encoding module and a decoding module; the first encoding module includes a first convolutional layer and a plurality of first encoders connected in sequence; the decoder includes a plurality of decoders connected in sequence and a second convolutional layer; The step of inputting the first resolution band data and the second resolution band data into a preset band resolution reconstruction model for resolution reconstruction to obtain reconstructed resolution band data comprises the following steps: Inputting the normalized first-resolution band data and the second-resolution band data into the forward diffusion module for forward diffusion processing to obtain forward diffusion data, wherein the forward diffusion data includes band noise-added data corresponding to a number of diffusion steps; Inputting the forward diffusion data into the first convolution layer for convolution processing to obtain a first feature array, using the first feature data as first input data of a first encoder for encoding processing to obtain sub-band encoded data output by the first encoder, using the first feature array and the sub-band encoded data output by the first encoder as first input data of a next encoder, repeating the encoding processing to obtain sub-band encoded data output by a plurality of first encoders; Using the sub-band coded data output by the last first encoder as the second input data of the first decoder for decoding processing to obtain sub-band decoded data output by the first decoder, using the sub-band decoded data output by the first decoder and the sub-band coded data output by the previous decoder as the second input data of the next decoder, repeating the decoding processing to obtain the last sub-band decoded data output by the first encoder; The sub-band decoded data output by the last first encoder is input into the second convolution layer for convolution processing, and the result output by the second convolution layer is used as the reconstructed resolution band data.

4. The soil moisture reconstruction method according to claim 3, characterized in that: The step of inputting the normalized first resolution band data and the second resolution band data into the forward diffusion module for forward diffusion processing to obtain forward diffusion data comprises the following steps: Constructing an image pair according to the normalized first-resolution band data and the second-resolution band data, wherein the image pair includes a first-resolution band image and a second-resolution band image; According to the image pair, the preset diffusion steps and the forward diffusion algorithm, the band noise data corresponding to the diffusion steps are obtained, wherein the noisy image conversion algorithm is: In the formula, x t is the band noise data corresponding to the t-th diffusion step, is the Gaussian noise related parameter corresponding to the t-th diffusion step, β i is the variance corresponding to the i-th diffusion step, y HR is the second resolution band image, x LR is the first resolution band image, ∈ is the random noise parameter that conforms to the Gaussian distribution.

5. The soil moisture reconstruction method according to claim 3 or 4, characterized in that: The first encoder includes a plurality of first residual blocks and downsampling layers connected in sequence; the first feature array includes convolution feature data corresponding to a plurality of diffusion steps; The first feature array and the sub-band coded data output by the first first encoder are used as the first input data of the next first encoder, and the encoding process is repeated to obtain the sub-band coded data output by a plurality of first encoders, including the steps of: The first input data is input to the first first residual block, residual processing is performed according to the first feature array in the first input data, the sub-band coded data, and a preset residual block algorithm to obtain an intermediate feature array output by the first first residual block, the intermediate feature array output by the first first residual block and the first feature array in the first input data are used as the third input data of the next first residual block, and the residual processing is repeated to obtain the intermediate feature data output by the last residual block, wherein the residual block algorithm is: Where, L i+1 is the intermediate feature array output by the i+1th residual block, L i is the intermediate feature array of the residual block output by the i-th first encoder, X is the first feature array, t e is a time code array, wherein the time code array includes time codes after a number of diffusion steps are coded by Transformer sinusoidal positions. is the first nonlinear mapping function, which represents the nonlinear mapping after the Conv2D layer and the Mish activation function. is the second nonlinear mapping function, which represents the nonlinear mapping processed by the FC layer and the ReLU activation function; The intermediate feature data output by the last residual block is input into the downsampling layer for downsampling to obtain the sub-band encoded data output by the first encoder.

