Surface water heat flux integrated estimation method, system and equipment

Abstract

The invention provides a surface water heat flux integrated estimation method, system and equipment, and relates to the technical field of hydro meteorological remote sensing, and the method comprises the steps: according to the target surface temperature data, target net radiation data, target air temperature data, target vegetation coverage data and target soil moisture data of a target region, calculating the target surface temperature data; constructing to obtain target surface environment key parameters corresponding to the target region; and inputting the target earth surface environment key parameters into the surface water heat flux integrated estimation model to obtain target earth surface sensible heat, latent heat and soil heat flux estimation values which are simultaneously output by the surface water heat flux integrated estimation model and correspond to the intra-day time scale of the target region, the surface water heat flux integrated estimation model is obtained by training a physical information neural network machine learning model based on the sample surface water heat flux observation data corresponding to the sample surface water heat flux key parameters and the sample surface water heat flux key parameters. According to the method, the surface water heat flux estimation accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the field of hydrological and meteorological remote sensing technology, and in particular to a surface water and heat flux integrated estimation method, system and equipment. Background Art

[0002] Surface water and heat flux refers to the exchange of water and heat between the earth's surface and the atmosphere. It describes the dynamic exchange process of energy and matter between the earth's surface and the atmosphere, including sensible heat flux (heat flux), latent heat flux and soil heat flux.

[0003] Existing remote sensing methods for estimating water and heat flux estimate latent heat flux, sensible heat flux, and soil heat flux separately, but have many limitations. For example, the empirical regression method relies on the calibration coefficient and has poor regional applicability; the impedance parameterization of the Penman-type formula is complex; the sensible heat flux is affected by the roughness length estimation; the soil heat flux ignores heat conduction; and the energy balance residual method has error transmission. These existing remote sensing methods for estimating water and heat flux make it difficult to accurately estimate the surface water and heat flux under complex surface conditions.

[0004] Therefore, there is an urgent need for an integrated surface water heat flux estimation method, system and equipment to solve the above problems. Summary of the Invention

[0005] In response to the problems existing in the prior art, the present invention provides a method, system and equipment for integrated estimation of surface water heat flux.

[0006] The present invention provides an integrated surface water heat flux estimation method, comprising: According to the target surface temperature data, target net radiation data, target air temperature data, target vegetation coverage data and target soil moisture data of the target area, the target surface environment key parameters corresponding to the target area are constructed; The target surface environment key parameters are input into the surface water heat flux integrated estimation model to obtain the target surface water heat flux estimation value corresponding to the target area on the daily time scale output by the surface water heat flux integrated estimation model, wherein the target surface water heat flux estimation value includes the sensible heat flux estimation value, the latent heat flux estimation value and the soil heat flux estimation value; the surface water heat flux integrated estimation model is obtained by training a physical information neural network machine learning model based on the sample surface environment key parameters and the sample surface water heat flux observation data corresponding to the sample surface environment key parameters.

[0007] According to a surface water heat flux integrated estimation method provided by the present invention, the surface water heat flux integrated estimation model is trained by the following steps: Obtain sample surface temperature data and sample net radiation data corresponding to the intraday time scale of the sample area; Obtain sample temperature data corresponding to the intraday time scale of the sample area; Obtaining sample vegetation coverage data and sample soil moisture data corresponding to the intraday time scale of the sample area; Performing time resolution conversion processing on the sample surface temperature data, the sample net radiation data, the sample air temperature data, the sample vegetation cover data, and the sample soil moisture data to obtain sample surface temperature data, sample net radiation data, sample air temperature data, sample vegetation cover data, and sample soil moisture data with the same time resolution; and constructing key parameters of the sample surface environment based on the sample surface temperature data, sample net radiation data, sample air temperature data, sample vegetation cover data, and sample soil moisture data with the same time resolution; Based on the ground flux station observation data, obtaining sample surface water heat flux observation data of the sample area at the intraday time scale, wherein the sample surface water heat flux observation data includes sensible heat flux observation value, latent heat flux observation value and soil heat flux observation value; Constructing surface water heat flux labels corresponding to the sample surface environment key parameters based on the sample surface water heat flux observation data, and constructing a training sample set based on the sample surface environment key parameters marked with the surface water heat flux labels; Based on the training sample set, the physical information neural network machine learning model is trained, and after determining that the training result satisfies the preset data loss function, the surface water heat flux integrated estimation model is obtained, wherein the preset data loss function is based on the error between the surface water heat flux prediction value and the sample surface water heat flux observation data, and the surface energy balance equation.

[0008] According to the integrated surface water heat flux estimation method provided by the present invention, the preset data loss function is specifically: ; in, represents the preset data loss function, N represents the total number of samples, Indicates the samples, represents the sample surface temperature data, represents the sample temperature data, represents the sample soil moisture data, represents the sample vegetation coverage data, represents the sample net radiation data, represents the observed value of the sensible heat flux, represents the predicted value of sensible heat flux, represents the predicted value of latent heat flux, represents the predicted soil heat flux, represents the surface energy balance weight coefficient, represents the latent heat flux observation value, represents the soil heat flux observation value.

[0009] According to a method for estimating surface water heat flux integration provided by the present invention, before performing time resolution conversion processing on the sample surface temperature data, the sample net radiation data, the sample air temperature data, the sample vegetation cover data, and the sample soil moisture data to obtain the sample surface temperature data, the sample net radiation data, the sample air temperature data, the sample vegetation cover data, and the sample soil moisture data with the same time resolution, the method further includes: The sample surface temperature data, the sample net radiation data, the sample air temperature data, the sample vegetation cover data and the sample soil moisture data are subjected to data preprocessing to obtain the sample surface temperature data, the sample net radiation data, the sample air temperature data, the sample vegetation cover data and the sample soil moisture data after data preprocessing, wherein the data preprocessing includes at least missing data filling processing and invalid value removal processing.

[0010] According to a surface water heat flux integrated estimation method provided by the present invention, the sample surface temperature data and the sample net radiation data are obtained based on geostationary satellites; the sample air temperature data are obtained based on atmospheric reanalysis data; and the sample vegetation cover data and the sample soil moisture data are obtained based on polar-orbiting satellites.

[0011] According to a surface water heat flux integrated estimation method provided by the present invention, after inputting the target surface environment key parameters into the surface water heat flux integrated estimation model and obtaining the target surface water heat flux estimation value corresponding to the target area on the intraday time scale output by the surface water heat flux integrated estimation model, the method further includes: Get preset time scale information; Based on the preset time scale information, the target surface water heat flux estimation value is cumulatively averaged to obtain the surface water heat flux estimation values ​​corresponding to different time scales.

