Evaporation simulation method and system based on PINN neural network

Abstract

The invention provides an evapotranspiration simulation method and system based on a PINN neural network, and belongs to the technical field of evapotranspiration calculation simulation. The method comprises the following steps: acquiring multi-source meteorological data and high-resolution remote sensing image data of a research area, and constructing an input data set; carrying out standardization processing on the input data set, and respectively generating a remote sensing image grid and a meteorological data grid; the grids are input into a trained PINN model, the PINN model performs feature extraction on the remote sensing image grids and the meteorological data grids by using multilayer convolution, and a feature map representing the evapotranspiration process is generated; embedding a surface energy balance equation into a loss function to realize physical constraint on the model; and combining the extracted features with a physical constraint result to generate a space-time distribution diagram of evapotranspiration. And performing visual display on the space-time distribution diagram based on a GIS technology to obtain an evapotranspiration intensity diagram and a change trend diagram of the research area. The problem that a traditional method lacks physical consistency is solved, and universality is enhanced.

Description

Technical Field

[0001] The invention belongs to the technical field of evapotranspiration calculation simulation, and in particular relates to an evapotranspiration simulation method and system based on a PINN neural network. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Evapotranspiration (ET) is an important part of the energy and water cycle on the earth's surface, and has a significant impact on agricultural irrigation, ecological balance, and climate change. Traditional evapotranspiration estimation methods mainly rely on empirical formulas (such as the FAO-56 Penman-Monteith formula) or physical models (such as the SEBAL surface energy balance model). These methods are calculated by inputting meteorological observation data, remote sensing images, and surface characteristic parameters, and can better explain the physical mechanism of evapotranspiration. However, these methods are highly dependent on the quality and integrity of the data. Once the data is missing or erroneous, the accuracy of the model will drop significantly. At the same time, the traditional model parameterization process is complex and the calculation efficiency is low, which makes it difficult to meet the needs of dynamic monitoring at the regional scale.

[0004] With the development of artificial intelligence and remote sensing technology, deep learning, especially convolutional neural networks (CNN), has been widely used in evapotranspiration simulation research. CNN can capture complex spatiotemporal relationships from remote sensing images and meteorological data by extracting high-order features of input data, greatly reducing dependence on domain expert experience and improving computational efficiency. However, most deep learning models are data-driven and lack the constraints of physical mechanisms, which limits their generalization capabilities in data-scarce scenarios. In addition, these models are often regarded as "black boxes" and it is difficult to explain the relationship between their prediction results and the physical process of evapotranspiration, which poses new challenges to the mechanistic study of the evapotranspiration process. Summary of the invention

[0005] In order to overcome the shortcomings of the above-mentioned prior art, the present invention provides an evapotranspiration simulation method and system based on a PINN neural network, which uses the SEBAL surface energy balance equation as a physical constraint, and combines the nonlinear feature extraction capability of CNN with the physical interpretability of Physics-Informed Neural Networks (PINNs) to achieve high efficiency and accuracy in evapotranspiration simulation. PINN embeds physical constraints (such as energy conservation, water balance, etc.) into the loss function to achieve the fusion of data-driven and physical mechanisms.

[0006] To achieve the above objectives, one or more embodiments of the present invention provide the following technical solutions: The first aspect of the present invention provides a evapotranspiration simulation method based on a PINN neural network; A PINN neural network-based evapotranspiration simulation method, comprising: Obtain multi-source meteorological data and high-resolution remote sensing image data in the study area and construct input datasets; Standardize the meteorological data and remote sensing image data in the input data set to generate remote sensing image grids and meteorological data grids of the study area respectively; The remote sensing image grid and meteorological data grid are input into the trained PINN model, and the dynamic changes of vegetation index are used to correct and refine the evapotranspiration simulation results, and the spatiotemporal distribution map of evapotranspiration in the study area is output; Based on GIS technology, the spatiotemporal distribution of evapotranspiration is visualized to obtain the evapotranspiration intensity map and change trend map of the study area.

[0007] Among them, the PINN model uses multi-layer convolution to extract features from remote sensing image grids and meteorological data grids to generate feature maps representing the evapotranspiration process; The surface energy balance equation is embedded into the loss function to implement physical constraints on the model; The extracted features are combined with the physical constraint results to generate the spatiotemporal distribution map of evapotranspiration.

