Distributed hydrological forecasting method and device, computer equipment and medium

Abstract

To provide a distributed hydrological forecasting method and device, computer equipment and a medium that simulate runoff data by comprehensively considering climate data and atmosphere boundary surface data of a target area, correct the runoff data obtained through simulation by utilizing the human activity data, and improve the accuracy of the simulated runoff data.SOLUTION: A method includes the steps of: acquiring various kinds of pieces of human activity data in a target area, and first climate data and atmosphere boundary surface data of the target area in a climate scene mode; inputting the first climate data and the atmosphere boundary surface data into a pre-constructed hydrological model to obtain first simulated runoff data corresponding to the climate scene mode; constructing a correction model corresponding to each piece of human activity data according to each piece of human activity data; and correcting the first simulated runoff data through each correction model to obtain second simulated runoff data corresponding to each human activity data.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to the technical field of hydrological information processing, and particularly relates to a distributed hydrological forecasting method, apparatus, computer device, and medium.

Background Art

[0002] Runoff is one of the exogenous forces that form the geomorphology and is involved in the geochemical processes of the earth's crust. It also affects soil development, plant growth, the formation of lakes and swamps, etc. The runoff volume is an important condition for the supply of industrial and agricultural water in a region and is a limiting factor for the scale of regional development. Therefore, in the construction of water conservancy facilities, measurement, calculation, forecasting, etc. of runoff are important tasks.

[0003] Currently, when simulating and forecasting runoff in a changing future environment, only the impact of climate change on the runoff effect is often considered, or it is often combined with the impact on the runoff effect of a single or hypothetical land use type change scenario based on historical trajectories. However, since the change in runoff is affected by multiple factors, considering only climate change and changes in land use types will reduce the accuracy of runoff simulation.

Summary of the Invention

Problems to be Solved by the Invention

[0004] In order to improve the accuracy of runoff forecasting, the present invention proposes a distributed hydrological forecasting method, apparatus, computer device, and medium.

Means for Solving the Problems

[0005] In a first aspect, the present invention obtaining a plurality of types of human activity data within a target area, and first climate data and atmospheric boundary data of the target area in a climate scenario mode; inputting the first climate data and the atmospheric boundary data into a pre-constructed hydrological model to obtain first simulation runoff data corresponding to the climate scenario mode; Based on each human activity data, constructing a correction model corresponding to each human activity data; correcting the first simulation outflow data by each correction model to obtain second simulation outflow data corresponding to each human activity data, and providing a distributed hydrological forecasting method.

[0006] In the prior art, when simulating and forecasting outflow data, only the influence of the outflow effect caused by climate change and single or hypothetical land use type change is considered. However, since the outflow data is affected by comprehensive influences of climate data, atmospheric boundary data, and human activities, by the above method, while simulating the outflow data by comprehensively considering the climate data and atmospheric boundary data of the target area, and correcting the simulated outflow data with human activity data, the accuracy of the outflow forecast is improved.

[0007] In any embodiment, the atmospheric boundary data includes the leaf area index values of each vegetation type, and the step of obtaining the leaf area index values of each vegetation type includes: obtaining the carbon dioxide concentration in the atmosphere and the geographical location of the target area; inputting the first climate data, the carbon dioxide concentration in the atmosphere, and the geographical location into a pre-constructed leaf area index prediction model to obtain the leaf area index values of each vegetation type.

[0008] In any embodiment, the step of constructing the leaf area index prediction model includes: obtaining the first historical leaf area index values of each vegetation type at the first time resolution of each grid in the target area; obtaining the first historical climate data and the historical carbon dioxide concentration in the atmosphere of the target area; training an initial leaf area index prediction model based on the first historical climate data, the historical carbon dioxide concentration in the atmosphere, the geographical location, and the first historical leaf area index values of each vegetation type to obtain the leaf area index prediction model.

[0009] In any embodiment, the step of obtaining the first historical leaf area index value of each vegetation type at the first time resolution of each grid in the target area is obtaining the total value of the historical leaf area index at the second time resolution of each grid in the target area; obtaining the percentage of the land use type of each vegetation type in each grid; calculating the second historical leaf area index value of each vegetation type in each grid based on the percentage of each land use type and the total value of each historical leaf area index; using the cubic spline interpolation method to calculate each second historical leaf area index value daily to obtain the first historical leaf area index value of each grid at the first time resolution.

[0010] In any embodiment, the step of obtaining the first historical climate data of the target area is obtaining the first historical climate data corresponding to a plurality of climate elements in the target area; calculating the correlation coefficient between the first historical climate data corresponding to each climate element and the first historical leaf area index value; screening the climate elements based on each correlation coefficient to obtain the screened climate elements; determining the first historical climate data of the target area from the first historical climate data corresponding to the screened climate elements.

[0011] In any embodiment, the atmospheric boundary data further includes land use type data, and the step of obtaining the land use type data is obtaining the land use change factor of the target area in the climate scenario mode; inputting the land use change factor into a pre-constructed future land use simulation model to obtain the land use type data.

[0012] In any embodiment, the future land use simulation model includes a system dynamics simulation model and a cellular automaton module based on an adaptive inertia competition mechanism. The step of inputting land use change factors into a pre-constructed future land use simulation model to obtain land use type data includes: inputting land use change factors into the system dynamics simulation model to obtain the land use type land demand; and predicting land use type data based on the land use change factors, the land use type land demand, and the cellular automaton module based on the adaptive inertia competition mechanism.

[0013] In any embodiment, the step of predicting land use type data based on the land use change factors, the land use type land demand, and the cellular automaton module based on the adaptive inertia competition mechanism includes: inputting land use change factors into an artificial neural network model to predict the land use suitability probability; calculating the neighborhood effect, the adaptive inertia coefficient, and the conversion cost corresponding to each land use type in the target area; calculating the occurrence probability of each land use type based on the land use suitability probability, the neighborhood effect, the adaptive inertia coefficient, and the conversion cost; predicting land use type data based on each occurrence probability and the roulette selection mechanism.

[0014] In any embodiment, the step of obtaining the first climate data includes: obtaining the second climate data of the target area in the climate scenario mode and the second historical climate data corresponding to the second climate data; calculating the deviation between the second climate data and the second historical climate data; obtaining the third climate data of the target area in the climate scenario mode; correcting the third climate data according to the deviation to obtain the first climate data.

[0015] In any embodiment, the step of obtaining the second climate data includes obtaining the fourth climate data of the target area in the climate scene mode, and interpolating the fourth climate data into a preset spatial resolution grid to obtain the second climate data.

[0016] In any embodiment, the hydrological model is a variable infiltration capacity model, and the step of constructing the variable infiltration capacity model includes obtaining training data for the variable infiltration capacity model, including the second historical climate data, historical atmospheric boundary data, soil terrain data, and the first historical outflow data, constructing an initial variable infiltration capacity model based on the second historical climate data, historical atmospheric boundary data, and soil terrain data in the training data, inputting the second historical climate data, historical atmospheric boundary data, and soil terrain data in the training data into the initial variable infiltration capacity model to obtain the third simulation outflow data, and calibrating the parameters in the initial variable infiltration capacity model based on the third simulation outflow data and the first historical outflow data in the training data to obtain the variable infiltration capacity model.

[0017] In any embodiment, the step of calibrating the parameters in the initial variable infiltration capacity model based on the third simulation outflow data and the first historical outflow data in the training data to obtain the variable infiltration capacity model includes calculating the correlation degree between the third simulation outflow data and the first historical outflow data in the training data, calibrating the parameters in the initial variable infiltration capacity model according to the correlation degree to obtain the calibrated variable infiltration capacity model, and obtaining test data including the second historical climate data, historical atmospheric boundary data, soil terrain data, and the first historical outflow data. Based on the test data, testing the parameters in the variable permeability model after calibration to obtain a variable permeability model, and including the step of obtaining a variable permeability model.