[0012] The present invention also provides a surface water heat flux integrated estimation system, comprising: A data processing module is used to construct target surface environment key parameters corresponding to the target area based on target surface temperature data, target net radiation data, target air temperature data, target vegetation coverage data and target soil moisture data of the target area; A flux estimation module is used to input the target surface environment key parameters into the surface water heat flux integrated estimation model to obtain the target surface water heat flux estimation value corresponding to the target area on the daily time scale output by the surface water heat flux integrated estimation model, wherein the target surface water heat flux estimation value includes the sensible heat flux estimation value, the latent heat flux estimation value and the soil heat flux estimation value; the surface water heat flux integrated estimation model is obtained by training a physical information neural network machine learning model based on the sample surface environment key parameters and the sample surface water heat flux observation data corresponding to the sample surface environment key parameters.

[0013] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the integrated surface water heat flux estimation method as described above is implemented.

[0014] The integrated surface water and heat flux estimation method, system and equipment provided by the present invention construct key surface environmental parameters by integrating multi-source data such as surface temperature, net radiation, air temperature, vegetation cover and soil moisture in the target area. The key surface environmental parameters are then input into an integrated water and heat flux estimation model trained by sample surface environmental parameters and synchronously observed water and heat flux data, thereby outputting estimated values ​​of sensible heat, latent heat and soil heat flux on a daily time scale, significantly improving the accuracy of water and heat flux estimation under complex surface conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 A schematic flow chart of the integrated surface water heat flux estimation method provided by the present invention; Figure 2 A schematic diagram of the overall process of the geostationary satellite-based integrated estimation method for surface water and heat flux provided by the present invention; Figure 3 This is a schematic diagram of the estimation results of sensible heat, latent heat and soil heat flux based on the integrated surface water heat flux estimation model provided by the present invention; Figure 4 This is a schematic diagram of the structure of the integrated surface water heat flux estimation system provided by the present invention; Figure 5 This is a schematic structural diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0017] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0018] Sensible heat flux, latent heat flux, and soil heat flux are important components of the surface energy balance. Sensible heat flux is driven by the temperature gradient between the surface and the atmosphere, transferring energy through heat conduction and convection, directly influencing the spatiotemporal distribution of atmospheric temperature. Latent heat flux originates from the evaporation or condensation of water, absorbing or releasing heat with phase change, regulating atmospheric humidity and driving cloud and precipitation formation. Soil heat flux, driven by the vertical soil temperature gradient, reflects the storage or release of thermal energy between the soil and the surface and serves as a critical buffer for regional energy budgets.

[0019] Deployed in geosynchronous orbit, geostationary meteorological satellites can provide continuous, high-frequency observations of target areas, providing unique technical support for quantifying surface water and heat fluxes. Their high-frequency observations can capture the intraday dynamics of water and heat fluxes, transcending the temporal and spatial limitations of traditional ground-based observations. This provides critical data support for extreme weather warnings (such as heat waves, rainstorms, and flooding), climate change assessments (such as regional energy cycle evolution), agricultural water resource management (such as crop water consumption monitoring), and sustainable ecological development (such as urban heat island effect control). By analyzing the water and heat flux characteristics in satellite remote sensing data, the scientific and accurate nature of multi-scale climate forecasts and water resource management decisions can be significantly improved.

[0020] Existing remote sensing methods for estimating heat flux from water use methods that estimate latent heat flux, sensible heat flux, and soil heat flux separately. Among them, the latent heat flux in surface heat flux, also known as evapotranspiration, is a core parameter in surface energy and water balance.

[0021] Existing methods for estimating latent heat flux can be divided into methods that directly parameterize latent heat flux and energy balance residual methods based on sensible heat flux estimation. Direct parameterization methods include empirical regression methods and methods based on Penman-type formulas. Specifically, empirical regression methods estimate latent heat flux by directly establishing an empirical relationship between latent heat flux and influencing variables. Evapotranspiration is the result of the combined effects of surface energy, temperature, vegetation, soil, and atmospheric conditions. Currently, available variables include atmospherically driven wind, temperature, humidity, and pressure, vegetation index, surface temperature, and solar radiation. With the development of machine learning technology, such methods have been further improved.

[0022] The Penman equation class introduces the concept of canopy impedance into the Penman equation to characterize the effects of vegetation physiology and soil water supply on latent heat flux, thereby estimating actual evaporation from unsaturated surfaces. This is a direct parameterization of latent heat flux. The energy balance residual method first uses remote sensing reversible parameters to obtain surface net radiation, soil heat flux, and sensible heat flux. The surface latent heat flux is then derived from the residual term of the energy balance equation. Sensible heat flux is primarily estimated using the global transfer formula based on the Monin-Obukhov similarity theory, utilizing the surface-air temperature difference. Soil heat flux is primarily estimated by assuming a proportional relationship with net radiation and correlation with vegetation cover.

[0023] Among the existing surface water heat flux estimation methods, the latent heat flux estimation based on the empirical regression method is simple, has few input variables, and is easy to operate, but it relies on the regression coefficient, and the coefficient determination usually requires ground measurement data calibration, which limits its application under different surface conditions at the regional scale; the latent heat flux estimation based on the Penman-type formula only requires a layer of atmospheric parameters, but its essence is the calculation of various impedances, with many input parameters and a complex model. On a complex and uneven underlying surface, the parameterization of impedance is very complex and uncertain, which affects the estimation accuracy and application of the latent heat flux; the estimation of the sensible heat flux depends on Due to the heat transfer roughness length and the difference between the radiative temperature and the aerodynamic temperature, additional impedances need to be parameterized. When the surface is partially covered with vegetation, the water and heat exchange between the soil and vegetation may not occur at the same altitude, making it difficult to estimate the heat transfer roughness length and hindering the accuracy and application of sensible heat flux estimates. Soil heat flux estimates only assume a correlation with net radiation and vegetation cover, ignoring the thermal conductivity properties of the soil itself, which affects the accuracy and application of the estimates. For latent heat flux estimates using the energy balance remainder method, errors in the sensible heat flux and soil heat flux estimates are transferred to the latent heat flux estimate. Furthermore, existing methods for estimating surface water and heat flux are primarily based on instantaneous observations from polar-orbiting satellites or estimates on a daily scale. They do not fully utilize the continuous surface observation capabilities of geostationary satellites and cannot obtain information on the intraday variability of surface water and heat flux.