[0008] As a further technical solution, the multi-source meteorological data includes temperature, precipitation, relative humidity, wind speed and radiation data in the study area.

[0009] As a further technical solution, the process of standardizing the meteorological data and remote sensing image data in the input data set to generate remote sensing image rasters and meteorological data rasters of the study area includes: unifying the data formats of meteorological data and remote sensing image data, eliminating outliers, projecting, resampling space, interpolating time series and filling missing values; and performing atmospheric correction and radiation correction on remote sensing image data; and finally generating remote sensing image rasters and meteorological data rasters of the study area that are consistent in time and space.

[0010] As a further technical solution, during the training process of the PINN model, a supervised learning method was used to compare the observed evapotranspiration data with the model prediction results using the observed evapotranspiration data as labels; Improve model performance using data augmentation, learning rate adjustment, and batch normalization; The mean square error and determination coefficient were used as evaluation indicators of model performance to quantify the accuracy of the simulation results.

[0011] As a further technical solution, the loss function is: ; in, represents the physical constraint loss, which is used to constrain the physical consistency of evapotranspiration simulation; Represents the error of the observed data and is used to minimize the difference between the model prediction and the true data.

[0012] As a further technical solution, the process of using the dynamic changes of vegetation index to correct and refine the evapotranspiration simulation results and generate a spatiotemporal distribution map of evapotranspiration includes: The evapotranspiration results were coupled with the dynamic vegetation index to analyze the impact of vegetation type and dynamic changes on evapotranspiration; Through regional zoning simulation, a detailed estimation of evapotranspiration characteristics under different vegetation cover types can be achieved.

[0013] As a further technical solution, the process of visualizing the spatiotemporal distribution map of evapotranspiration based on GIS technology and obtaining the evapotranspiration intensity map and change trend map of the study area is as follows: Based on the generated spatiotemporal distribution map of evapotranspiration, the interannual and seasonal variation trends of evapotranspiration are analyzed, and the driving effects of meteorological conditions and vegetation changes on evapotranspiration are evaluated; The results are visualized using GIS technology, including regional evapotranspiration intensity maps and change trend maps; the formula for evapotranspiration change intensity is: ; In the formula, is the difference in evapotranspiration before and after the change; is the total area of ​​the study area; For the time span.

[0014] A second aspect of the present invention provides an evapotranspiration simulation system based on a PINN neural network.

[0015] An evapotranspiration simulation system based on a PINN neural network, comprising: The input data set acquisition module is configured to: acquire multi-source meteorological data and high-resolution remote sensing image data of the study area and construct an input data set; The data grid generation module is configured to: perform standardization processing on the meteorological data and remote sensing image data in the input data set, and respectively generate a remote sensing image grid and a meteorological data grid of the study area; The spatiotemporal distribution map acquisition module is configured to: input the remote sensing image grid and the meteorological data grid into the trained PINN model, use the dynamic changes of the vegetation index to correct and refine the evapotranspiration simulation results, and output the spatiotemporal distribution map of the evapotranspiration in the study area; The visualization display module is configured to: visualize the spatiotemporal distribution map of evapotranspiration based on GIS technology, and obtain the evapotranspiration intensity map and change trend map of the study area.

[0016] Among them, the PINN model uses multi-layer convolution to extract features from remote sensing image grids and meteorological data grids to generate feature maps representing the evapotranspiration process; The surface energy balance equation is embedded into the loss function to implement physical constraints on the model; The extracted features are combined with the physical constraint results to generate the spatiotemporal distribution map of evapotranspiration.

[0017] The third aspect of the present invention provides a computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps in the evapotranspiration simulation method based on a PINN neural network as described in the first aspect of the present invention.

[0018] A fourth aspect of the present invention provides an electronic device, comprising a memory, a processor, and a program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the evaporation simulation method based on a PINN neural network as described in the first aspect of the present invention are implemented.

[0019] One or more of the above technical solutions have the following beneficial effects: (1) This paper combines convolutional neural networks (CNNs) with physical information embedding networks (PINNs), fully utilizing the nonlinear modeling capabilities of data-driven methods while embedding physical constraints, thereby significantly improving the accuracy and interpretability of evapotranspiration simulations. The multi-scale spatial features in meteorological data and remote sensing images are automatically captured through the feature extraction module of CNN, and physical constraints such as surface energy balance are introduced using PINNs, solving the problem of lack of physical consistency in traditional methods.