[0018] In any embodiment, the correlation degree includes at least one of the relative error, the Nash efficiency coefficient, and the Kling-Gupta efficiency coefficient.

[0019] In any embodiment, each piece of human activity data is human activity data within different periods, and the step of obtaining each piece of human activity data includes: obtaining second historical outflow data within a preset time period; determining a plurality of sudden change times of the second historical outflow data; dividing the preset time period into a plurality of periods according to each sudden change time; and determining human activity data corresponding to each period.

[0020] In any embodiment, the correction model is a long short-term memory network model, and the step of constructing each long short-term memory network model includes: dividing the second historical outflow data into third historical outflow data of a plurality of periods according to each sudden change time; and constructing each long short-term memory network model based on each third historical outflow data and the first simulation outflow data corresponding to each third historical outflow data.

[0021] In any embodiment, the sudden change time of the second historical outflow data is determined by any one of the M-K sudden change test method, the sliding t-test method, and the Pettitt test method.

[0022] In the second aspect, the present invention further includes: an acquisition module for acquiring a plurality of types of human activity data within a target area, first climate data of the target area in a climate scene mode, and atmospheric boundary data; A simulation module that inputs the first climate data and the atmospheric boundary data into a pre-constructed hydrological model to obtain first simulation outflow data corresponding to the climate scenario mode, A construction module that constructs a correction model corresponding to each human activity data based on each human activity data, A correction module that corrects the first simulation outflow data by each correction model to obtain second simulation outflow data corresponding to each human activity data, and provides a distributed water forecast device including the correction module.

[0023] In the prior art, when performing simulation forecasting of outflow data, only the influence of the outflow effect due to climate change and single or assumed land use type change is considered. However, since the outflow data is affected by the comprehensive influence of climate data, atmospheric boundary data, and human activities, the above device comprehensively considers the climate data and atmospheric boundary data of the target area to simulate the outflow data, and improves the accuracy of the outflow forecast by correcting the simulated outflow data with human activity data.

[0024] In a third aspect, the present invention further includes a memory and a processor, the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the computer instructions to execute the steps of the distributed hydrological forecasting method described in any one of the first aspect or the embodiments of the first aspect, and provides a computer device.

[0025] In a fourth aspect, the present invention further provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, it realizes the steps of the distributed hydrological forecasting method described in any one of the first aspect or the embodiments of the first aspect.

Brief Description of the Drawings

[0026] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings necessary for the description of the specific embodiments or the prior art. However, the drawings in the following description are only some embodiments of the present invention, and it is obvious to those skilled in the art that based on these drawings, other drawings can be obtained without creative efforts.

Figure 1

Figure 2

Figure 3

Figure 4

Embodiments for Carrying out the Invention

[0027] Hereinafter, with reference to the drawings, the technical solutions of the present invention will be clearly and completely described. However, it is obvious that the described embodiments are only a part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments that can be obtained by those skilled in the art without creative efforts belong to the protection scope of the present invention.

[0028] Furthermore, the technical features according to the respective embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.

[0029] The present invention proposes a distributed hydrological forecasting method, device, computer device, and medium in order to improve the accuracy of simulated outflow data.

[0030] FIG. 1 is a flowchart of a distributed hydrological forecasting method according to an exemplary embodiment. As shown in FIG. 1, the distributed hydrological forecasting method includes the following steps S101 to S104.

[0031] Step S101: Obtain multiple types of human activity data within the target area, the first climate data of the target area in the climate scene mode, and the atmospheric boundary data.

[0032] In any embodiment, the human activity data includes, but is not limited to, the usage amount of industrial water, the usage amount of agricultural water, the usage amount of domestic water, the construction of water conservancy projects, afforestation, etc., and there is no particular limitation here.

[0033] In any embodiment, the climate data includes, but is not limited to, precipitation, temperature, humidity, wind speed, etc., and there is no particular limitation here.

[0034] In any embodiment, the atmospheric boundary includes important elements such as land use type and vegetation growth, and is an important link connecting ecological elements such as soil, atmosphere, and water. It is also affected by climate change and human activities, and affects the outflow data through influencing hydrological processes such as infiltration, blocking, and evaporation. In the embodiments of the present invention, the atmospheric boundary data includes the leaf area index value of each vegetation type and the land use type data.

[0035] In any embodiment, in different climate scene modes, the climate data and the atmospheric boundary data are different.

[0036] In any embodiment, the climate scene mode is obtained from the earth climate mode data of the 6th Coupled Model Intercomparison Project (CMIP6 project). The CMIP6 project considered complex biogeophysical processes and chemical processes in the test design process, and also significantly improved the resolution of the atmosphere-ocean model. According to the mode participation information provided by the CMIP6 project, approximately 50 modes are involved in the CMIP6 mode comparison plan, and each mode can provide earth meteorological prediction data from the historical period to 2100 and beyond. The earth climate modes in the CMIP6 project include multiple representative scenes as shown in Table 1.

[0037] Table 1 Representative Scenarios in the CMIP6 Project JPEG2025077965000002.jpg118170

[0038] Step S102: Input the first climate data and atmospheric boundary data into a pre-constructed hydrological model to obtain first simulation outflow data corresponding to the climate scenario mode.

[0039] In any embodiment, the hydrological model may adopt a Variable Infiltration Capacity (VIC) model. The VIC model is a large-scale hydrological model. The VIC model performs simulation calculations by adopting a water balance mode or an energy balance mode. The main processes include evapotranspiration calculation, soil water content calculation, outflow calculation, and confluence calculation. Also, the effects of frozen soil and snowmelt can be considered.

[0040] Step S103: Based on each human activity data, construct a correction model corresponding to each human activity data.

[0041] In any embodiment, the correction model is trained using the model simulation outflow data and the historical outflow data of the corresponding time period. In the process of constructing the correction model, since the influence of human activity data in different time periods on the outflow data is different, a plurality of correction models are constructed based on the human activity data in different time periods. That is, when the human activity data is different, the selected correction model is different.

[0042] In any embodiment, the correction model may be a Long Short-Term Memory (LSTM) network model.

[0043] Step S104: Correct the first simulation outflow data by each correction model to obtain second simulation outflow data corresponding to each human activity data.

[0044] In the prior art, when performing simulation forecasting of runoff data, only the impacts of climate change and the runoff effects caused by single or hypothetical land use type changes are considered. However, since runoff data is affected by comprehensive influences of climate data, atmospheric boundary data, and human activities, the runoff data of the target area is simulated by comprehensively considering the climate data and atmospheric boundary data of the target area by the above method, and at the same time, the accuracy of runoff forecasting is improved by using a long short-term memory network model considering human activities to correct the simulated runoff data.

[0045] In one example, the atmospheric boundary data includes the leaf area index value (LAI: Leaf Area Index) of each vegetation type, and the LAI value represents the growth changes of vegetation such as when the plant turns green or when early seasonal changes are observed. The LAI value is the most important vegetation parameter for hydrological simulation and is directly affected by climate change. What can be obtained in the related art is the total LAI value of each grid in the target area, and the LAI value of each vegetation type in each grid cannot be obtained. When the vegetation types are different, the impacts on runoff data are different. Obtaining the LAI value of each vegetation type is beneficial for more accurate runoff forecasting. Therefore, in the embodiments of the present invention, in the above step S101, the total value of the leaf area index is separated as follows to obtain the leaf area index value of each vegetation type.

[0046] First, the carbon dioxide concentration (CO 2 ) in the atmosphere and the geographical location of the target area are obtained. Exemplarily, the geographical location includes, but is not limited to, internal longitude, latitude, and elevation, etc.