[0024] In response to the problems in existing parameterization schemes for sensible heat, latent heat and soil heat flux that the input parameters are numerous and difficult to obtain, and the impedance, heat transfer roughness length, and soil thermal conductivity properties are difficult to accurately estimate under complex surface conditions, the present invention provides an integrated surface water heat flux estimation method based on geostationary satellites. By fully utilizing the high-frequency observation characteristics of geostationary satellites, the equation parameters are solved through machine learning methods based on the surface energy balance equation, eliminating the need to estimate parameters such as impedance, heat transfer roughness length, and soil thermal conductivity properties that are difficult to quantify, thereby achieving simultaneous estimation of the intraday variation information of sensible heat, latent heat, and soil heat flux.

[0025] Figure 1 The schematic diagram of the flow chart of the integrated estimation method of surface water heat flux provided by the present invention is as follows: Figure 1 As shown, the present invention provides an integrated estimation method for surface water heat flux, comprising: Step 101 : constructing target surface environment key parameters corresponding to the target area based on target surface temperature data, target net radiation data, target air temperature data, target vegetation coverage data and target soil moisture data of the target area.

[0026] In this paper, the target surface temperature data refers to the actual surface temperature of the target area, acquired via geostationary satellites. It reflects the thermal state of the surface at a specific time and space. As a key indicator of surface radiant energy, surface temperature directly influences the energy exchange between the surface and the atmosphere. For example, higher surface temperatures accelerate surface water evaporation, affecting soil moisture and vegetation growth. Furthermore, abnormal surface temperature can be associated with environmental issues such as the urban heat island effect and drought, making it essential information for constructing key parameters of the surface environment.

[0027] Target net radiation data is the sum of shortwave net radiation and longwave net radiation, representing the net energy actually received by the Earth's surface. Shortwave net radiation refers to the difference between the total solar radiation reaching the Earth's surface and the solar radiation reflected by the surface. Longwave net radiation refers to the difference between the atmospheric longwave radiation and the longwave radiation at the Earth's surface. Target net radiation data can also be obtained from geostationary satellites. Net radiation data is the primary energy source driving various physical, chemical, and biological processes on the Earth's surface. It determines the changing trends in surface temperature and the migration and transformation of substances such as water and heat. For example, in areas with high net radiation, surface water evaporation and vegetation transpiration may be more intense, thus affecting the regional water cycle and climate characteristics.

[0028] Target temperature data refers to the temperature of the air in the target area. It can be obtained through atmospheric reanalysis data and reflects the thermal state of the atmosphere. Changes in temperature data can affect the heat balance of the surface. For example, on cold nights, a drop in temperature can cause a rapid drop in surface temperature, affecting the depth of soil freezing and the cold resistance of vegetation. At the same time, surface temperature also feeds back to the atmosphere through radiation and convection, affecting the distribution and variability of temperature.

[0029] Target vegetation cover data refers to the percentage of the vertically projected surface area of ​​vegetation (including herbs, shrubs, and trees) in the target area relative to the total area of ​​the statistical area. This data can be obtained using polar-orbiting satellites. Vegetation cover reflects the condition of surface vegetation and the quality of the ecological environment. Vegetation, through physiological processes such as photosynthesis and transpiration, plays a key role in the surface water cycle, energy balance, and climate regulation. For example, areas with high vegetation cover generally have better soil and water conservation capabilities, reducing surface runoff and soil erosion. Vegetation can also improve the local microclimate by blocking sunlight and lowering surface temperature.

[0030] Target soil moisture data represents the soil moisture content in the target area and can also be obtained via polar-orbiting satellites. Soil moisture is a crucial component of the Earth's surface ecosystem, directly influencing the growth, development, and distribution of vegetation. Suitable soil moisture conditions provide plants with an adequate water supply, promoting photosynthesis and metabolism. However, excessive or insufficient soil moisture can adversely affect vegetation growth, leading to root hypoxia, wilting, and even death. Furthermore, soil moisture participates in the surface water cycle, influencing processes such as surface runoff, infiltration, and evaporation.

[0031] After collecting the above data, the collected raw data are quality checked and corrected to remove outliers and noise interference, ensure the accuracy and reliability of the data, and facilitate subsequent analysis and comparison.

[0032] Step 102: Input the target surface environment key parameters into the surface water heat flux integrated estimation model to obtain the target surface water heat flux estimation value corresponding to the target area on the daily time scale output by the surface water heat flux integrated estimation model, wherein the target surface water heat flux estimation value includes the sensible heat flux estimation value, the latent heat flux estimation value and the soil heat flux estimation value; the surface water heat flux integrated estimation model is obtained by training a physical information neural network machine learning model based on the sample surface environment key parameters and the sample surface water heat flux observation data corresponding to the sample surface environment key parameters.

[0033] In the present invention, the construction stage of the integrated surface water heat flux estimation model is obtained by training the machine learning model using the sample surface environment key parameters and the corresponding sample surface water heat flux observation data; in the application stage, the target surface environment key parameters of the target area are input into the integrated surface water heat flux estimation model, and the integrated surface water heat flux estimation model outputs the target surface water heat flux estimation value of the target area on the intraday time scale. The estimated value includes three parts: sensible heat flux, latent heat flux and soil heat flux.

[0034] Specifically, in the present invention, the key parameters of the target surface environment are a series of parameters that reflect the key characteristics and status of the surface environment of the target area, including surface temperature, net radiation, air temperature, vegetation coverage and soil moisture, etc. These parameters can be combined to comprehensively describe the surface environmental conditions of the target area. They are important input information for estimating the surface water and heat flux, helping the integrated surface water and heat flux estimation model to understand the surface environmental characteristics of the target area, thereby more accurately estimating the surface water and heat flux.

[0035] The sample surface environment key parameters are surface environment key parameter data collected from multiple representative regions. These regions should have a certain degree of diversity in terms of geographical environment, climatic conditions and vegetation types to ensure that the integrated surface water and heat flux estimation model can learn the water and heat flux change laws under different surface environments.

[0036] The sample surface water and heat flux observation data are the actual water and heat flux data of the sample surface obtained through field observation, including sensible heat flux, latent heat flux and soil heat flux. These observation data serve as the true labels of the integrated surface water and heat flux estimation model and are used to train and verify the accuracy of the model.

[0037] During the training process, the physical information neural network machine learning model is trained using continuous information on the daily variations of key sample surface environmental parameters as input and corresponding daily variations of sample surface water and heat flux observation data as output. The physical information neural network machine learning model continuously adjusts its parameters to learn the complex nonlinear relationship between input parameters and output results until it achieves good prediction accuracy on both the training and validation sets. The trained physical information neural network machine learning model (i.e., the integrated surface water and heat flux estimation model) can quickly and accurately estimate surface water and heat flux based on the input key surface environmental parameters.