[0020] (2) Through automated data preprocessing, model training, and evapotranspiration estimation, an integrated processing flow for evapotranspiration simulation is achieved, which greatly reduces the reliance on expert knowledge and manual intervention and improves simulation efficiency. In addition, by combining regional zoning with dynamic vegetation indices (such as NDVI), the impact of different vegetation types and dynamic changes on evapotranspiration can be reflected, further enhancing the applicability of the model.

[0021] (3) Combining deep learning technology with GIS analysis can generate evapotranspiration distribution maps with fine spatial distribution and clear physical meaning, supporting temporal and spatial trend analysis and result visualization. This integrated processing not only improves the accuracy and credibility of prediction results, but also provides efficient scientific support for water resources management, ecological and environmental protection, and related fields.

[0022] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0024] Figure 1 This is a flow chart of the method of the first embodiment.

[0025] Figure 2 It is a system structure diagram of the second embodiment. DETAILED DESCRIPTION

[0026] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0027] It should be noted that the terms used herein are for describing specific embodiments only and are not intended to be limiting of exemplary embodiments according to the present invention.

[0028] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0029] The present invention proposes a evapotranspiration simulation method and system based on a PINN neural network, which models the surface energy balance equation through a neural network, combines actual observation data, accurately simulates the evapotranspiration process, improves simulation accuracy and calculation efficiency, and can effectively solve the problem that the traditional model parameterization process is complex, the calculation efficiency is low, and it is difficult to meet the needs of dynamic monitoring at a regional scale. The scheme of the present invention will be described in detail below in conjunction with specific embodiments.

[0030] Embodiment 1 This embodiment discloses a evapotranspiration simulation method based on a PINN neural network; like Figure 1 As shown, a evapotranspiration simulation method based on a PINN neural network includes: Step S1, obtaining multi-source meteorological data and high-resolution remote sensing image data of the study area, and constructing an input data set; Among them, daily meteorological data of the study area are collected, including temperature, precipitation, relative humidity, wind speed, radiation, etc. High-resolution remote sensing images (such as NDVI and LAI) are obtained to dynamically monitor changes in vegetation cover. A long-term, multi-scale input data set is constructed through meteorological observation stations, meteorological reanalysis data, and remote sensing image data to ensure that the spatial resolution and temporal resolution meet the requirements of evapotranspiration simulation. In addition, auxiliary geographic data (such as land use type maps and soil attribute data) are also obtained to provide environmental variables for regional evapotranspiration simulation.

[0031] Step S2, standardizing the meteorological data and remote sensing image data in the input data set to generate a remote sensing image grid and a meteorological data grid of the study area respectively; Among them, the standardized processing of meteorological data and remote sensing image data includes: data format unification, outlier removal, projection transformation, spatial resampling, time series interpolation and missing value filling. In order to ensure data consistency and accuracy, it is also necessary to perform atmospheric correction and radiation correction on remote sensing image data, and generate remote sensing image grids and meteorological data grids of the study area that are consistent in time and space. By obtaining grids of meteorological data and remote sensing image data, it is convenient for subsequent efficient spatial analysis and modeling. Furthermore, the spatial resolution of remote sensing image grids and meteorological data grids is unified to 500m, the temporal resolution is adjusted to daily, data outliers are removed, and interpolation processing is performed to fill missing values ​​to further ensure data accuracy.

[0032] Step S3, inputting the remote sensing image grid and the meteorological data grid into the trained PINN model, using the dynamic changes of the vegetation index to correct and refine the evapotranspiration simulation results, and outputting the spatiotemporal distribution map of the evapotranspiration in the study area; During the PINN model training process, 1 / 10 of the image pairs in the target area image library are randomly selected as samples (if there are more than 1000 pairs, 1000 pairs are selected). The evapotranspiration observation data obtained by the eddy covariance method is used as a label to generate training data. The data is randomly divided into a training set and a validation set with a ratio of 9:1.

[0033] The key variables of surface energy balance are extracted and embedded as physical constraints; the key variables of surface energy balance include: net radiation flux (Rn), sensible heat flux (H), latent heat flux (LE) and soil heat flux (G).

[0034] Create an energy conservation constraint: ; Physical constraints serve as auxiliary training objectives to enhance the physical consistency of model predictions.