[0047] Next, input the first climate data, the atmospheric carbon dioxide concentration, and the geographical location into a pre-constructed leaf area index prediction model to obtain the leaf area index values for each vegetation type. Exemplarily, the leaf area index prediction model can be obtained by a random forest model. Predicting the leaf area index values for each vegetation type for each grid based on the first climate data, the atmospheric carbon dioxide concentration, the geographical location, and the random forest model may be expressed as follows. JPEG2025077965000003.jpg13170

[0048] Here, LAI sim represents the leaf area index values for each vegetation type obtained by simulation, F RF represents a random forest model corrected and verified using historical period data, M represents climate data such as monthly precipitation and temperature, CO 2 represents the CO 2 content in the atmosphere for the corresponding year, and location represents the longitude, latitude, and altitude of the preset grid center point.

[0049] In one example, the leaf area index prediction model is constructed in the following steps.

[0050] Step a1: Obtain the first historical leaf area index values for each vegetation type at the first time resolution of each grid within the target area. Exemplarily, the vegetation type may be cultivated land, forest land, grassland, etc., and there is no particular limitation here.

[0051] Step a2: Obtain the first historical climate data and the historical atmospheric carbon dioxide concentration of the target area.

[0052] Step a3: Based on the first historical climate data, the historical atmospheric carbon dioxide concentration, the geographical location, and the first historical leaf area index values of each vegetation type, train an initial leaf area index prediction model to obtain a leaf area index prediction model. Exemplarily, the initial leaf area index prediction model may be a random forest model. Further, after constructing the leaf area index prediction model, this model may be tested using other historical data and adjusted to further improve the prediction accuracy of the leaf area index values of each vegetation type.

[0053] In the above embodiment, using the first historical climate data, the historical atmospheric carbon dioxide concentration, the geographical location, and the LAI value, a leaf area index prediction model combining climate - CO 2 - geographical location is created to clarify the relationship between climate data, CO 2 and geographical location and the LAI value of each vegetation type. Further, the historical leaf area index values of each vegetation type may be traced back using this leaf area index prediction model.

[0054] In any embodiment, in step a1 above, the first historical leaf area index values of each vegetation type at the first time resolution of each grid in the target area are obtained as follows.

[0055] First, obtain the total value of the historical leaf area index at the second time resolution of each grid in the target area.

[0056] Next, obtain the percentage of the land use type of each vegetation type in each grid. Exemplarily, the land use percentage may be determined from land use data by the spatial analysis function of ArcGIS software.

[0057] Furthermore, based on the percentage of each land use type and the total value of each historical leaf area index, calculate the second historical leaf area index value of each vegetation type in each grid.

[0058] Finally, using the cubic spline interpolation method, each second historical leaf area index value is calculated daily to obtain each first historical leaf area index value at the first-hour resolution of each grid. Since the time resolution of the original total LAI value (obtainable from GIMMS LAI3g or GLASS LAI data) is 15 days / 8 days, and the VIC hydrological model needs to input the LAI value daily, the daily LAI value of each vegetation type during the historical period, that is, the first historical leaf area index, is obtained by the cubic spline interpolation method.

[0059] As shown in FIG. 2, the LAI value of the (1,1) grid is L11, and by the method according to the embodiment of the present invention, the total LAI value of the (1,1) grid is the x within the (1,1) grid 1 , x 2 , …, x N and separated into the LAI values of each vegetation type (for example, cultivated land, forest land, grassland). The calculation formula is as follows. JPEG2025077965000004.jpg47170

[0060] Here, X i is the leaf area index value of vegetation type i obtained within a preset grid, M is the total value of the leaf area index, n = 1, 2, 3, … N, representing N different types of vegetation, and Fraction i is the percentage of the preset grid occupied by the i-th vegetation type. n = N + 1 represents bare soil, and the sum of the percentages of the N + 1 land use types within one grid is 1. In the embodiment of the present invention, a reasonable threshold is set for Fraction i . For example, when Fraction i is less than 0.05, Fraction i is set to 0. This method can avoid the occurrence of abnormal values. The percentages occupied by other land use types must be adjusted according to the percentage of that grid to ensure that the sum of the percentages of all land use types in the specified grid is 1.

[0061] Thus, for each grid, a linear equation with N elements can be created. Around each preset simulation unit, a system of linear equations with N elements is constructed using the linear equations with N elements created for all the preset grids within a preset neighboring range (i.e., within a certain range around it, such as a 5×5 grid). By solving the system of linear equations with N elements using the least squares method, the leaf area index value of each vegetation type within each preset simulation unit can be obtained.

[0062] In one example, in step a2 above, the first historical climate data of the target area is obtained as follows.

[0063] First, the first historical climate data corresponding to a plurality of climate elements in the target area is obtained. Exemplarily, the climate elements may be temperature, precipitation, humidity, etc.

[0064] Next, the correlation coefficient between the first historical climate data corresponding to each climate element and the first historical leaf area index value is calculated.

[0065] Furthermore, the climate elements are screened based on each correlation coefficient to obtain the screened climate elements.

[0066] Finally, the first historical climate data of the target area is determined from the first historical climate data corresponding to the screened climate elements. Exemplarily, the climate elements with a correlation coefficient greater than a preset value may be screened to obtain the first historical climate data.

[0067] In one example, the atmospheric boundary data further includes land use type data. In step S101 above, the land use type data is obtained as follows.

[0068] First, the land use change factors of the target area in the climate scene mode are obtained. Exemplarily, considering elements such as the actual topographic and geomorphic conditions of the basin and the development of urban areas, information such as elevation, slope, population distribution, GDP distribution, and climate change is selected as land use change factors.

[0069] After that, the land use change factors are input into a pre-established constructed future land use simulation model (FLUS: Future Land-Use Simulation) to obtain land use type data.

[0070] In an embodiment of the present invention, after the construction of the future land use simulation model is completed, it is necessary to test the simulation effect of the future land use simulation model using the Kappa coefficient. Using the land use type data of the Yangtze River Basin in 2010 and 2015 as initial data, and temperature, precipitation, DEM, slope length, gradient, GDP, population, distance from the city center, distance from the county center, distance from the railway, and distance from the road as land use change factors, simulate the land use type data of the Yangtze River Basin in 2020, compare it with the actual value, and calculate the Kappa coefficient. The calculation formula of the Kappa coefficient is as follows. JPEG2025077965000005.jpg22160

[0071] Here, P 0 is the proportion of grids correctly simulated, P c is the proportion of grids correctly simulated in a random situation, and 1 is the proportion of grids correctly simulated in an ideal situation. Generally, when Kappa < 0.4, it indicates a low similarity; when 0.4 ≤ Kappa ≤ 0.75, it indicates a general similarity; when Kappa > 0.75, it indicates a significant consistency and a good simulation effect.

[0072] In one example, the FLUS model includes a system dynamics simulation model (SD: Systems Dynamics) and a cellular automaton module based on an adaptive inertia competition mechanism, and obtains land use type data in the following steps.

[0073] Step b1: Input the land use change factors into the system dynamics simulation model to obtain the land use type land demand.

[0074] In the embodiment of the present invention, using the social and economic data and land use types of each urban area in the Yangtze River Basin in 2010 and 2015, an empirical formula of the interaction between population, social economy, and meteorological elements is applied to construct an SD model of the Yangtze River Basin. Based on the changes in population, social economy, and meteorological elements in the study area in 2030 under five different climate scenario modes, simulations are carried out to predict the land demand of each land use type in five different climate scenario modes in 2030.

[0075] Step b2: Predict the land use type data based on the land use change factors, the land use type land demand, and the cellular automaton module based on the adaptive inertia competition mechanism.

[0076] In any embodiment, the land use type data is predicted as follows.

[0077] First, input the land use change factors into the artificial neural network model to predict the land use suitability probability.

[0078] Next, calculate the neighborhood effect, adaptive inertia coefficient, and conversion cost corresponding to each land use type in the target area.

[0079] Furthermore, calculate the occurrence probability of each land use type based on the land use suitability probability, neighborhood effect, adaptive inertia coefficient, and conversion cost.

[0080] Finally, predict the land use type data based on each occurrence probability and the roulette selection mechanism.