[0038] In the present invention, the integrated surface water and heat flux estimation model estimates the surface water and heat flux on the intraday time scale. The intraday time scale refers to the time range within a day, which is divided into hours, half hours or even smaller time intervals. It can provide a more detailed understanding of the diurnal variation of energy and water exchange between the surface and the atmosphere, such as the differences in water and heat flux characteristics during the day and night, and in different time periods. It helps to deeply analyze the diurnal variation of surface water and heat flux and its influencing factors, such as the diurnal variation of solar radiation and the diurnal rhythm of vegetation physiological activities. In the present invention, the integrated surface water and heat flux estimation model outputs the target surface water and heat flux estimation value of the target area on the intraday time scale, including the sensible heat flux estimation value, the latent heat flux estimation value and the soil heat flux estimation value. These estimation values ​​are presented in the form of time series, showing the changes in surface water and heat flux at different times.

[0039] The output estimation results can then be analyzed. For example, statistical indicators such as the average, maximum, and minimum water and heat flux values ​​for different time periods can be calculated, and a daily water and heat flux curve can be plotted. Furthermore, the estimation results can be compared with measured data (if available) or with estimates from other models to assess the accuracy and reliability of the model. If the estimation results show significant deviations, further analysis may be necessary, such as the quality of the input data and the model parameter settings, and optimization and improvement of the model can be carried out.

[0040] The integrated surface water and heat flux estimation method provided by the present invention constructs key surface environmental parameters by integrating multi-source data such as surface temperature, net radiation, air temperature, vegetation cover and soil moisture in the target area. The key surface environmental parameters are then input into an integrated water and heat flux estimation model trained by sample surface environmental parameters and synchronously observed water and heat flux data, thereby outputting estimated values ​​of sensible heat, latent heat and soil heat flux on a daily time scale, significantly improving the accuracy of water and heat flux estimation under complex surface conditions.

[0041] Based on the above embodiment, the surface water heat flux integrated estimation model is trained by the following steps: Obtain sample surface temperature data and sample net radiation data corresponding to the intraday time scale of the sample area; Obtain sample temperature data corresponding to the intraday time scale of the sample area; Obtaining sample vegetation coverage data and sample soil moisture data corresponding to the intraday time scale of the sample area; Performing time resolution conversion processing on the sample surface temperature data, the sample net radiation data, the sample air temperature data, the sample vegetation cover data, and the sample soil moisture data to obtain sample surface temperature data, sample net radiation data, sample air temperature data, sample vegetation cover data, and sample soil moisture data with the same time resolution; and constructing key parameters of the sample surface environment based on the sample surface temperature data, sample net radiation data, sample air temperature data, sample vegetation cover data, and sample soil moisture data with the same time resolution; Based on the ground flux station observation data, obtaining sample surface water heat flux observation data of the sample area at the intraday time scale, wherein the sample surface water heat flux observation data includes sensible heat flux observation value, latent heat flux observation value and soil heat flux observation value; Constructing surface water heat flux labels corresponding to the sample surface environment key parameters based on the sample surface water heat flux observation data, and constructing a training sample set based on the sample surface environment key parameters marked with the surface water heat flux labels; Based on the training sample set, the physical information neural network machine learning model is trained, and after determining that the training results meet the preset data loss function, the surface water heat flux integrated estimation model is obtained, wherein the preset data loss function is based on the error between the surface water heat flux prediction value and the sample surface water heat flux observation data, and the surface energy balance equation.

[0042] In the present invention, since the data collection time intervals of different data sources may be different, the time resolutions of the sample surface temperature, net radiation, air temperature, vegetation cover and soil moisture data obtained are inconsistent. Through time resolution conversion processing, these data are unified to the same time interval, such as 1 hour, 30 minutes, etc. Specifically, in the present invention, interpolation methods (such as linear interpolation, spline interpolation) can be used to downscale and resample data with higher time resolution, or to upscale and resample data with lower time resolution. For example, if the surface temperature data is collected every half hour, and the vegetation coverage data has only one value per day, the vegetation coverage data with the same time resolution as the surface temperature data can be obtained by interpolation through the average vegetation coverage within the day or in combination with other auxiliary information (such as vegetation growth model).

[0043] Furthermore, the temporally resolved sample surface temperature, net radiation, air temperature, vegetation cover, and soil moisture data were integrated to form a set of key parameters that comprehensively reflect the surface environmental characteristics of the sample area. These parameters provide input features for the subsequent construction of an integrated surface water and heat flux estimation model. Analyzing the interrelationships between these parameters helps the model better understand the mechanisms by which the surface environment influences water and heat flux.

[0044] In the present invention, the sample surface water heat flux observation data is obtained based on the ground flux station observation data, including sensible heat flux observations, latent heat flux observations, and soil heat flux observations. The ground flux station calculates the sensible heat flux and latent heat flux between the surface and the atmosphere by measuring parameters such as wind speed, temperature, and humidity, while the soil heat flux is measured by a heat flux plate. In the present invention, the surface water heat flux observations at different times of the day are obtained to describe in detail the diurnal variation of energy and moisture exchange between the surface and the atmosphere, such as the relative size changes of sensible heat flux and latent heat flux during the day, and the direction and intensity changes of soil heat flux at night.

[0045] Furthermore, the sample surface water heat flux observation data (sensible heat flux observations, latent heat flux observations, and soil heat flux observations) are used as labels for the corresponding sample surface environmental key parameters. This clearly defines the true surface water heat flux value corresponding to the surface environmental key parameter at each time point. The sample surface environmental key parameters labeled with surface water heat flux labels are then combined to form a training sample set. Each sample contains a set of surface environmental key parameters (input) and corresponding surface water heat flux observations (output) for subsequent machine learning model training.

[0046] In the present invention, the physical information neural network machine learning model is capable of processing complex nonlinear relationships and is suitable for estimating surface water heat flux. Specifically, a training sample set is input into the physical information neural network machine learning model, which continuously adjusts its own parameters (such as the weights and biases of the neural network) to learn the mapping relationship between the input key parameters of the surface environment and the output surface water heat flux observations. During the training process, the training sample set is divided into a training set and a validation set. The training set is used to update the model parameters, and the validation set is used to evaluate the generalization ability of the model to prevent overfitting.