[0035] Furthermore, the trained PINN model extracts features from the input data through multi-layer convolution to generate a feature map representing the evapotranspiration process. In the feature extraction process, a dual-branch network with shared weights is used to extract deep features of the dual-phase input data (meteorological and remote sensing).

[0036] Step S31, the dual-branch network with shared weights is mainly used to extract deep features of meteorological data and remote sensing image data respectively. The shared weights represent that the convolution kernel parameters of the two paths in the dual-branch network are the same, indicating that the two paths have the same feature extraction capabilities and are used to capture the similarity of the two types of input data.

[0037] In the process of extracting bi-temporal input data, branch 1 is used to process meteorological data (such as temperature, wind speed and other rasterized inputs), and branch 2 is used to process remote sensing image data (such as NDVI, LAI).

[0038] The input of each branch i=1,2 can be represented as a 3D tensor: ; in and is the spatial dimension, is the number of channels.

[0039] During feature extraction, for the input tensor , the convolution layer applies K convolution kernels (weight sharing), each of which is k×k×C in size, to generate the output feature map : ; in For the l+1 Output feature map of the layer; is the weight of the jth convolution kernel; is the bias term; is the activation function.

[0040] A nonlinear activation function is applied after convolution to introduce nonlinear expression capabilities: ; In the formula, is a nonlinear activation function, is the maximum value function.

[0041] Subsequently, batch normalization is performed on the output feature map to stabilize the training. The formula is as follows: ; in are the mean and variance of the current batch; is the normalized result, F is the feature (or activation value) of the current input, and is the output obtained after the convolution operation; is a very small constant used to prevent division by zero when calculating the standard deviation.

[0042] The spatial dimension of the feature map is reduced layer by layer through downsampling, and the number of channels is expanded at the same time. In this embodiment, after 4 times of downsampling, the size of the feature map is reduced to 1 / 8 of the original size, and the number of channels is expanded to 512.

[0043] Step S32: For the extracted features, use the pyramid pooling module (PPM) to aggregate multi-scale features to improve the perception of global information. First, divide the feature map into pooling areas of different sizes (such as 1×1, 2×2, 4×4), calculate the global average value for each pooling area, and generate a vector of fixed length. These multi-scale features are spliced ​​with the original features to enhance the context expression ability: ; in, is the concatenated feature map; Contact represents the concatenation function; 、 、 They are the feature maps obtained by maximum pooling; is the original feature map.

[0044] The surface energy balance equation (such as the SEBAL model) is embedded into the loss function to ensure that the model training conforms to the physical laws of evapotranspiration. The loss function is defined as: ; in, represents the physical constraint loss, which is used to constrain the physical consistency of evapotranspiration simulation; Represents the error of the observed data and is used to minimize the difference between the model prediction and the true data.

[0045] The extracted features are combined with the physical constraint results to generate a spatiotemporal distribution map of the evapotranspiration in the study area, where the spatiotemporal distribution map of evapotranspiration includes the total evapotranspiration and components such as canopy evaporation, vegetation transpiration, and soil evaporation. Furthermore, the process of generating the spatiotemporal distribution map includes: coupling the evapotranspiration results with dynamic vegetation indices (such as NDVI), with the aim of using the dynamic changes of the vegetation index to further correct or refine the evapotranspiration simulation results to reflect the impact of vegetation cover on the evapotranspiration process.

[0046] Vegetation indices (such as NDVI) and and Highly correlated, and Low correlation with NDVI, among which, It represents the transpiration of vegetation; represents canopy evaporation; Indicates soil evaporation. Therefore, NDVI is used to correct and The simulation results are shown in Figure 2.

[0047] First, the vegetation coverage changes were dynamically monitored by NDVI, and the vegetation coverage rate was calculated. : ; is the maximum value of NDVI in the study area (high density vegetation); is the minimum NDVI value (bare soil) in the study area.

[0048] based on The function corrects each component, for canopy evaporation: ; in is the canopy evaporation coefficient, is the total evapotranspiration.

[0049] For vegetation transpiration: ; in is the canopy evaporation coefficient.

[0050] For soil evaporation: ; In the dynamic coupling correction, the temporal and spatial distribution of evapotranspiration is corrected by combining the dynamic NDVI with the evapotranspiration results of the daily time series. The steps include: Calculated based on daily NDVI ; Calculate canopy evaporation, vegetation transpiration, and soil evaporation components for each grid pixel; Smooth NDVI dynamic changes through time series interpolation or filtering (such as Savitzky-Golay filter) to reduce observation noise.