6. The soil moisture reconstruction method according to claim 5, characterized in that: The decoder comprises a plurality of second residual blocks and upsampling layers connected in sequence; The method uses the sub-band decoded data output by the first decoder and the sub-band coded data output by the previous decoder as the second input data of the next decoder, repeats the decoding process, and obtains the sub-band decoded data output by the last first encoder, including the steps of: According to the sub-band decoded data, the sub-band encoded data and a preset decoding algorithm in the second input data, the sub-band decoded data output by the first encoder is obtained, wherein the decoding algorithm is: D n =Upsampling(Resblock(Resblock(D n+1 ,E n ))) Where D n The sub-band decoded data output by the nth decoder, D n+1 The sub-band decoded data output by the n+1th decoder, E n is the sub-band coded data output by the nth first encoder, Upsampling(·) is the processing function of the upsampling layer, and Resblock(·) is the processing function of the second residual block.

7. The soil moisture reconstruction method according to claim 6, characterized in that: The soil moisture reconstruction model includes a time feature extraction module, a spatial feature extraction module and a data reconstruction module; the time feature extraction module includes an embedding layer, a second encoding module, a fully connected layer and a regularization layer; the second encoding module includes a plurality of second encoders connected in sequence; the spatial feature extraction module includes a convolution module, a two-dimensional global average pooling layer, a fully connected layer and a regularization layer; the convolution module includes a plurality of sub-convolution units, and the sub-convolution units include a two-dimensional convolution layer and a two-dimensional global maximum pooling layer; the data reconstruction module includes a fully connected layer, an activation layer and a two-dimensional convolution layer; The reconstructed resolution band data, the resampled soil property data, the resampled terrain data, the geographical location data and the soil moisture data to be reconstructed are input into a preset soil moisture reconstruction model for data reconstruction to obtain the reconstructed soil moisture data, including the steps of: The reconstructed resolution band data is used as a time series dynamic variable, the time series dynamic variable and the soil moisture data to be reconstructed are input into the time feature extraction module, spatial mapping and position encoding are performed according to the embedding layer to obtain mapping encoded data, the mapping encoded data is input into the second encoding module for encoding processing to obtain the last encoded data output by the second encoder, and the encoded data output by the last second encoder is processed in sequence through the full connection layer and the regularization layer of the time feature extraction module to obtain time feature data; The resampled soil attribute data, the resampled terrain data, and the geographic location data are used as time series static variables, and the time series static variables and the soil moisture data to be reconstructed are respectively input into the spatial feature extraction module, and convolution processing is performed according to a plurality of sub-convolution units of the convolution module, and the convolution data output by the plurality of sub-convolution units are spliced ​​to obtain first spliced ​​data; and the first spliced ​​data is processed sequentially through the two-dimensional global average pooling layer, the fully connected layer, and the regularization layer to obtain spatial feature data; The time feature data and the space feature data are respectively input into the data reconstruction module, and the time feature data and the space feature data are respectively fully connected according to the fully connected layer, and the fully connected feature data corresponding to the time feature data and the fully connected feature data corresponding to the space feature data output by the fully connected layer are spliced ​​to obtain second spliced ​​data; the second spliced ​​data is processed in sequence through the activation layer and the two-dimensional convolution layer to obtain the reconstructed soil moisture data.

8. A soil moisture reconstruction device, characterized in that: include: A data acquisition module, used to obtain multimodal data collected by a multi-band satellite sensor, wherein the multimodal data includes first resolution band data, second resolution band data, soil moisture data to be reconstructed, soil attribute data, terrain data, and geographic location data; A resolution reconstruction module, used for inputting the first resolution band data and the second resolution band data into a preset band resolution reconstruction model for resolution reconstruction to obtain reconstructed resolution band data, wherein the band resolution reconstruction model is a noise prediction model constructed based on a U-net network structure using the first resolution band data and the second resolution band data as training data; A resampling module, used for resampling the soil property data and the terrain data to the resolution of the reconstructed resolution band data, to obtain resampled soil property data and resampled terrain data; The soil moisture reconstruction module is used to input the reconstructed resolution band data, resampled soil attribute data, resampled terrain data, geographical location data and soil moisture data to be reconstructed into a preset soil moisture reconstruction model for data reconstruction to obtain reconstructed soil moisture data.

9. A computer device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor; when the computer program is executed by the processor, the steps of the soil moisture reconstruction method according to any one of claims 1 to 7 are implemented.

10. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the soil moisture reconstruction method according to any one of claims 1 to 7 are implemented.

Images