[0047] In the present invention, the preset data loss function is constructed based on the error between the predicted surface water heat flux and the sample surface water heat flux observation data, as well as the surface energy balance equation. This function not only takes into account the difference between the predicted and observed values ​​(such as the mean square error (MSE) and mean absolute error (MAE)), but also constrains the prediction results through the surface energy balance equation to ensure that the estimated surface water heat flux satisfies the law of conservation of energy. Based on the above embodiment, the preset data loss function is specifically: ; in, represents the preset data loss function, N represents the total number of samples, Indicates the samples, represents the sample surface temperature data, represents the sample temperature data, represents the sample soil moisture data, represents the sample vegetation coverage data, represents the sample net radiation data, represents the observed value of the sensible heat flux, represents the predicted value of sensible heat flux, represents the predicted value of latent heat flux, represents the predicted soil heat flux, represents the surface energy balance weight coefficient, represents the latent heat flux observation value, represents the soil heat flux observation value.

[0048] During the training process, the value of the loss function is continuously calculated. When the value of the loss function meets the preset threshold (that is, the training result meets the preset data loss function), it is considered that the machine learning model has learned the relationship between the input parameters and the output results. At this time, the training is stopped and the integrated surface water and heat flux estimation model is obtained, which can be used to estimate the surface water and heat flux in other regions or unobserved periods.

[0049] On the basis of the above embodiment, before performing time resolution conversion processing on the sample surface temperature data, the sample net radiation data, the sample air temperature data, the sample vegetation cover data, and the sample soil moisture data to obtain the sample surface temperature data, the sample net radiation data, the sample air temperature data, the sample vegetation cover data, and the sample soil moisture data with the same time resolution, the method further includes: The sample surface temperature data, the sample net radiation data, the sample air temperature data, the sample vegetation cover data and the sample soil moisture data are subjected to data preprocessing to obtain the sample surface temperature data, the sample net radiation data, the sample air temperature data, the sample vegetation cover data and the sample soil moisture data after data preprocessing, wherein the data preprocessing includes at least missing data filling processing and invalid value removal processing.

[0050] In the present invention, after obtaining sample surface temperature, sample net radiation, sample air temperature, sample vegetation cover and sample soil moisture data, due to the influence of various factors such as equipment accuracy, environmental interference and transmission errors during the data acquisition process, there are often missing values ​​and invalid values ​​in the original data. These abnormal data will interfere with subsequent model training and analysis, reducing the accuracy and reliability of the model. Therefore, the present invention adopts data preprocessing to clean and correct these data to ensure the quality and integrity of the data, and provide high-quality input data for building an accurate integrated estimation model of surface water and heat flux. For example, during the data transmission process, some data may fail to be successfully transmitted to the data center due to network problems, signal interference and other reasons, resulting in data missing. For time series data, if the data changes relatively smoothly within a period of time before and after the missing data, the average value of the data within a certain time window before and after the missing value can be used to fill in. When calculating the intraday change of surface temperature, if the data for a certain hour is missing, the average value of the surface temperature for two hours before and after the hour can be taken as the filling value. If the data changes linearly near the missing point, the value of the missing point is calculated based on the values ​​of the two known data points before and after the missing point and the time interval between them. For example, if the temperature in a certain area is known to be 20 degrees Celsius and 24 degrees Celsius at 10 am and 12 am respectively, the temperature at 11 am can be calculated as 22 degrees Celsius by linear interpolation.

[0051] In the present invention, the data acquisition equipment may have measurement errors, causing the collected data to fall outside a reasonable range. For example, the accuracy of a temperature sensor is limited, and in extreme environments, it may measure clearly unreasonable temperature values. Furthermore, during data transmission, the received data may contain garbled characters or invalid values ​​due to reasons such as packet loss, corruption, or encoding errors. Alternatively, certain environmental factors may interfere with the normal operation of the data acquisition equipment, generating invalid data. For example, strong electromagnetic interference may affect the signal transmission of the sensor, resulting in abnormal fluctuations or invalid values ​​in the collected data.

[0052] Based on the invalid values ​​generated by the above reasons, the present invention can set reasonable upper and lower thresholds according to the physical meaning and actual distribution of the data. Data that exceeds the threshold range is identified as invalid values ​​and removed. For example, it is known that the normal range of temperature variation in a certain area within a year is -20 degrees Celsius to 40 degrees Celsius, then the temperature data below -20 degrees Celsius or above 40 degrees Celsius will be regarded as invalid values ​​and removed. Alternatively, the judgment can be made in combination with the inherent logical relationship of the data. For example, the surface temperature on a clear sky is usually not lower than the air temperature. If the surface temperature is significantly lower than the air temperature and does not conform to the actual physical process, it can be determined as an invalid value.

[0053] After missing data filling and invalid value removal, the resulting sample surface temperature data, sample net radiation data, sample air temperature data, sample vegetation cover data, and sample soil moisture data are of higher quality and completeness. These high-quality data can provide reliable input features for the subsequent construction of an integrated surface water and heat flux estimation model, helping to improve the model's training results and prediction accuracy. At the same time, the complete dataset also facilitates more in-depth data analysis and research, such as analyzing the correlation between key surface environmental parameters and surface water and heat flux, and exploring the diurnal and seasonal variations of surface water and heat flux.

[0054] Based on the above embodiment, the sample surface temperature data and the sample net radiation data are obtained based on geostationary satellites; the sample air temperature data are obtained based on atmospheric reanalysis data; and the sample vegetation cover data and the sample soil moisture data are obtained based on polar-orbiting satellites.

[0055] Geostationary satellites have an orbital period that matches the Earth's rotational period, remaining stationary relative to the Earth's surface. This characteristic enables them to conduct continuous, uninterrupted observations of specific areas, acquiring data with high temporal resolution. In this invention, geostationary satellites utilize a variety of sensors to measure physical quantities related to surface temperature and net radiation, two parameters whose dynamic intraday changes require capture. For example, thermal infrared sensors on geostationary satellites can detect infrared radiation emitted by the Earth's surface and convert this energy into surface temperature values. These sensors have high spatial and temporal resolution, providing surface temperature data at various timescales (e.g., hours and minutes), meeting the requirements for monitoring dynamic surface temperature changes required for surface water and heat flux estimation.

[0056] Atmospheric reanalysis data is a set of atmospheric state variable data sets at a global or regional scale generated by combining observation data (including ground meteorological station observations, satellite remote sensing observations, and sounding data) with numerical weather forecast models and using data assimilation technology. Atmospheric reanalysis data comprehensively considers information from multiple observation data sources and fills in the gaps in observation data through model simulation, providing continuous and complete meteorological element field data. In the present invention, for the sample air temperature data required for surface water and heat flux estimation, atmospheric reanalysis data can provide a continuous intraday air temperature series. These data not only have a high temporal resolution (such as hourly), but also have good spatial coverage, which can make up for the spatial and temporal limitations of ground meteorological station observations. For example, in some areas where ground meteorological stations are sparsely distributed, atmospheric reanalysis data can provide relatively reliable air temperature information to ensure the integrity of the input variables required for surface water and heat flux estimation.

