Drainage basin hydrological evaluation method and system under climate change

Abstract

The invention relates to the technical field of hydrological assessment and environmental science, in particular to a watershed hydrological assessment method and system under climate change, and the method comprises the steps: collecting multi-source heterogeneous data, and generating fusion feature data and causal path data through multi-modal fusion; optimizing a watershed hydrological network structure based on reinforcement learning, performing runoff simulation by using an enhanced hydrological model, and generating optimized runoff prediction data; combining runoff prediction data and a run-length theory to extract drought characteristic data, and generating scene data for describing an extreme scene through a path constraint type generative adversarial network; and constructing a dynamic joint distribution model of the drought characteristics based on the scene data, and carrying out multi-scene risk assessment. According to the method, accurate modeling and risk quantification of drainage basin drought characteristics in a complex climate scene are realized, the precision and applicability of hydrological assessment are remarkably improved, and a scientific basis is provided for drainage basin water resource management.

Description

Technical Field

[0001] The present invention relates to the field of hydrological assessment and environmental science and technology, and in particular to a method and system for basin hydrological assessment under climate change. Background Art

[0002] Climate change has had a profound impact on the hydrological process of the basin, including significant changes in runoff patterns, drought frequency and intensity, which has put forward higher requirements for the scientific management and sustainable use of water resources in the basin. The existing technology (Chinese invention patent, CN111797129B, publication number: A method for assessing hydrological drought under climate change scenarios) usually relies on hydrological models (such as SWAT model) combined with statistical methods (such as Copula function) to assess hydrological drought. Although these methods can provide relatively accurate assessments under historical climate conditions, they have obvious shortcomings under climate change scenarios: (1) they do not fully utilize multi-source heterogeneous data and ignore the dynamic causal relationship between meteorological, hydrological and ecological variables; (2) they cannot dynamically optimize the basin network structure and are difficult to adapt to the network disturbance caused by climate change; (3) they lack high-reliability extreme scenario data generation methods, resulting in limited ability to quantify drought characteristics. Therefore, a new method combining multimodal data fusion, dynamic model optimization and extreme scenario analysis is urgently needed to improve the accuracy and applicability of assessment. Summary of the invention

[0003] In view of the many problems existing in the above-mentioned prior art, the present invention provides a method and system for basin hydrological assessment under climate change. The present invention extracts the causal relationship between meteorological, hydrological and ecological variables through multimodal data fusion, optimizes the basin hydrological network structure, and uses a path-constrained generative adversarial network to generate extreme scenario data, and combines a dynamic joint distribution model to assess multi-scenario risks. The present invention can accurately capture the comprehensive response of the hydrological state in the basin to climate change, and provide scientific support for the quantification of drought characteristics and risk management.

[0004] A watershed hydrological assessment method under climate change includes the following steps:

[0005] Collect meteorological data, geographic data, groundwater dynamics data, vegetation cover dynamics data and social water use behavior data, clean and standardize the collected data, and generate fusion feature data and causal path data through a multimodal fusion model. The causal path data reflects the causal relationship and dynamic association between meteorological, hydrological and ecological variables;

[0006] Based on the fusion of feature data and causal path data, a directed graph structure of the basin hydrological network is constructed. The node and edge weights in the directed graph are optimized by combining reinforcement learning to generate optimized basin hydrological network data, which is then input into the enhanced hydrological model for runoff simulation. The runoff simulation results are corrected by dynamically adjusting the model parameters to generate optimized runoff prediction data.

[0007] Based on the optimized runoff prediction data, the drought severity and duration are quantified by the standardized runoff index, and the characteristics of drought events are extracted by combining the run theory to generate drought characteristic data. In addition, the drought characteristic data and the optimized runoff prediction data are combined to generate scenario data describing extreme scenarios through a path-constrained generative adversarial network.

[0008] Based on the scenario data, a dynamic joint distribution model of drought characteristics is constructed. Multi-scenario risk assessment is carried out on the scenario data in combination with the dynamic joint distribution model. Based on the assessment results, basin hydrological assessment data is generated to evaluate the comprehensive response of drought characteristics and hydrological conditions in the basin.