[0051] Assess the contribution of vegetation types and changes. Compare the evapotranspiration characteristics of different vegetation cover types to quantify the impact of climate change on the regional water cycle; divide regions by land use type (forest, grassland, shrubs, etc.) and refine the estimation of evapotranspiration characteristics.

[0052] In addition, supervised learning methods are used for the PINN model, and observed evapotranspiration data (such as eddy covariance data or remote sensing inversion data) are used as labels to compare with the model prediction results. Technical means such as data enhancement, learning rate adjustment and batch normalization are used to improve model performance. Evaluation indicators of model performance include mean square error (MSE) and coefficient of determination (R²) to quantify the accuracy of simulation results.

[0053] Step S4, visualizing the spatiotemporal distribution map of evapotranspiration based on GIS technology, and obtaining the evapotranspiration intensity map and change trend map of the study area.

[0054] Among them, based on the generated spatiotemporal distribution map of evapotranspiration, the interannual and seasonal variation trends of evapotranspiration are analyzed, and the driving effects of meteorological conditions and vegetation changes on evapotranspiration are evaluated. The results are visualized through GIS technology, including regional evapotranspiration intensity maps and change trend maps, to provide support for water resources management and ecological environmental protection. Among them, the formula for evapotranspiration change intensity is: ; In the formula, is the difference in evapotranspiration before and after the change; is the total area of ​​the study area; For the time span.

[0055] Embodiment 2 This embodiment discloses an evapotranspiration simulation system based on a PINN neural network; like Figure 2 As shown, an evapotranspiration simulation system based on a PINN neural network comprises: The input data set acquisition module is configured to: acquire multi-source meteorological data and high-resolution remote sensing image data of the study area and construct an input data set; The data grid generation module is configured to: perform standardization processing on the meteorological data and remote sensing image data in the input data set, and respectively generate a remote sensing image grid and a meteorological data grid of the study area; The spatiotemporal distribution map acquisition module is configured to: input the remote sensing image grid and the meteorological data grid into the trained PINN model, use the dynamic changes of the vegetation index to correct and refine the evapotranspiration simulation results, and output the spatiotemporal distribution map of the evapotranspiration in the study area; The visualization display module is configured to: visualize the spatiotemporal distribution map of evapotranspiration based on GIS technology, and obtain the evapotranspiration intensity map and change trend map of the study area.

[0056] Among them, the PINN model uses multi-layer convolution to extract features from remote sensing image grids and meteorological data grids to generate feature maps representing the evapotranspiration process; The surface energy balance equation is embedded into the loss function to implement physical constraints on the model; The extracted features are combined with the physical constraint results to generate the spatiotemporal distribution map of evapotranspiration.

[0057] Embodiment 3 The purpose of this embodiment is to provide a computer-readable storage medium.

[0058] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the evapotranspiration simulation method based on a PINN neural network as described in Example 1.

[0059] Embodiment 4 The purpose of this embodiment is to provide an electronic device.

[0060] An electronic device comprises a memory, a processor and a program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the evaporation simulation method based on a PINN neural network as described in Example 1 are implemented.

[0061] The steps involved in the apparatuses of the above embodiments 2, 3 and 4 correspond to the method embodiment 1, and the specific implementation methods can refer to the relevant description part of embodiment 1. The term "computer-readable storage medium" should be understood as a single medium or multiple media including one or more instruction sets; it should also be understood to include any medium that can store, encode or carry an instruction set for execution by a processor and enable the processor to execute any method in the present invention.

[0062] Those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0063] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A PINN neural network-based evapotranspiration simulation method, characterized in that: include: Obtain multi-source meteorological data and high-resolution remote sensing image data in the study area and construct input datasets; Standardize the meteorological data and remote sensing image data in the input data set to generate remote sensing image grids and meteorological data grids of the study area respectively; The remote sensing image grid and meteorological data grid are input into the trained PINN model, and the dynamic changes of vegetation index are used to correct and refine the evapotranspiration simulation results, and the spatiotemporal distribution map of evapotranspiration in the study area is output; Based on GIS technology, the temporal and spatial distribution of evapotranspiration is visualized to obtain the evapotranspiration intensity map and change trend map of the study area; Among them, the PINN model uses multi-layer convolution to extract features from remote sensing image grids and meteorological data grids to generate feature maps representing the evapotranspiration process; The surface energy balance equation is embedded into the loss function to implement physical constraints on the model; The extracted features are combined with the physical constraint results to generate the spatiotemporal distribution map of evapotranspiration.