[0081] In the embodiment of the present invention, a three-layer BP neural network model is used to obtain the land use suitability probability. The number of neurons in each layer of the neural network is set based on the selected spatial variables, and random sampling is performed according to the land use change factors. Then, based on the samples, an artificial neural network algorithm (ANN: Artificial Neural Network) training is carried out to obtain the cell development probability. ANN is a multi-layer feed-forward neural network, and its calculation process includes the training and prediction stages. That is, it is as follows. JPEG2025077965000006.jpg39170

[0082] Here, net j (p, t) represents the signal received by the j-th hidden layer grid p at time t, and X i (p, t) is the i-th variable corresponding to the i-th input layer grid p and time t, and w i,j is the weight between the input layer and the hidden layer, and sp(p, k, t) represents the suitability probability that the k-th land use type appears at grid p and time t. W j,k is the weight between the hidden layer and the output layer, and Sigmoid(net j (p, t)) is the correlation function from the hidden layer to the output layer. For sp(p, k, t) output from the BP-ANN, the sum of the land use suitability probabilities of each land use type at grid p and time t is always 1. That is, it is as follows. JPEG2025077965000007.jpg21167

[0083] In the embodiment of the present invention, based on the land use change factors, the land use type land demand in a specific future year (2030), and the cellular automaton module (CA) based on the adaptive inertia competition mechanism, the land use type data (spatial distribution of land use types) in 2030 is predicted.

[0084] JPEG2025077965000008.jpg44170

[0085] JPEG2025077965000009.jpg Represents the total number of grid units occupied by land use type k within the N×N window at the last iteration time t - 1, where w k is the variable weight between different land use types, because different land use types have different neighborhood effects. w k can be obtained based on expert knowledge and model tests, or the default values of the FLUS model can be directly adopted.

[0086] In the cellular automaton module based on the adaptive inertia competition mechanism, the adaptive inertia coefficient is defined according to the difference between the land demand and the allocated amount of each land use type, and the inheritance of the current land use type in each grid unit is automatically adjusted. The core idea of this adaptive inertia mechanism is that when the land demand of a specific land use type conflicts with its current quantity and development trend, the inertia coefficient is automatically adjusted to decelerate / accelerate it, reverse the trend, and shift the development trend of the land use type in the direction of its macro demand. For example, if more urban construction land is needed in the future plan, but the area of urban construction land decreased in the previous iteration process, the inertia coefficient is increased in the next iteration process to maintain the area of urban construction land and promote the shift from other land use types to urban construction land. The land use adaptive inertia coefficient is defined as follows. JPEG2025077965000010.jpg60170

[0087] JPEG2025077965000011.jpg29170

[0088] Conversion cost SC c→kis another factor that affects the dynamic change of land use types and represents the difficulty of converting from the current land use type c to the target land use type k. The value of the conversion cost varies in the range of [0, 1], indicating that the larger the value, the more difficult the conversion. The conversion cost can be determined by analyzing the historical land use type data in the research area and the experience of experts, or the default parameters of the FLUS model can also be adopted. The conversion cost reflects the inherent attributes of land use types and does not consider influencing factors such as technological progress and human activities, so the conversion cost does not change in the model.

[0089] In the embodiments of the present invention, based on the land use type compatibility probability, the neighborhood effect, the adaptation inertia coefficient, and the conversion cost, the comprehensive probability of the appearance of the land use type of each grid can be calculated. JPEG2025077965000012.jpg15170

[0090] JPEG2025077965000013.jpg62170

[0091] The land use type with the highest appearance probability of the land use type is the type that this grid preferentially converts to, but there is also a chance of conversion to land use types with low appearance probabilities of the land use type. To achieve this, the FLUS model uses a roulette selection mechanism to determine which land use type occupies the grid unit. The land use type that the grid converts to is proportional to the appearance probability of that land use type. For a specific grid unit p at the iteration time t, after calculating the appearance probability of the land use type of each grid, a roulette is constructed based on the appearance probabilities of all land use types. Each part of the roulette is represented by a land use type. The area of the sector is proportional to the appearance probability of each land use type. Then, a uniform distribution random number in the range of 0 to 1 is generated, and according to the sector corresponding to the random number, the land use type corresponding to the grid unit in this iteration is assigned. By this roulette selection mechanism, the land use type of this grid has a higher probability of being selected for land use types with higher appearance probabilities of the land use type.

[0092] In the embodiments of the present invention, taking the land use status in 2015 as the reference year, and combining with the land use demand of various land use types in 2030 in different climate scenario modes simulated by the SD model, meteorology, elevation (DEM), slope length, gradient, gross domestic product (GDP), population, distance from the city center, distance from the county center, distance from the railway, and distance from the road are used as land use change factors, and the spatial distribution of land use types is obtained by the simulation of the cellular automaton module (CA) based on the adaptive inertia competition mechanism.

[0093] In one example, the first climate data is the grid point data after correction by the station data. In step S101 above, the first climate data is obtained by the following steps.

[0094] Step c1: Obtain the second climate data of the target area in the climate scenario mode and the second historical climate data corresponding to the second climate data.

[0095] In any embodiment, the second historical climate data is obtained from the meteorological station data. Considering that there are problems such as unit differences and some measurement deficiencies in the actually measured meteorological station data, first, the meteorological station data is converted into standard units (for example, the unified standard unit of precipitation is mm, the unified standard unit of the maximum temperature is °C, the unified standard unit of the minimum temperature is °C, and the unified standard unit of wind speed is m / s), and it is necessary to exclude meteorological stations where the measurement-deficient time zone exceeds 10% of the total time zone. In the embodiments of the present invention, the second historical climate data includes precipitation data, the maximum temperature, the minimum temperature, and the wind speed near the ground.

[0096] In the embodiments of the present invention, the second climate data is the earth climate mode data in the CMIP6 project after interpolation processing.

[0097] In the embodiments of the present invention, considering that the Earth climate model data in the CMIP6 project is grid point data different from the meteorological station data, it is necessary to align the geographical positions of the CMIP6 Earth climate model data and the second historical climate data (meteorological station data). The specific process of obtaining the second climate data is as follows. First, obtain the fourth climate data of the target area in the climate scenario mode, that is, the CMIP6 Earth climate model data. Next, interpolate the fourth climate data onto a preset spatial resolution grid to obtain the second climate data. Exemplarily, each Earth climate model data (fourth climate data) with different resolutions is uniformly downscaled and interpolated onto an 1 / 8×1 / 8 grid to obtain the second climate data. At this time, the second historical climate data corresponding to the second climate data is also data interpolated onto the same spatial resolution grid.

[0098] Step c2: Calculate the deviation between the second climate data and the second historical climate data.

[0099] Step c3: Obtain the third climate data of the target area in different climate scenarios of the CMIP6 project. Similarly, the third climate data is climate data interpolated onto the same preset spatial resolution grid as the second climate data. That is, the third climate data, the second climate data, and the second historical climate data are on the same spatial resolution grid.

[0100] Step c4: Correct the third climate data according to the deviation to obtain the first climate data.

[0101] In any embodiment, the third climate data is corrected using a deviation correction method (EDCDF: Equidistant Cumulative Distribution Function). According to the relationship between the second climate data and the second historical climate data, correct the empirical distribution of the future time period of the climate data. The basic principle is that for a specific percentile, assuming that the difference (deviation) between the historical simulation value and the observed value is carried over to the future period, the adjustment function (Δx) does not change. This method may be expressed as follows. JPEG2025077965000014.jpg13170

[0102] JPEG2025077965000015.jpg70170

[0103] In an embodiment of the present invention, data from 1961 to 2003 is used as the training period, and data from 2004 to 2100 is used as the correction period (here, data from 2004 to 2014 is used as the verification period).

[0104] In one example, the hydrological model is a variable infiltration capacity model, and the variable infiltration capacity model is constructed as follows.