[0009] Preferably, the collected meteorological data include precipitation data, temperature data and humidity data recorded hourly; the geographic data include digital elevation models and land use type maps; the groundwater dynamics data include monitoring well water level data; the vegetation cover dynamics data include vegetation cover change data calculated based on the normalized vegetation index; and the social water use behavior data include agricultural irrigation water volume and industrial water volume statistically divided into regions.

[0010] Preferably, the multimodal fusion model generates fusion feature data through the following process:

[0011] Extract spatial features through convolutional neural networks;

[0012] Extract time series features using long short-term memory networks;

[0013] The extracted spatial features and time series features are input into the multi-layer perceptron network for fusion to generate fused feature data.

[0014] Preferably, the causal path data is generated by a causal network model, which is based on Granger causality analysis and a self-supervised learning algorithm to extract the causal relationship between meteorological data, hydrological data and ecological variables, and represents the causal path through a directed graph. The causal path data includes causal relationship weights and lag time parameters.

[0015] Preferably, the steps of constructing a directed graph structure of a watershed hydrological network include:

[0016] The meteorological variables, hydrological variables and ecological variables in the causal path data are defined as network nodes;

[0017] The reinforcement learning agent adjusts the weights of the edges in the network to optimize the connection strength between nodes;

[0018] Output optimized watershed hydrological network data for subsequent runoff simulation.

[0019] Preferably, the steps of performing runoff simulation using the enhanced hydrological model include:

[0020] Input the optimized watershed hydrological network data into the enhanced hydrological model;

[0021] Dynamically adjust soil permeability, evapotranspiration ratio and groundwater recharge rate;

[0022] The optimization algorithm is combined to minimize the error between the runoff simulation results and the historical measured runoff data, and the optimized runoff prediction data is generated.

[0023] Preferably, the step of extracting drought event characteristics comprises:

[0024] The standardized runoff index is calculated based on the optimized runoff prediction data. The calculation formula of the standardized runoff index is:

[0025]

[0026] Among them, SRI is the standardized runoff index, Q is the time series runoff value, μ is the mean of the time series runoff value, and σ is the standard deviation of the time series runoff value;

[0027] The cumulative intensity S and duration D of drought events are calculated in combination with the run theory. The calculation formula of the cumulative intensity is:

[0028]

[0029] Where S is the cumulative intensity of drought events, SRI i is the normalized runoff index during the i-th period of the drought period, and D is the duration of the drought event.

[0030] Preferably, the step of generating scenario data by using a path-constrained generative adversarial network includes:

[0031] The generator combines the node and edge weights of the watershed hydrological network to generate extreme scenario data that meets the constraints;

[0032] The discriminator verifies the credibility of the generated scenario data through optimal transmission theory to ensure the physical consistency of the scenario data.

[0033] Preferably, the step of constructing a dynamic joint distribution model of drought characteristics based on scenario data comprises:

[0034] The probability distribution of drought characteristics is calculated using the dynamic kernel density estimation method. The calculation formula of the dynamic kernel density estimation is:

[0035]

[0036] Among them, f(x) is the probability density value at the point x to be estimated, n is the number of samples, h is the smoothing parameter, and x i is the value of the i-th sample point, K is the kernel function;

[0037] The dynamic joint distribution model performs multi-scenario risk assessment on scenario data and calculates the occurrence probability and distribution characteristics of drought characteristics under different scenarios.

[0038] A system for implementing the watershed hydrological assessment method under climate change, comprising:

[0039] Data collection module, used to collect meteorological data, geographic data, groundwater dynamic data, vegetation cover dynamic data and social water use behavior data, and clean and standardize the collected data;

[0040] A data fusion module, connected to the data acquisition module, for generating fusion feature data and causal path data through a multimodal fusion model, wherein the causal path data reflects the causal relationship and dynamic association between meteorological variables, hydrological variables and ecological variables;

[0041] A watershed network optimization module, connected to the data fusion module, is used to construct a directed graph structure of the watershed hydrological network based on the fused feature data and the causal path data, optimize the node and edge weights in the directed graph in combination with reinforcement learning, and generate optimized watershed hydrological network data;