2. The evapotranspiration simulation method based on a PINN neural network according to claim 1, characterized in that: The multi-source meteorological data include temperature, precipitation, relative humidity, wind speed and radiation data in the study area.

3. The evapotranspiration simulation method based on a PINN neural network according to claim 1, characterized in that: The process of standardizing the meteorological data and remote sensing image data in the input data set to generate the remote sensing image grid and meteorological data grid of the study area includes: unifying the data format of the meteorological data and the remote sensing image data, eliminating outliers, projecting, resampling the space, interpolating the time series and filling the missing values; and performing atmospheric correction and radiation correction on the remote sensing image data; and finally generating the remote sensing image grid and meteorological data grid of the study area that are consistent in time and space.

4. The evapotranspiration simulation method based on a PINN neural network according to claim 1, characterized in that: During the training process of the PINN model, a supervised learning method was used to compare the observed evapotranspiration data with the model prediction results using the observed evapotranspiration data as labels; Improve model performance using data augmentation, learning rate adjustment, and batch normalization; The mean square error and determination coefficient were used as evaluation indicators of model performance to quantify the accuracy of the simulation results.

5. The evapotranspiration simulation method based on a PINN neural network according to claim 1, characterized in that: The loss function is: ； in, represents the physical constraint loss, which is used to constrain the physical consistency of evapotranspiration simulation; Represents the error of the observed data and is used to minimize the difference between the model prediction and the true data.

6. The evapotranspiration simulation method based on a PINN neural network according to claim 1, characterized in that: The process of using the dynamic change of vegetation index to correct and refine the evapotranspiration simulation result and generate the spatiotemporal distribution map of evapotranspiration includes: The evapotranspiration results were coupled with the dynamic vegetation index to analyze the impact of vegetation type and dynamic changes on evapotranspiration; Through regional zoning simulation, a detailed estimation of evapotranspiration characteristics under different vegetation cover types can be achieved.

7. The evapotranspiration simulation method based on a PINN neural network according to claim 1, characterized in that: The process of visualizing the spatiotemporal distribution map of evapotranspiration based on GIS technology and obtaining the evapotranspiration intensity map and change trend map of the study area is as follows: Based on the generated spatiotemporal distribution map of evapotranspiration, the interannual and seasonal variation trends of evapotranspiration are analyzed, and the driving effects of meteorological conditions and vegetation changes on evapotranspiration are evaluated; The results are visualized using GIS technology, including regional evapotranspiration intensity maps and change trend maps; the formula for evapotranspiration change intensity is: ； In the formula, is the difference in evapotranspiration before and after the change; is the total area of ​​the study area; For the time span.

8. An evapotranspiration simulation system based on a PINN neural network, characterized in that: include: The input data set acquisition module is configured to: acquire multi-source meteorological data and high-resolution remote sensing image data of the study area and construct an input data set; The data grid generation module is configured to: perform standardization processing on the meteorological data and remote sensing image data in the input data set, and respectively generate a remote sensing image grid and a meteorological data grid of the study area; The spatiotemporal distribution map acquisition module is configured to: input the remote sensing image grid and the meteorological data grid into the trained PINN model, use the dynamic changes of the vegetation index to correct and refine the evapotranspiration simulation results, and output the spatiotemporal distribution map of the evapotranspiration in the study area; The visualization display module is configured to: visualize the spatiotemporal distribution map of evapotranspiration based on GIS technology, and obtain the evapotranspiration intensity map and change trend map of the study area; Among them, the PINN model uses multi-layer convolution to extract features from remote sensing image grids and meteorological data grids to generate feature maps representing the evapotranspiration process; The surface energy balance equation is embedded into the loss function to implement physical constraints on the model; The extracted features are combined with the physical constraint results to generate the spatiotemporal distribution map of evapotranspiration.

9. A computer-readable storage medium having a program stored thereon, characterized in that: When the program is executed by a processor, the steps of the evapotranspiration simulation method based on a PINN neural network as described in any one of claims 1 to 7 are implemented.

10. An electronic device comprising a memory, a processor, and a program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps in the evapotranspiration simulation method based on the PINN neural network as described in any one of claims 1 to 7 are implemented.

Images