[0057] Polar-orbiting satellites can provide high-resolution observation data across the globe. They typically carry a variety of sensors, including multispectral and microwave sensors. Multispectral sensors can obtain spectral reflectance information from the Earth's surface in different wavelengths, allowing vegetation coverage to be inferred using algorithms such as the vegetation index. Microwave sensors are sensitive to soil moisture and can penetrate clouds and vegetation to obtain information on surface soil moisture.

[0058] In the present invention, based on the multispectral data of polar-orbiting satellites, vegetation indices such as the Normalized Difference Vegetation Index (NDVI) and the Enhanced Vegetation Index (EVI) can be used in combination with ground-measured data to calibrate and verify the model, and vegetation coverage data at different time scales (such as multi-day or daily scales) can be inverted. These data can reflect the growth status and spatial distribution of surface vegetation.

[0059] Microwave sensors on polar-orbiting satellites (such as active microwave radars and passive microwave radiometers) are the primary means of acquiring soil moisture data. Active microwave radars transmit microwave signals and receive surface-scattered echoes to obtain information about soil surface roughness and dielectric constant, thereby inferring soil moisture. Passive microwave radiometers measure the microwave radiation energy emitted from the surface and, in conjunction with radiation transmission models, infer soil moisture. In this paper, the soil moisture data products acquired by polar-orbiting satellites have high spatial resolution and a certain temporal resolution (e.g., several days to a week), capable of reflecting the spatial distribution and dynamic changes of soil moisture.

[0060] The present invention makes comprehensive use of multiple data sources so that the model input can be obtained through remote sensing data, thereby realizing large-area estimation of surface water heat flux, while reducing the errors and uncertainties that may exist in a single data source, and improving the accuracy and reliability of integrated estimation of surface water heat flux.

[0061] Based on the above embodiment, after inputting the target surface environment key parameters into the surface water heat flux integrated estimation model and obtaining the target surface water heat flux estimation value corresponding to the target area on the intraday time scale output by the surface water heat flux integrated estimation model, the method further includes: Get preset time scale information; Based on the preset time scale information, the target surface water heat flux estimation value is cumulatively averaged to obtain the surface water heat flux estimation values ​​corresponding to different time scales.

[0062] Different application scenarios require different timescales for estimating surface water and heat flux. For example, in agricultural irrigation management, understanding daily variations in surface water and heat flux is crucial to properly schedule irrigation times and quantities, ensuring the necessary moisture and heat conditions for crop growth. In climate change research, however, long-term trends in surface water and heat flux on monthly or annual scales are often of greater interest for analyzing the energy balance and water cycle characteristics of global or regional climate systems.

[0063] Furthermore, the specific time range is clarified by presetting time scale information. For example, the daily scale can be set to a natural day (from 0:00 to 24:00 on the current day) or a meteorological day (usually from 20:00 the previous day to 20:00 on the current day, used for meteorological business statistics); the monthly scale can be divided by month, or customized according to actual needs (such as agricultural season months); the annual scale can be a calendar year or a hydrological year (with the start and end times determined according to local hydrological characteristics). In addition to clarifying the time range, the time interval must also be determined, that is, the interval between two adjacent estimated time points. For example, in intraday estimation, the time interval is 1 hour or 30 minutes; in daily estimation, the time interval is 1 day; in monthly estimation, the time interval is 1 month; and in annual estimation, the time interval is 1 year.

[0064] After obtaining daily sensible heat, latent heat, and soil heat flux information, the estimated water heat flux values ​​within the corresponding time range are cumulatively averaged according to the preset time scale information. For example, in a daily-scale estimation, the estimated sensible heat flux, latent heat flux, and soil heat flux values ​​at each time of the day (e.g., hourly) are added and averaged to obtain the daily average sensible heat flux, latent heat flux, and soil heat flux. The cumulative averaging process reflects the average water heat flux within that time scale, intuitively reflecting the surface energy and water budget, and can produce estimates at different time scales. The averaging method can be selected according to specific needs, such as arithmetic average and weighted average.

[0065] In one embodiment, the cumulative averaging process is described on a daily scale. Assuming that the sensible heat flux, latent heat flux, and soil heat flux are calculated hourly, the estimated sensible heat flux values ​​for the 24 hours of a day are summed to obtain the total sensible heat flux for that day. Similarly, the 24-hour estimated values ​​of the latent heat flux and soil heat flux are summed to obtain the total latent heat flux and total soil heat flux for that day. The total sensible heat flux is then divided by 24 hours to obtain the average sensible heat flux for that day. The total latent heat flux and total soil heat flux are then divided by 24 hours to obtain the average latent heat flux and average soil heat flux for that day.

[0066] The present invention uses cumulative averaging processing to make the estimated value better reflect the real characteristics of surface water heat flux at different time scales, and expand the time scale of surface water heat flux estimation.

[0067] Figure 2 The overall flow diagram of the integrated estimation method of surface water heat flux based on geostationary satellite provided by the present invention can be referred to Figure 2 The figure below provides an overview of the integrated surface water heat flux estimation method provided by the present invention. In the present invention, the geostationary satellites can be selected from the Fengyun series, MSG series, GOES series, or Sunflower series, without any specific limitation. Furthermore, continuous observations from networked polar-orbiting satellites can also provide the input data required by the present invention.

[0068] In this invention, there are five main input variables, including surface temperature ( ), net radiation ( )、Temperature( ), vegetation coverage ( ), soil moisture ( ), among which, the surface temperature and net radiation can be directly obtained from geostationary satellite observations. The three variables of air temperature, vegetation cover and soil moisture are obtained by using the daily continuous air temperature of atmospheric reanalysis data, and the multi-day or daily scale data of vegetation cover and soil moisture based on polar-orbiting satellites.

[0069] Furthermore, the input variable data of the present invention is required to be continuous within a day, and the data time interval is half an hour or hour. The continuous data within a natural day is taken as a valid sample, and the geostationary satellite observation data can meet this time scale requirement; the temperature data from the atmospheric reanalysis data is usually also on the hourly scale, which can meet the input requirements; the vegetation coverage data from the polar-orbiting satellite is usually on the daily or 8-day time scale. Since the vegetation coverage is not sensitive to time changes, for the daily scale data, it can be directly assumed that the time within the day is unchanged. For the 8-day time scale, the present invention uses the interval data of two consecutive times to obtain the daily scale data through linear interpolation, and then assumes that it is unchanged within the day; soil moisture usually does not change much on the daily scale. Assuming that the soil moisture is unchanged within the day, it is directly obtained using the daily scale soil moisture data.