[0042] A runoff simulation module is connected to the watershed network optimization module and is used to input the optimized watershed hydrological network data into the enhanced hydrological model for runoff simulation, and to correct the runoff simulation results by dynamically adjusting the model parameters to generate optimized runoff prediction data;

[0043] A drought feature extraction module, connected to the runoff simulation module, is used to calculate the standardized runoff index based on the optimized runoff prediction data, extract drought event features in combination with the run theory, and generate drought feature data;

[0044] A scenario generation module, connected to the drought feature extraction module, for combining drought feature data and optimized runoff prediction data to generate scenario data describing extreme scenarios through a path-constrained generative adversarial network;

[0045] An assessment module is connected to the scenario generation module, and is used to construct a dynamic joint distribution model of drought characteristics based on scenario data, perform multi-scenario risk assessment on the scenario data in combination with the dynamic joint distribution model, and generate watershed hydrological assessment data based on the assessment results, wherein the watershed hydrological assessment data includes distribution information of drought characteristics, dynamic changes in runoff, and comprehensive response analysis of multiple scenario superpositions.

[0046] Compared with the prior art, the advantages and beneficial effects of the present invention are:

[0047] The present invention uses multimodal fusion technology to achieve deep fusion of multi-source heterogeneous data such as meteorology, geography, and groundwater dynamics, and generates fused feature data and causal path data that can reflect causal relationships, effectively solving the problem of insufficient causal analysis in the prior art.

[0048] The present invention optimizes the basin hydrological network structure through reinforcement learning, realizes the dynamic adjustment of node and edge weights, generates optimized basin hydrological network data that conforms to the impact of climate change, and overcomes the lack of adaptability caused by the fixed network structure in traditional methods.

[0049] The present invention generates extreme scenario data through a path-constrained generative adversarial network, achieves high-reliability modeling of drought scenarios, and verifies the physical consistency of the data through optimal transmission theory, solving the defect of limited ability to describe extreme scenarios.

[0050] The present invention combines the dynamic joint distribution model with kernel density estimation technology to achieve accurate assessment of the probability of occurrence of drought characteristics under multiple scenarios and enhance the ability to adapt to complex scenario risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a schematic diagram of the process of the present invention;

[0052] Figure 2 Schematic diagram of multimodal data fusion process in the present invention;

[0053] Figure 3 A schematic diagram of the scenario generation process of the path-constrained generative adversarial network in the present invention;

[0054] Figure 4 It is a schematic diagram of multi-scenario risk assessment of the dynamic joint distribution model in the present invention;

[0055] Figure 5 It is a structural block diagram of the system of the present invention. DETAILED DESCRIPTION

[0056] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is obvious that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0057] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0058] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0059] like Figure 1 As shown, a basin hydrological assessment method under climate change includes the following steps:

[0060] Collect meteorological data, geographic data, groundwater dynamics data, vegetation cover dynamics data and social water use behavior data, clean and standardize the collected data, and generate fusion feature data and causal path data through a multimodal fusion model. The causal path data reflects the causal relationship and dynamic association between meteorological, hydrological and ecological variables;

[0061] Preferably, the collected meteorological data include precipitation data, temperature data and humidity data recorded hourly; the geographic data include digital elevation models and land use type maps; the groundwater dynamics data include monitoring well water level data; the vegetation cover dynamics data include vegetation cover change data calculated based on the normalized vegetation index; and the social water use behavior data include agricultural irrigation water volume and industrial water volume statistically divided into regions.

[0062] In principle, the data collection is to cover the key factors that affect the hydrology of the basin in multiple dimensions. Meteorological data (such as hourly precipitation data, temperature data and humidity data) directly affect evapotranspiration, soil moisture and runoff processes; geographic data (such as digital elevation models and land use type maps) provide information on the topography and human activities of the basin; groundwater dynamic data (such as monitoring well water level data) reflect groundwater level changes and recharge dynamics; vegetation cover dynamic data (such as vegetation cover change data calculated based on the normalized vegetation index) describes the relationship between vegetation and evapotranspiration; social water use behavior data (such as agricultural irrigation water and industrial water use) describes the direct impact of human activities on water resource consumption.