[0105] First, obtain the training data of the variable infiltration capacity model including the second historical climate data, historical atmospheric boundary data, soil topography data, and the first historical outflow data.

[0106] Next, based on the second historical climate data, historical atmospheric boundary data, and soil topography data in the training data, construct an initial variable infiltration capacity model. Here, the second historical climate data is climate data interpolated to a preset spatial resolution grid, the historical atmospheric boundary data is the percentage of each land use type statistically calculated in a preset spatial resolution grid, and the soil topography data refers to the soil type with the largest percentage inside a preset spatial resolution grid.

[0107] Next, input the second historical climate data, historical atmospheric boundary data, and soil topography data in the training data into the initial variable infiltration capacity model to obtain the third simulation outflow data.

[0108] Finally, based on the third simulation outflow data and the first historical outflow data in the training data, the parameters in the initial variable infiltration capacity model are calibrated to obtain a variable infiltration capacity model. In an embodiment of the present invention, after calibrating the parameters in the initial variable infiltration capacity model, it is also necessary to test the calibrated variable infiltration capacity model with test data to verify the availability of the model.

[0109] In an embodiment of the present invention, the parameters in the initial variable infiltration capacity model include the shape parameter (b) of the soil water storage capacity curve, the percentage (Ds) of the maximum speed of the basic outflow in the maximum speed when the basic outflow grows non-linearly, the maximum speed (Dm) of the basic outflow, the percentage (Ws) of the soil water content in the bottom soil layer when the non-linear basic outflow occurs in the maximum soil water content, and the depths (d1, d2, d3) of the three-layer soil.

[0110] In any embodiment, the parameters in the initial variable infiltration capacity model are calibrated as follows.

[0111] First, calculate the correlation degree between the third simulation outflow data and the first historical outflow data in the training data. The correlation degree includes at least one of the relative error, the Nash efficiency coefficient, and the Kling - Gupta efficiency coefficient.

[0112] JPEG2025077965000016.jpg43170

[0113] The Nash efficiency coefficient (NSE: Nash - Sutcliffe Efficiency coefficient) represents the degree of matching between the simulated historical outflow data and the average value of the measured historical outflow data within the corresponding time period. JPEG2025077965000017.jpg22166

[0114] JPEG2025077965000018.jpg26170

[0115] The Kling-Gupta Efficiency (KGE) is calculated as follows. JPEG2025077965000019.jpg98170

[0116] Here, γ, α, and β represent the linear correlation coefficient, relative variability, and deviation, respectively, between the simulated outflow data χ s and the observed historical outflow data χ o . μ s and μ o represent the mean values of the simulated outflow data χ s and the observed historical outflow data χ o , respectively, and σ s and σ o represent the standard deviations of the simulated outflow data χ s and the observed historical outflow data χ o , respectively. Cov so is the covariance between the simulated outflow data χ s and the observed historical outflow data χ o . The closer the KGE value is to 1, the better the simulation effect.

[0117] Next, according to the degree of correlation, the parameters in the initial variable permeability model are calibrated to obtain a variable permeability model. Exemplarily, according to the degree of correlation, the parameters can be manually adjusted by an empirical calibration method (i.e., the meaning of the parameters and the influence on the model simulation results), or an automatic parameter calibration method (such as the SCE-UA parameter automatic calibration method) can be used to perform automatic parameter adjustment.

[0118] Next, test data including the second historical climate data, historical atmospheric boundary data, soil topography data, and the first historical outflow data is obtained.

[0119] Finally, based on the test data, the parameters in the calibrated variable permeability model are tested to obtain a variable permeability model.

[0120] In an embodiment of the present invention, the first simulation outflow data obtained by VIC model simulation may be represented as follows. JPEG2025077965000020.jpg10170

[0121] Here, Q sim represents the first simulation outflow data obtained by simulation, F VIC represents the simulation process of the VIC model, P represents the precipitation per day required for the simulation of the VIC model, T max represents the maximum temperature per day required for the simulation of the VIC model, T min represents the minimum temperature per day required for the simulation of the VIC model, Wind represents the wind speed per day required for the simulation of the VIC model, Landuse represents the land use type data for the corresponding time period, LAI represents the LAI value per day required for the simulation of the VIC model, Veg represents other vegetation parameters other than the LAI value such as vegetation albedo. Since such data is not easily changed and not easily obtained, the default values of the vegetation parameter set of the VIC model are adopted. Soil represents the soil parameters for the corresponding time period, Basin represents the basin characteristic parameters for the corresponding time period such as basin elevation, area, and river network status, and Parameters represents the parameters obtained by adjusting the parameters using the historical outflow data and the simulation outflow data. Here, P, T max 、T min 、Wind, and LAI are daily data. Since the land use type data generally does not change suddenly on a daily basis, it is input annually. On the other hand, characteristic data such as Veg, Soil, and Basin do not change easily and can be regarded as fixed data.

[0122] In one example, considering that different human activity data result in different impacts on the outflow data, when training the correction model using different outflow data, the obtained correction models are also different. Therefore, different correction models are selected based on the human activity data to correct the first simulation outflow data.

[0123] In step S101 above, each human activity data is human activity data within different periods, and the step of obtaining each human activity data includes step d1 and step d2.

[0124] Step d1: Obtain the second historical outflow data within a preset time period.

[0125] Step d2: Determine multiple mutation times of the second historical outflow data. Exemplarily, the mutation times of the second historical outflow data may be determined by any one of the Mann-Kendall mutation test method, the sliding t-test method, and the Pettitt test method. Also, a splitting point can be artificially set to split the historical outflow data into multiple segments. For example, if 1970, 1980, 1990, 2000, and 2010 are set, the outflow sequence can be split into before 1970, 1970 - 1979, 1980 - 1989, 1990 - 1999, 2000 - 2010, and after 2010.

[0126] In any embodiment, the specific procedure of the Mann-Kendall mutation test method is as follows.

[0127] Let the original time series be x 1 、x 2 、…x n and s k be the cumulative number where the i-th sample x i is greater than x j (1 ≤ j ≤ i), and define the statistic. JPEG2025077965000021.jpg48170

[0128] Under the assumption that the original sequence is randomly independent, etc., the mean E(s k of sk ) and the dispersion V ar (s k ) are as follows respectively. JPEG2025077965000022.jpg58170

[0129] For s in the above formula k When standardized, the following formula is obtained. JPEG2025077965000023.jpg35170

[0130] UF k is a sequence of statistical quantities, constitutes one UF curve, and can grasp whether there is an obvious change trend through reliability testing. By applying this method to the reverse sequence and calculating another curve UB, the intersection point of the two curves within the confidence interval is determined as the mutation point. When the significance level α = 0.05, the critical values of the statistical quantities UF and UB are ±1.96. UF>0 indicates that the sequence is on an upward trend, conversely, the sequence shows a downward trend, and when it is greater than 1.96 or less than -1.96, it indicates that the upward or downward trend is significant.

[0131] In any embodiment, the sliding t - test method tests the mutation point by analyzing whether there is a significant difference in the average values of two subsequences in the sequence.

[0132] JPEG2025077965000024.jpg73170

[0133] The statistical quantity follows a t - distribution with degrees of freedom V = n 1 +n 2 - 2.

[0134] In any embodiment, the Pettitt test method determines the mutation point by whether there is a significant difference in the cumulative distribution functions before and after the mutation point. In the Pettitt test method, for the original time series x 1 , x 2 , …x N and the constructed statistical quantity U t,N is expressed as follows. JPEG2025077965000025.jpg51170

[0135] Statistic U t,N Let the maximum value of be K τ Then the corresponding sample τ is a change point, and the test formula for the significance level is as follows. JPEG2025077965000026.jpg44170

[0136] Step d3: Divide the preset time period into multiple periods according to each change time.

[0137] Step d4: Determine the human activity data corresponding to each period.

[0138] In one example, the correction model is a long short-term memory network model, and each long short-term memory network model is constructed in the following steps.