[0070] In this invention, the output estimated data is determined to be hourly or half-hourly based on the final estimation goal, thereby unifying the temporal resolution of the input daily data for surface temperature, air temperature, net radiation, vegetation cover, and soil moisture. In particular, for half-hourly data, the present invention averages the data from two adjacent moments. Because thermal infrared surface temperature data is affected by clouds, direct satellite inversion data often produces invalid values. This invention excludes these invalid values ​​from the calculation.

[0071] In the present invention, the above five input variables are selected to be closely related to the surface water heat flux.H )、latent heat( LE ) and soil heat flux ( G ) is expressed by the following formula: ;Formula (1) ;Formula (2) ;Formula (3) For the functional relationships in formula (1), formula (2) and formula (3), 、 and The present invention uses ground flux site observation data and solves parameters through machine learning methods. The ground flux site observation data include: sensible heat, latent heat and soil heat flux. The three variables are target variables. The site observation data are usually on a half-hour or hourly scale. By processing these target variables, continuous time scale data within the day are obtained (that is, sample surface water heat flux observation data on the intraday time scale).

[0072] Since machine learning is a data-driven method for finding parameters, this paper uses available site data and consistent long-term satellite data to construct a preset data loss function through a physical information neural network machine learning method, while accurately optimizing sensible heat, latent heat, and soil heat flux while complying with the physical constraints of the surface energy balance equation. , the formula is as follows: ;Formula (4) In the machine learning process of the neural network, the error of the loss function of the above formula (4) is ensured to be minimal. Considering that the scale ranges of the observation instruments for measuring surface sensible heat, latent heat and soil heat flux at the site are different, there is a problem of energy balance not being closed. The error of energy imbalance is about 20%. The present invention adds a smaller surface energy balance weight coefficient The error caused by constrained energy balance. In the process of machine learning, through continuous training sample data, the number of neural network layers, training times, number of processed samples, and surface energy balance weight coefficient of the minimum loss function are obtained. , and the corresponding parameters for estimating sensible heat, latent heat, and soil heat flux, that is, the functions in formula (1), formula (2), and formula (3) 、 and The corresponding parameters.

[0073] Finally, the target area's daily continuous surface temperature data, net radiation data, air temperature data, vegetation cover data, and soil moisture data are substituted into the integrated surface water and heat flux estimation model. Through the functional relationship learned by the integrated surface water and heat flux estimation model, the daily variation information of the sensible heat, latent heat, and soil heat flux in the target area can be calculated.

[0074] Figure 3 This is a schematic diagram of the estimation results of sensible heat, latent heat and soil heat flux based on the integrated surface water heat flux estimation model provided by the present invention. Figure 3 As shown in the figure, the present invention uses the continuous data of surface temperature, net radiation, air temperature, vegetation cover and soil moisture obtained by process model simulation, and obtains the estimation results of sensible heat, latent heat and soil heat flux through the integrated estimation model of surface water heat flux. The error between the estimation results and the measured data is within The following is superior to the surface water heat flux estimated by the currently commonly used single variable method, and the estimation results of the present invention can well capture the intraday variation of the surface water heat flux.

[0075] The present invention addresses the problems of existing integrated surface heat flux estimation methods that use single-variable estimation, have complex models, multiple input parameters, require impedance calculation, and have high estimation uncertainty. By utilizing high-frequency observation information from geostationary satellites, simplifying the parameterization process of sensible heat, latent heat, and soil heat fluxes, and based on the physical constraints of the surface energy balance, the integrated surface heat flux estimation is transformed into solving a mathematical equation. Unknown parameters are acquired through machine learning methods, and surface temperature, air temperature, net radiation, vegetation index, and soil moisture are used as input data to simultaneously estimate the intraday variation of heat flux. By utilizing high-frequency observation information from geostationary satellites and using fewer input variables, the present invention solves the impedance calculation problem that relies on many parameter inputs in existing surface heat flux estimation processes. Furthermore, impedance calculation is not required during surface heat flux estimation, and input variables are relatively few. Unlike existing single-variable surface heat flux estimation methods, the present invention achieves simultaneous estimation of sensible heat, latent heat, and soil heat fluxes, avoiding error propagation. While accurately estimating sensible heat, latent heat, and soil heat fluxes, all three still adhere to energy balance. Moreover, unlike existing surface water heat flux estimation which mainly focuses on the transit time of polar-orbiting satellites or daily-scale water heat flux estimation, the present invention provides intraday variation information of surface water heat flux based on geostationary satellites, which can meet the research on the variation law of surface water heat flux in large areas.

[0076] The surface water heat flux integrated estimation system provided by the present invention is described below. The surface water heat flux integrated estimation system described below and the surface water heat flux integrated estimation method described above can be referred to each other.

[0077] Figure 4The schematic diagram of the structure of the integrated surface water heat flux estimation system provided by the present invention is as follows: Figure 4 As shown, the present invention provides a surface water heat flux integrated estimation system, including a data processing module 401 and a flux estimation module 402, wherein the data processing module 401 is used to construct target surface environment key parameters corresponding to the target area based on target surface temperature data, target net radiation data, target air temperature data, target vegetation cover data and target soil moisture data of the target area; the flux estimation module 402 is used to input the target surface environment key parameters into the surface water heat flux integrated estimation model to obtain the target surface water heat flux estimation value corresponding to the target area on the intraday time scale output by the surface water heat flux integrated estimation model, wherein the target surface water heat flux estimation value includes a sensible heat flux estimation value, a latent heat flux estimation value and a soil heat flux estimation value; the surface water heat flux integrated estimation model is obtained by training a physical information neural network machine learning model based on sample surface environment key parameters and sample surface water heat flux observation data corresponding to the sample surface environment key parameters.

[0078] The integrated surface water and heat flux estimation system provided by the present invention constructs key surface environmental parameters by integrating multi-source data such as surface temperature, net radiation, air temperature, vegetation cover and soil moisture in the target area. The key surface environmental parameters are then input into an integrated water and heat flux estimation model trained with sample surface environmental parameters and synchronously observed water and heat flux data, thereby outputting estimated values ​​of sensible heat, latent heat and soil heat flux on a daily time scale, significantly improving the accuracy of water and heat flux estimation under complex surface conditions.

[0079] The system provided in the embodiment of the present invention is used to execute the above-mentioned method embodiments. Please refer to the above-mentioned embodiments for the specific process and detailed content, which will not be repeated here.