[0063] Preprocessing includes data cleaning, standardization, and missing value filling to ensure data quality and availability. Cleaning improves data accuracy by removing outliers and redundant information, and standardization uses mean normalization method:

[0064]

[0065] Among them, X′ is the standardized data, X is the original data, mean(X) is the mean of the data, and std(X) is the standard deviation of the data. This method makes the scales of different physical quantities consistent, so as to adapt to the subsequent multimodal fusion process. Missing values ​​are filled by spatiotemporal interpolation methods, such as inferring the data distribution of unobserved areas based on Kriging interpolation.

[0066] In effect, this step ensures high-quality input of multi-dimensional data and lays a solid foundation for subsequent modeling.

[0067] The core of the multimodal fusion model is to fuse different data types (time series, raster data, and vector data) in a unified computing framework. First, a convolutional neural network (CNN) is used to extract spatial features from raster data, such as terrain elevation and the distribution pattern of land use types. In the specific implementation, CNN captures the local features of the data through convolution kernels and extracts high-level semantic information through multi-layer pooling operations. Subsequently, a long short-term memory network (LSTM) is used to analyze time series data (such as precipitation and groundwater level changes). The network effectively models the long-term dependencies in the time series by introducing memory units.

[0068] The fusion model inputs the extracted spatial features and time series features into a multi-layer perceptron (MLP) to achieve the fusion of heterogeneous data. The specific operations include feature concatenation, weight normalization, and multi-layer nonlinear mapping to generate fused feature data. The fused feature data is a high-dimensional vector containing multi-dimensional information, which can reflect the pattern of a single data and characterize the interaction between data.

[0069] The fused feature data provides a high-dimensional representation that fully captures the interactive characteristics of space, time and variables, providing a rich information basis for causal analysis and hydrological network modeling.

[0070] In a specific watershed, hourly precipitation data, temperature and humidity data were collected to generate a daily averaged meteorological time series; a digital elevation model (10-meter resolution) and a land use type map were generated using high-resolution remote sensing images; monitoring well data recorded water level fluctuations at different observation points in the watershed; and the Normalized Difference Vegetation Index (NDVI) was extracted from MODIS data to provide a dynamic trend of vegetation coverage. Through the above preprocessing, standardized and time-space consistent data input was formed.

[0071] After integrating these data, the multimodal fusion model generated fusion feature data. In the causal path analysis, it was found that precipitation significantly affected runoff dynamics and had a three-day lag effect on groundwater levels. Finally, the generated causal path data was used for subsequent basin hydrological network optimization, verifying the reliability of the model.

[0072] Preferably, Figure 2 As shown, the multimodal fusion model generates fusion feature data through the following process:

[0073] Extract spatial features through convolutional neural networks;

[0074] Extract time series features using long short-term memory networks;

[0075] The extracted spatial features and time series features are input into the multi-layer perceptron network for fusion to generate fused feature data.

[0076] Spatial feature extraction (CNN): Convolutional neural networks are good at extracting local features from rasterized spatial data. In this solution, the input data includes digital elevation models (DEMs) and land use type maps. By setting convolution kernels of different sizes (e.g., 3×3 or 5×5), CNN is able to extract local spatial features in raster data, such as slope, aspect, and land use distribution patterns. Multi-layer convolution operations combined with pooling layers further capture high-level semantic features of spatial data, such as terrain complexity and regional land use intensity.

[0077] Time series feature extraction (LSTM): Long short-term memory networks are used to extract dynamic features from time series data (such as hourly precipitation, groundwater level changes, and temperature fluctuations). LSTM effectively learns long-term dependencies in time series by introducing memory units and gating mechanisms. In this scheme, LSTM is able to identify the lag effects of meteorological changes on runoff dynamics, such as the lag response time of precipitation to runoff. The input time series data is segmented into windows of fixed length (such as data from the past 7 days) and encoded through the embedding layer before being input into the LSTM network for training.