[0139] First, according to each change time, divide the second historical outflow data into third historical outflow data of multiple periods.

[0140] Next, based on each third historical outflow data and the first simulation outflow data corresponding to each third historical outflow data, construct each long short-term memory network model.

[0141] Table 2 describes future outflow simulation scenarios jointly determined by future climate data, atmospheric boundary data, and different human activity intensity data. Among them, the future climate scenario (the first climate data) is obtained from the earth climate model data in the CMIP6 project.

[0142] Table 2 Settings of future outflow simulation scenarios in this embodiment JPEG2025077965000027.jpg198170

[0143] In one example, in the above step S104, the plurality of second simulation outflow data are obtained as follows. JPEG2025077965000028.jpg13170

[0144] Here, Q cor (t) represents the second simulation outflow data corresponding to the human activity data at time t, and Q sim (t) represents the first simulation outflow data at time t, and Q sim (t - 1) represents the first simulation outflow data at time t - 1, and N is for the long short-term memory network model JPEG2025077965000029.jpg19170

[0145] Embodiments of the present invention further provide a distributed hydrological forecasting device based on a similar inventive concept. As shown in FIG. 3, this device includes an acquisition module 301, a simulation module 302, a construction module 303, and a correction module 304.

[0146] The acquisition module 301 is used to acquire multiple types of human activity data within the target area, and the first climate data and atmospheric boundary data of the target area in the climate scene mode. For details, refer to the description of step S101 in the above embodiments, so it will not be elaborated here.

[0147] The simulation module 302 is used to input the first climate data and atmospheric boundary data into a pre-constructed hydrological model to obtain the first simulation outflow data corresponding to the climate scene mode. For details, refer to the description of step S102 in the above embodiments, so it will not be elaborated here.

[0148] The construction module 303 is used to construct a correction model corresponding to each human activity data based on each human activity data. For details, refer to the description of step S103 in the above embodiments, so it will not be elaborated here.

[0149] The correction module 304 is used to correct the first simulation outflow data by each correction model to obtain the second simulation outflow data corresponding to each human activity data. For details, refer to the description of step S104 in the above embodiment, and thus it will not be described in detail here.

[0150] In the prior art, when performing a simulation forecast of outflow data, only the influence of the outflow effect caused by climate change and single or assumed land use type change is considered. However, since the outflow data is affected by comprehensive effects of climate data, atmospheric boundary data, and human activities, the above device comprehensively considers the climate data and atmospheric boundary data of the target area to simulate the outflow data, and improves the accuracy of the outflow forecast by correcting the simulated outflow data with human activity data.

[0151] In one example, the atmospheric boundary data includes the leaf area index values of each vegetation type, and the acquisition module 301 includes a first acquisition sub-module and a first prediction sub-module.

[0152] The first acquisition sub-module is used to acquire the carbon dioxide concentration and geographical location in the atmosphere of the target area. For details, refer to the description of the above embodiment, and thus it will not be described in detail here.

[0153] The first prediction sub-module is used to input the first climate data, the carbon dioxide concentration in the atmosphere, and the geographical location into a pre-constructed leaf area index prediction model to obtain the leaf area index values of each vegetation type. For details, refer to the description of the above embodiment, and thus it will not be described in detail here.

[0154] In one example, the first prediction sub-module includes a first acquisition unit, a second acquisition unit, and a training unit.

[0155] The first acquisition unit is used to acquire the first historical leaf area index values of each vegetation type at the first time resolution for each grid in the target area. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0156] The second acquisition unit is used to acquire the first historical climate data and the historical atmospheric carbon dioxide concentration of the target area. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0157] The training unit is used to train an initial leaf area index prediction model based on the first historical climate data, the historical atmospheric carbon dioxide concentration, the geographical location, and the first historical leaf area index values of each vegetation type to obtain a leaf area index prediction model. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0158] In one example, the first acquisition unit includes a first acquisition subunit, a first acquisition subunit, a first calculation subunit, and a second calculation subunit.

[0159] The first acquisition subunit is used to acquire the total value of the historical leaf area index at the second time resolution for each grid in the target area. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0160] The second acquisition subunit is used to acquire the percentage of the land use type of each vegetation type in each grid. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0161] The first calculation subunit is used to calculate the second historical leaf area index value of each vegetation type in the grid based on each land use type percentage and the total value of each historical leaf area index. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0162] The second calculation subunit is used to calculate each second historical leaf area index value daily using the cubic spline interpolation method and obtain each first historical leaf area index value at the first hourly resolution of each grid. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0163] In one example, the second acquisition unit includes a third acquisition subunit, a third calculation subunit, a screening subunit, and a determination subunit.

[0164] The third acquisition subunit is used to acquire first historical climate data corresponding to a plurality of climate elements in the target area. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0165] The third calculation subunit is used to calculate the correlation coefficient between the first historical climate data corresponding to each climate element and the first historical leaf area index value. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0166] The screening subunit is used to screen climate elements based on each correlation coefficient and obtain the screened climate elements. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0167] The determination subunit is used to determine the first historical climate data of the target area from the first historical climate data corresponding to the screened climate elements. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0168] In one example, the atmospheric boundary data further includes land use type data, and the acquisition module 301 further includes a second acquisition submodule and a first simulation submodule.

[0169] The second acquisition sub-module is used to acquire the land use change factors of the target area in the climate scene mode. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0170] The first simulation sub-module is used to input the land use change factors into a pre-constructed future land use simulation model to obtain land use type data. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0171] In one example, the future land use simulation model includes a system dynamics simulation model and

[0172] a cellular automaton module based on an adaptive inertia competition mechanism, and the first simulation sub-module includes a first prediction unit and a second prediction unit.

[0173] The first prediction unit is used to input the land use change factors into the system dynamics simulation model to obtain the land use type land demand. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0174] The second prediction unit is used to predict the land use type data based on the land use change factors, the land use type land demand, and the cellular automaton module based on the adaptive inertia competition mechanism. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0175] In one example, the second prediction unit includes a first prediction sub-unit, a fourth calculation sub-unit, a fifth calculation sub-unit, and a second prediction sub-unit.

[0176] The first prediction subunit is used to input land use change factors into an artificial neural network model to predict the land use suitability probability. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0177] The fourth calculation subunit is used to calculate the neighborhood effect, adaptation inertia coefficient, and conversion cost corresponding to each land use type in the target area. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0178] The fifth calculation subunit is used to calculate the occurrence probability of each land use type based on the land use suitability probability, neighborhood effect, adaptation inertia coefficient, and conversion cost. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0179] The second prediction subunit is used to predict land use type data based on each occurrence probability and the roulette selection mechanism. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0180] In one example, the acquisition module 301 includes a third acquisition sub-module, a calculation sub-module, a fourth acquisition sub-module, and a correction sub-module.

[0181] The third acquisition sub-module is used to acquire the second climate data of the target area in the climate scene mode and the second historical climate data corresponding to the second climate data. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0182] The calculation sub-module is used to calculate the deviation between the second climate data and the second historical climate data. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0183] The fourth acquisition sub-module is used to acquire the third climate data of the target area in the climate scenario mode. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0184] The correction sub-module is used to correct the third climate data according to the deviation to obtain the first climate data. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0185] In one example, the third acquisition sub-module includes a third acquisition unit and a fourth acquisition unit.

[0186] The third acquisition unit is used to acquire the fourth climate data of the target area in the climate scenario mode. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0187] The fourth acquisition unit is used to interpolate the fourth climate data onto a preset spatial resolution grid to obtain the second climate data. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0188] In one example, the hydrological model is a variable infiltration capacity model, and the simulation module 302 includes a fifth acquisition sub-module, a first construction sub-module, a second simulation sub-module, and a calibration sub-module.