[0080] Figure 5 A schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 5As shown, the electronic device may include: a processor (Processor) 501, a communication interface (Communications Interface) 502, a memory (Memory) 503 and a communication bus 504, wherein the processor 501, the communication interface 502, and the memory 503 communicate with each other through the communication bus 504. The processor 501 can call the logic instructions in the memory 503 to execute the integrated surface water heat flux estimation method, which includes: constructing the target surface environment key parameters corresponding to the target area based on the target surface temperature data, target net radiation data, target air temperature data, target vegetation cover data and target soil moisture data of the target area; inputting the target surface environment key parameters into the surface water heat flux integrated estimation model to obtain the target surface water heat flux estimation value corresponding to the target area on the intraday time scale output by the surface water heat flux integrated estimation model, wherein the target surface water heat flux estimation value includes the sensible heat flux estimation value, the latent heat flux estimation value and the soil heat flux estimation value; the surface water heat flux integrated estimation model is obtained by training a physical information neural network machine learning model based on the sample surface environment key parameters and the sample surface water heat flux observation data corresponding to the sample surface environment key parameters.

[0081] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0082] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0083] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A surface water heat flux integrated estimation method, characterized in that: include: According to the target surface temperature data, target net radiation data, target air temperature data, target vegetation coverage data and target soil moisture data of the target area, the target surface environment key parameters corresponding to the target area are constructed; The target surface environment key parameters are input into the surface water heat flux integrated estimation model to obtain the target surface water heat flux estimation value corresponding to the target area on the daily time scale output by the surface water heat flux integrated estimation model, wherein the target surface water heat flux estimation value includes the sensible heat flux estimation value, the latent heat flux estimation value and the soil heat flux estimation value; the surface water heat flux integrated estimation model is obtained by training a physical information neural network machine learning model based on the sample surface environment key parameters and the sample surface water heat flux observation data corresponding to the sample surface environment key parameters.

2. The surface water heat flux integrated estimation method according to claim 1, characterized in that: The surface water and heat flux integrated estimation model is trained through the following steps: Obtain sample surface temperature data and sample net radiation data corresponding to the intraday time scale of the sample area; Obtain sample temperature data corresponding to the intraday time scale of the sample area; Obtaining sample vegetation coverage data and sample soil moisture data corresponding to the intraday time scale of the sample area; Performing time resolution conversion processing on the sample surface temperature data, the sample net radiation data, the sample air temperature data, the sample vegetation cover data, and the sample soil moisture data to obtain sample surface temperature data, sample net radiation data, sample air temperature data, sample vegetation cover data, and sample soil moisture data with the same time resolution; and constructing key parameters of the sample surface environment based on the sample surface temperature data, sample net radiation data, sample air temperature data, sample vegetation cover data, and sample soil moisture data with the same time resolution; Based on the ground flux station observation data, obtaining sample surface water heat flux observation data of the sample area at the intraday time scale, wherein the sample surface water heat flux observation data includes sensible heat flux observation value, latent heat flux observation value and soil heat flux observation value; Constructing surface water heat flux labels corresponding to the sample surface environment key parameters based on the sample surface water heat flux observation data, and constructing a training sample set based on the sample surface environment key parameters marked with the surface water heat flux labels; Based on the training sample set, the physical information neural network machine learning model is trained, and after determining that the training result satisfies the preset data loss function, the surface water heat flux integrated estimation model is obtained, wherein the preset data loss function is based on the error between the surface water heat flux prediction value and the sample surface water heat flux observation data, and the surface energy balance equation.

3. The integrated surface water heat flux estimation method according to claim 2, characterized in that: The preset data loss function is specifically: ； in, represents the preset data loss function, N represents the total number of samples, Indicates the samples, represents the sample surface temperature data, represents the sample temperature data, represents the sample soil moisture data, represents the sample vegetation coverage data, represents the sample net radiation data, represents the observed value of the sensible heat flux, represents the predicted value of sensible heat flux, represents the predicted value of latent heat flux, represents the predicted soil heat flux, represents the surface energy balance weight coefficient, represents the latent heat flux observation value, represents the soil heat flux observation value.

4. The integrated surface water heat flux estimation method according to claim 2, characterized in that: Before performing time resolution conversion processing on the sample surface temperature data, the sample net radiation data, the sample air temperature data, the sample vegetation cover data, and the sample soil moisture data to obtain the sample surface temperature data, the sample net radiation data, the sample air temperature data, the sample vegetation cover data, and the sample soil moisture data with the same time resolution, the method further includes: The sample surface temperature data, the sample net radiation data, the sample air temperature data, the sample vegetation cover data and the sample soil moisture data are subjected to data preprocessing to obtain the sample surface temperature data, the sample net radiation data, the sample air temperature data, the sample vegetation cover data and the sample soil moisture data after data preprocessing, wherein the data preprocessing includes at least missing data filling processing and invalid value removal processing.

5. The integrated surface water heat flux estimation method according to claim 2, characterized in that: The sample surface temperature data and the sample net radiation data are obtained based on geostationary satellites; the sample air temperature data are obtained based on atmospheric reanalysis data; and the sample vegetation cover data and the sample soil moisture data are obtained based on polar-orbiting satellites.

6. The integrated surface water heat flux estimation method according to claim 1, characterized in that: After inputting the target surface environment key parameters into the surface water heat flux integrated estimation model to obtain the target surface water heat flux estimation value corresponding to the target area on a daily time scale output by the surface water heat flux integrated estimation model, the method further includes: Get preset time scale information; Based on the preset time scale information, the target surface water heat flux estimation value is cumulatively averaged to obtain the surface water heat flux estimation values ​​corresponding to different time scales.

7. A surface water heat flux integrated estimation system, characterized in that: include: A data processing module is used to construct target surface environment key parameters corresponding to the target area based on target surface temperature data, target net radiation data, target air temperature data, target vegetation coverage data and target soil moisture data of the target area; A flux estimation module is used to input the target surface environment key parameters into the surface water heat flux integrated estimation model to obtain the target surface water heat flux estimation value corresponding to the target area on the daily time scale output by the surface water heat flux integrated estimation model, wherein the target surface water heat flux estimation value includes the sensible heat flux estimation value, the latent heat flux estimation value and the soil heat flux estimation value; the surface water heat flux integrated estimation model is obtained by training a physical information neural network machine learning model based on the sample surface environment key parameters and the sample surface water heat flux observation data corresponding to the sample surface environment key parameters.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the integrated surface water heat flux estimation method according to any one of claims 1 to 6 is implemented.

Images