[0078] Feature fusion (MLP): The extracted spatial features and time series features are respectively formed into high-dimensional vectors, which are integrated into a joint feature vector through splicing operations. The multi-layer perceptron is used to perform nonlinear mapping and feature fusion on the joint feature vector. The fusion process includes feature normalization, weight adjustment, and multi-layer activation operations. The final output fused feature data can comprehensively reflect the interactive relationship between spatial and temporal variables. For example, the slope change (spatial feature) and continuous precipitation events (time series features) in a certain area may cause extreme runoff events. These interactive relationships are modeled and explicitly characterized through MLP.

[0079] The model uniformly represents data of different modalities (space and time) as high-dimensional fused feature data, which can reflect the complex interactive relationship between meteorology, hydrology and ecosystems, and provide accurate and reliable input for causal path analysis. Through the time series feature extraction of LSTM, the model can accurately capture the lagged response of meteorological variables (such as precipitation and temperature) to hydrological variables (such as groundwater level and runoff), supporting in-depth analysis of the hydrological dynamics of the basin. Through the fusion of spatial and temporal features by MLP, the model can identify the interaction between spatial features (such as land use change) and temporal dynamics (such as long-term drought trends).

[0080] Embodiment, in practical applications, the multimodal data of a certain river basin includes a high-resolution digital elevation model (10-meter grid resolution), a land use type map, hourly precipitation, and groundwater dynamics data. First, the digital elevation model and the land use type map are input into CNN, and local and global spatial features, such as slope and land use intensity distribution, are extracted through a three-layer convolutional network. Secondly, the hourly precipitation data and groundwater level data are divided into 7-day windows and input into LSTM for time series modeling to capture lag effects and periodic changes. Finally, the spatial feature vector output by CNN is spliced ​​with the temporal feature vector output by LSTM, and input into MLP for fusion to generate fused feature data containing spatial and temporal interaction information.

[0081] For example, in a continuous precipitation event, LSTM identified a delayed response of a significant increase in groundwater level on the third day after the peak of precipitation, while the land use features extracted by CNN showed that the slope and vegetation cover in the area had an important impact on the runoff path. Through the fusion of MLP, the model accurately characterized the dynamic relationship between precipitation, groundwater and land use, providing precise input for causal path analysis and watershed hydrological network modeling.

[0082] Preferably, the causal path data is generated by a causal network model, which is based on Granger causality analysis and a self-supervised learning algorithm to extract the causal relationship between meteorological data, hydrological data and ecological variables, and represents the causal path through a directed graph. The causal path data includes causal relationship weights and lag time parameters.

[0083] Granger causality analysis is a classic method for detecting causality in time series. In this scheme, assume two variables X and Y. If the effect of using past X values ​​to predict Y is significantly better than using only past values ​​of Y, then X is considered to be the Granger cause of Y. The formula is as follows:

[0084]

[0085] Among them, Y t is the target variable value at time ttt, X t-j is the value of the dependent variable at time lag jjj, β i and γ j is the regression coefficient, ∈ t is the error term, p and q are the number of lag terms respectively.

[0086] In this scheme, Granger causality analysis is used to preliminarily screen the direct causal relationship between meteorological variables (such as precipitation and temperature) and hydrological variables (such as groundwater level changes and runoff), and to estimate the lag time parameters. For example, there may be a lag response of several hours or days in precipitation to groundwater level changes.

[0087] To address the implicit causal relationships in multimodal data (such as the indirect impact of vegetation cover changes on runoff), this solution introduces a self-supervised learning algorithm to build a causal network model. Self-supervised learning uses unlabeled data to generate pseudo labels through specific tasks, such as predicting whether there is a synergistic effect between the change patterns of variables. The specific implementation includes:

[0088] Define input data characteristics, such as precipitation time series, normalized difference vegetation index, groundwater dynamics;

[0089] Construct positive samples (pairs of variables that change together) and negative samples (pairs of variables that change independently) through contrastive learning methods;

[0090] The neural network model is trained to output causal weights, which reflect the strength of direct or indirect causality between different variables.

[0091] The causal path data is stored in the form of a directed graph, where nodes represent meteorological variables (hydrological variables and ecological variables such as precipitation, temperature, runoff, vegetation cover, etc.), and edges represent causal relationships between variables. The weight of the edge represents the strength of the causal relationship, and the lag time parameter represents the time delay of the causal relationship. For example, the causal weight of precipitation on runoff is 0.8, and the lag time is 6 hours, indicating that the change in precipitation has a high correlation with the runoff dynamics and there is a certain lag.