[0189] The fifth acquisition sub-module is used to acquire the training data of the variable infiltration capacity model, including the second historical climate data, historical atmospheric boundary data, soil terrain data, and the first historical outflow data. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0190] The first construction sub-module is used to construct an initial variable infiltration capacity model based on the second historical climate data, historical atmospheric boundary data, and soil terrain data in the training data. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0191] The second simulation sub-module is used to input the second historical climate data, historical atmospheric boundary data, and soil terrain data in the training data into the initial variable infiltration capacity model to obtain the third simulation outflow data. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0192] The calibration sub-module is used to calibrate the parameters in the initial variable infiltration capacity model based on the third simulation outflow data and the first historical outflow data in the training data to obtain a variable infiltration capacity model. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0193] In one example, the calibration sub-module includes a calculation unit, a calibration unit, a fifth acquisition unit, and a verification unit.

[0194] The calculation unit is used to calculate the correlation degree between the third simulation outflow data and the first historical outflow data in the training data. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0195] The calibration unit is used to calibrate the parameters in the initial variable infiltration capacity model according to the correlation degree to obtain a calibrated variable infiltration capacity model. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0196] The fifth acquisition unit is used to acquire test data including second historical climate data, historical atmospheric boundary data, soil terrain data, and first historical outflow data. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0197] The verification unit is used to verify the parameters in the calibrated variable infiltration capacity model based on the test data and obtain the variable infiltration capacity model. For details, refer to the description of the above embodiments, and thus will not be elaborated here.

[0198] In one example, the correlation degree in the calculation unit includes at least one of relative error, Nash efficiency coefficient, and Klein - Gupta efficiency coefficient.

[0199] In one example, each human activity data is human activity data within different periods, and the acquisition module 301 further includes a sixth acquisition sub - module, a first determination sub - module, a first division sub - module, and a second determination sub - module.

[0200] The sixth acquisition sub - module is used to acquire second historical outflow data within a preset time period.

[0201] The first determination sub - module is used to determine multiple abrupt change times of the second historical outflow data.

[0202] The first division sub - module is used to divide a preset time period into multiple periods according to each abrupt change time.

[0203] The second determination sub - module is used to determine human activity data corresponding to each period.

[0204] In one example, the correction model is a long - short - term memory network model, and the construction module 304 includes a second division sub - module and a second construction sub - module.

[0205] The second segmentation sub-module is used to divide the second historical outflow data into the third historical outflow data of multiple periods according to each mutation time.

[0206] The second construction sub-module is used to construct each long short-term memory network model based on each third historical outflow data and the first simulation outflow data corresponding to each third historical outflow data.

[0207] In one example, in the decision sub-module, the mutation time of the second historical outflow data is determined by any one of the M-K mutation test method, the sliding t-test method, and the Pettitt test method.

[0208] For the specific limitations and beneficial effects of the above device, reference can be made to the limitations on the above distributed hydrological forecasting method, so detailed description is not provided here. Each of the above modules may be fully or partially realized by software, hardware, and combinations thereof. Each of the above modules may be incorporated into the processor of the computer device in hardware form, or may be independent, and may be stored in the memory of the computer device in software form to facilitate the processor to call and execute the operations corresponding to each of the above modules.

[0209] Figure 4 is a schematic diagram of the hardware configuration of a computer device according to an exemplary embodiment. As shown in Figure 4, this device includes one or more processors 410 and a memory 420 including a persistent memory, a volatile memory, and a hard disk, and one processor 410 is illustrated in Figure 4. This device may further include an input device 430 and an output device 440.

[0210] The processor 410, the memory 420, the input device 430, and the output device 440 may be connected via a bus or other means, and in Figure 4, the connection via the bus is illustrated.

[0211] The processor 410 may be a central processing unit (CPU: Central Processing Unit). The processor 410 may be other general-purpose processors, digital signal processors (DSP: Digital Signal Processor), application specific integrated circuits (ASIC: Application Specific Integrated Circuit), field-programmable gate arrays (FPGA: Field-Programmable Gate Array) or other programmable logic devices, discrete gates or transistor logic devices, chips such as discrete hardware components, or combinations of the various chips described above. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0212] The memory 420 is a non-transitory computer-readable storage medium including persistent memory, volatile memory, and a hard disk, and can be used to store non-transitory software programs such as program instructions / modules corresponding to the distributed hydrological forecasting method in the embodiments of the present application, non-transitory computer-executable programs, and modules. The processor 410 executes various functional applications and data processing of the server by executing the non-transitory software programs, instructions, and modules stored in the memory 420, that is, realizes any of the above distributed hydrological forecasting methods.

[0213] Memory 420 may include a program storage area capable of storing an operating system and application programs necessary for at least one function, and a data storage area capable of storing data to be used as needed. Further, memory 420 can include a high-speed random access memory, and can further include a non-volatile memory such as at least one magnetic disk memory device, flash memory device, or other non-volatile solid state memory device. In some embodiments, memory 420 optionally includes a memory remotely located with respect to processor 410 that can be connected to the data processing device via a network. Examples of the above network include, but are not limited to, the Internet, intranet, local area network, mobile communication network, and combinations thereof.

[0214] Input device 430 can receive input numeric or character information and generate signal inputs related to user settings and function control. Output device 440 may include a display device such as a display screen.

[0215] One or more modules are stored in memory 420 and, when executed by one or more processors 410, execute the method as shown in FIG. 1.

[0216] The above product can execute the method according to the embodiments of the present invention, and includes functional modules and beneficial effects corresponding to the execution method. For technical details not described in detail in this embodiment, specifically, reference can be made to the related descriptions in the embodiment shown in FIG. 1.

[0217] Embodiments of the present invention further provide a non-transitory computer storage medium storing computer-executable instructions that can execute any of the methods in the above method embodiments. Here, the storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD), a solid-state drive (SSD), or the like. The storage medium may include a combination of memories of the above types.

[0218] In addition, in this specification, relational terms such as "first" and "second" are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of such an actual relationship or order between these entities or operations. Further, the term "comprising", "containing" or any other variation thereof is intended to cover non-exclusive inclusion such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the existence of other same elements in the process, method, article or device comprising that element.

[0219] The above are only specific embodiments of the present invention, and are intended to enable those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to these embodiments shown herein, but conforms to the broadest scope consistent with the principles of the present application and the novel features.

Claims

1. 1. A method for distributed hydrological forecasting, comprising: acquiring a plurality of types of human activity data within a target region, and a first climate data and an atmospheric boundary surface data of the target region in a climate scene mode; inputting the first climate data and the atmospheric interface data into a pre-constructed hydrological model to obtain first simulated runoff data corresponding to the climate scene mode; constructing a correction model corresponding to each of the human activity data based on each of the human activity data; correcting the first simulated runoff data by each of the correction models to obtain second simulated runoff data corresponding to each of the human activity data; The atmospheric interface data includes a Leaf Area Index value for each vegetation type, and obtaining the Leaf Area Index value for each vegetation type includes: obtaining an atmospheric carbon dioxide concentration and a geographic location of the region of interest; inputting the first climate data, the atmospheric carbon dioxide concentration, and the geographic location into a pre-constructed leaf area index prediction model to obtain a leaf area index value for each vegetation type; The step of constructing the leaf area index prediction model comprises: obtaining first historical Leaf Area Index values ​​for each vegetation type at a first temporal resolution for each grid within the region of interest; obtaining first historical climate data and historical atmospheric carbon dioxide concentrations for the region of interest; training an initial Leaf Area Index forecasting model based on the first historical climate data, the historical atmospheric carbon dioxide concentration, the geographic location, and a first historical Leaf Area Index value for each vegetation type to obtain the Leaf Area Index forecasting model; obtaining first historical Leaf Area Index values ​​for each vegetation type at a first temporal resolution for each grid within the region of interest, comprising: obtaining a historical Leaf Area Index sum value at a second temporal resolution for each grid within the region of interest; obtaining a percentage of land use types for each of said vegetation types in each grid; calculating a second historical Leaf Area Index value for each of the vegetation types in each grid based on the percentage of each of the land use types and each of the historical Leaf Area Index sum values; and calculating each of the second historical LAI values ​​on a daily basis using cubic spline interpolation to obtain each of the first historical LAI values ​​at a first temporal resolution for each of the grids; calculating a second historical LAI value for the vegetation type in each grid based on the percentage of each of the land use types and each of the historical LAI sum values, and for each grid, creating a system of equations using all predefined grids within a predefined neighborhood around the grid, and obtaining the first historical Leaf Area Index value at a first temporal resolution for the vegetation type in the grid based on the percentage of land use type and the total historical Leaf Area Index value for each of the predefined grids.