[0092] The causal network model quantifies the direct effects of meteorological variables on hydrological variables and the indirect effects of ecological variables through causal path data. For example, precipitation has a weight of 0.7 on groundwater level with a lag time of 48 hours; changes in vegetation cover indirectly affect runoff dynamics by regulating evapotranspiration.

[0093] The combination of Granger causality analysis and self-supervised learning enables the model to capture complex interactions between nonlinear, cross-modal variables, such as the impact of temperature fluctuations and changes in vegetation cover on runoff.

[0094] The causal pathway data provide accurate input for basin hydrological network optimization and the construction of dynamic joint distribution models, supporting further runoff prediction and risk assessment.

[0095] Embodiment, in a watershed with significant climate change, the input data include hourly recorded precipitation and temperature time series, daily groundwater dynamics data, vegetation cover change data (NDVI calculated based on MODIS images) and runoff observation data. First, Granger causality analysis is used to detect the causal relationship between precipitation and groundwater level changes. The results show that precipitation has a significant lagged effect on groundwater level, with a lag time of 48 hours. Then, a self-supervised learning model is used to model the implicit relationship between vegetation cover and runoff. The results show that changes in vegetation cover indirectly affect runoff dynamics by regulating evapotranspiration.

[0096] The directed graph generated by the causal path data includes nodes such as precipitation, temperature, groundwater level, runoff and vegetation cover. The edge weights and lag parameters represent the causal strength and time delay between variables, respectively. For example, the weight of precipitation to runoff is 0.85, with a lag time of 6 hours; the weight of vegetation cover to runoff is 0.6, with no obvious lag. The causal path data provides a reliable basis for the subsequent optimization of the basin hydrological network and the generation of extreme scenarios.

[0097] Based on the fusion of feature data and causal path data, a directed graph structure of the basin hydrological network is constructed. The node and edge weights in the directed graph are optimized by combining reinforcement learning to generate optimized basin hydrological network data, which is then input into the enhanced hydrological model for runoff simulation. The runoff simulation results are corrected by dynamically adjusting the model parameters to generate optimized runoff prediction data.

[0098] The fusion of characteristic data and causal path data provides high-quality input data for constructing the directed graph structure of the basin hydrological network. The fusion of characteristic data captures the complex interactive relationship between space, time and variables, and the causal path data clarifies the causal relationship and lag effect of meteorological variables (hydrological variables and ecological variables). In the directed graph:

[0099] Nodes: represent key hydrological variables (such as precipitation, groundwater level, runoff, and evapotranspiration).

[0100] Edges: represent the causal relationship between nodes, edge weights quantify the strength of the causal relationship, and lag parameters quantify the time delay of the causal effect. By integrating this information, the directed graph structure not only provides an intuitive representation of the associations between variables, but also dynamically captures the transmission effects of the hydrological network.

[0101] This solution adopts an intelligent optimization method based on reinforcement learning, which uses intelligent agents to dynamically adjust the weights of nodes and edges in the graph to optimize the performance of the basin hydrological network. The core of reinforcement learning is that the intelligent agent learns the optimal strategy for decision-making through interaction:

[0102] State: the nodes, edge weights, and structure of the current directed graph.

[0103] Action: Adjust node properties or edge weights, such as increasing edge weights to enhance the effect of precipitation on runoff.

[0104] Reward function: Reverse optimization is performed based on the error between the runoff simulation results and the measured data, and the rationality of the network structure is improved by minimizing the error. In iterative learning, the agent gradually optimizes the directed graph by comparing the measured and simulated results, and generates optimized watershed hydrological network data.

[0105] The optimized watershed hydrological network data is loaded as input into the enhanced hydrological model for runoff simulation. The enhanced hydrological model achieves higher accuracy through dynamic adjustment of the following parameters:

[0106] Soil permeability: reflects the impact of different soil types on runoff.