2. The step of acquiring first historical climate data for the region of interest comprises: acquiring first historical climate data corresponding to a plurality of climate elements of the target area; Calculating a correlation coefficient between first historical climate data corresponding to each of the climate elements and the first historical leaf area index value; Screening the climate elements based on each of the correlation coefficients to obtain screened climate elements; and determining first historical climate data for the region of interest from first historical climate data corresponding to the screened climate elements.

3. The atmospheric boundary surface data further includes land use type data, and the step of obtaining the land use type data includes: obtaining land use change factors of the target area in the climate scene mode; The method according to claim 1, further comprising the step of inputting the land use change factors into a previously constructed future land use simulation model to obtain the land use type data.

4. The future land use simulation model includes a system dynamics simulation model and a cellular automaton module based on an adaptive inertial competition mechanism, and the step of inputting the land use change factors into a previously constructed future land use simulation model to obtain the land use type data includes: inputting the land use change factors into the system dynamics simulation model to obtain land use type land demand; and forecasting the land use type data based on the land use change factors, the land use type land demand, and a cellular automaton module based on an adaptive inertial competition mechanism.

5. The step of predicting the land use type data based on the land use change factors, the land use type land demand, and a cellular automaton module based on an adaptive inertial competition mechanism includes: inputting the land use change factors into an artificial neural network model to predict land use suitability probability; calculating neighborhood effects, adaptive inertia coefficients, and conversion costs corresponding to each land use type of the target area; Calculating an occurrence probability of each land use type based on the land use suitability probability, the neighborhood effect, the adaptive inertia coefficient, and the conversion cost; and predicting the land use type data based on each of the occurrence probabilities and a roulette selection mechanism.

6. The step of acquiring the first climate data includes: acquiring second climate data for the area of ​​interest in the climate scene mode and second historical climate data corresponding to the second climate data; calculating a deviation between the second climate data and the second historical climate data; acquiring third climate data for the region of interest in the climate scene mode; and correcting the third climatic data in response to the deviation to obtain the first climatic data.

7. The step of acquiring second climate data includes: acquiring fourth climate data for the region of interest in the climate scene mode; and interpolating the fourth climate data to a predetermined spatial resolution grid to obtain the second climate data.

8. The hydrological model is a variable infiltration capacity model, and the step of constructing the variable infiltration capacity model includes: obtaining training data for the variable infiltration capacity model, the training data including second historical climate data, historical atmospheric interface data, soil topography data, and first historical runoff data; constructing an initial variable infiltration capacity model based on the second historical climate data, the historical atmospheric interface data, and the soil topography data in the training data; inputting the second historical climate data, the historical atmospheric interface data, and the soil topography data in the training data into the initial variable infiltration capacity model to obtain a third simulated runoff data; and calibrating parameters in the initial variable permeability model based on the third simulated runoff data and first historical runoff data in the training data to obtain the variable permeability model.

9. calibrating parameters in the initial variable permeability model based on the third simulation runoff data and the first historical runoff data in the training data to obtain the variable permeability model; Calculating a correlation between the third simulation runoff data and the first historical runoff data in the training data; calibrating parameters in the initial variable permeability model according to the degree of correlation to obtain a calibrated variable permeability model; acquiring test data including second historical climate data, historical atmospheric interface data, soil topography data, and the first historical runoff data; and calibrating parameters in a calibrated variable permeability model based on the test data to obtain the variable permeability model.

10. 10. The method of claim 9, wherein the correlation measure comprises at least one of a relative error, a Nash efficiency coefficient, and a Klein-Gupta efficiency coefficient.

11. Each of the human activity data is human activity data within a different time period, and the step of acquiring each of the human activity data includes: Obtaining second history outflow data within a preset time period; determining a plurality of sudden change times of the second historical spill data; Dividing the preset time period into a plurality of periods according to each of the sudden change times; and determining human activity data corresponding to each said period of time.

12. The correction model is a long short-term memory network model, and the step of constructing each of the long short-term memory network models includes: Dividing the second history data into a plurality of periods of third history data according to each of the sudden change times; 12. The method of claim 11, further comprising constructing each of the long short-term memory network models based on each of the third historical runoff data and first simulated runoff data corresponding to each of the third historical runoff data.

13. The method according to claim 11, wherein the sudden change time of the second historical outflow data is determined by any one of an MK sudden change test method, a sliding t-test method, and a Pettitt test method.

14. 1. A distributed hydrological forecasting system comprising: an acquisition module for acquiring multiple types of human activity data within a target region, and first climate data and atmospheric boundary surface data of the target region in a climate scene mode; a simulation module for inputting the first climate data and the atmospheric interface data into a pre-constructed hydrological model to obtain first simulated runoff data corresponding to the climate scene mode; a construction module for constructing a correction model corresponding to each of the human activity data based on each of the human activity data; a correction module for correcting the first simulated runoff data by each of the correction models to obtain second simulated runoff data corresponding to each of the human activity data; The atmospheric interface data includes a Leaf Area Index value for each vegetation type, and obtaining the Leaf Area Index value for each vegetation type includes: obtaining an atmospheric carbon dioxide concentration and a geographic location of the region of interest; inputting the first climate data, the atmospheric carbon dioxide concentration, and the geographic location into a pre-constructed leaf area index prediction model to obtain a leaf area index value for each vegetation type; The step of constructing the leaf area index prediction model comprises: obtaining first historical Leaf Area Index values ​​for each vegetation type at a first temporal resolution for each grid within the region of interest; obtaining first historical climate data and historical atmospheric carbon dioxide concentrations for the region of interest; training an initial Leaf Area Index forecasting model based on the first historical climate data, the historical atmospheric carbon dioxide concentration, the geographic location, and a first historical Leaf Area Index value for each vegetation type to obtain the Leaf Area Index forecasting model; obtaining first historical Leaf Area Index values ​​for each vegetation type at a first temporal resolution for each grid within the region of interest, comprising: obtaining a historical Leaf Area Index sum value at a second temporal resolution for each grid within the region of interest; obtaining a percentage of land use types for each of said vegetation types in each grid; calculating a second historical Leaf Area Index value for each of the vegetation types in each grid based on the percentage of each of the land use types and each of the historical Leaf Area Index sum values; and calculating each of the second historical LAI values ​​on a daily basis using cubic spline interpolation to obtain each of the first historical LAI values ​​at a first temporal resolution for each of the grids; calculating a second historical LAI value for the vegetation type in each grid based on the percentage of each of the land use types and each of the historical LAI sum values, and for each grid, creating a system of equations centered on the grid using all predefined grids within the predefined neighborhood, and obtaining the first historical Leaf Area Index value at a first temporal resolution for the vegetation type in the grid based on the percentage of land use type and the total historical Leaf Area Index value for each of the predefined grids.

15. A computer device comprising: a memory; and a processor, the memory and the processor being communicatively connected to each other; computer instructions stored in the memory; and the processor executing the computer instructions to perform steps of the distributed hydrological forecasting method according to any one of claims 1 to 13.

16. A computer-readable storage medium having a computer program stored thereon, A computer-readable storage medium, comprising a computer program which, when executed by a processor, implements the steps of the method for distributed hydrological forecasting according to any one of claims 1 to 13.

Images