[0107] Evapotranspiration ratio: describes the regulation of the evapotranspiration process by vegetation and meteorological conditions.

[0108] Groundwater recharge rate: quantifies the contribution of groundwater level dynamics to runoff. During the runoff simulation process, the model adjusts the above parameters through an optimization algorithm to minimize the error between the simulation results and the historical measured data, and finally generates optimized runoff prediction data.

[0109] In the example, in an application of a certain watershed, the input data includes meteorological characteristics (hourly precipitation and temperature), hydrological characteristics (groundwater level dynamics and runoff records) and ecological characteristics (vegetation cover changes). First, a directed graph is constructed based on the fusion feature data and causal path data, where the nodes include precipitation, temperature, groundwater level, runoff and evapotranspiration, and the edge weights and lag parameters are optimized by the reinforcement learning agent. For example, the edge weight from precipitation to runoff is optimized from 0.7 to 0.85, and the lag time is 6 hours.

[0110] The optimized directed graph is input into the enhanced hydrological model to dynamically adjust soil infiltration rate, evapotranspiration ratio and groundwater recharge rate, for example:

[0111] The soil permeability was adjusted to 0.25 (representing sandy soil) and the evapotranspiration ratio was adjusted to 0.6.

[0112] The groundwater recharge rate is set at 0.1 mm / h according to the seasonal fluctuation of groundwater level changes.

[0113] After multiple rounds of iterations, the mean square error between the runoff simulation results output by the model and the measured runoff was reduced to 2%, verifying the predictive ability of the optimized basin hydrological network.

[0114] Preferably, the steps of constructing a directed graph structure of a watershed hydrological network include:

[0115] The meteorological variables, hydrological variables and ecological variables in the causal path data are defined as network nodes;

[0116] The reinforcement learning agent adjusts the weights of the edges in the network to optimize the connection strength between nodes;

[0117] Output optimized watershed hydrological network data for subsequent runoff simulation.

[0118] In a watershed hydrological network, nodes represent key variables that have direct or indirect effects on runoff dynamics, including:

[0119] Meteorological variables: such as precipitation, temperature, and humidity.

[0120] Hydrological variables: such as groundwater level, runoff, evapotranspiration.

[0121] Ecological variables: such as vegetation coverage and soil moisture. These nodes are derived from causal path data, which clearly defines the dynamic associations and causal relationships of various variables.

[0122] The edges in the network represent the relationship between nodes, and their weights reflect the strength of the causal relationship. The lag time parameter characterizes the time delay of the causal effect. For example, the edge weight of precipitation to runoff may be 0.8, and the lag time is 6 hours, indicating that precipitation has a significant impact on runoff but there is a certain time lag.

[0123] In order to improve the structural rationality of the basin hydrological network, this scheme introduces reinforcement learning agents to dynamically optimize the weights of the edges in the network. The reinforcement learning process includes the following elements:

[0124] Status: nodes, edge weights and structure of the current watershed hydrological network.

[0125] Action: Adjust the weights of the edges between nodes. For example, increase the weight of an edge to reflect a stronger causal relationship.

[0126] Reward function: By comparing the error between simulated runoff and measured runoff (such as mean square error), the agent is guided to optimize the edge weights so that the runoff simulation results are closer to actual observations.

[0127] The reinforcement learning agent continuously optimizes the network structure through interactive learning in multiple iterations to ensure that the node and edge weights can truly reflect the interactions between variables in the watershed.

[0128] In actual application, the specific execution steps include:

[0129] (1) Input the causal path data into the system, including the initial weight and lag time parameters of each node variable. For example, the initial edge weights of precipitation and temperature in the meteorological variables and runoff in the hydrological variable are 0.6 and 0.4 respectively, and the lag time parameters are 3 hours and 1 hour.

[0130] (2) The agent randomly initializes edge weights to generate an initial watershed hydrological network.

[0131] This network was input into the enhanced hydrological model to simulate runoff output.

[0132] Calculate the error between the simulated runoff and the measured runoff, for example using the mean square error formula:

[0133]

[0134] Among them, MSE is the mean square error, Q sim,i is the simulated runoff value at the i-th moment, Q obs,i is the measured runoff value at the i-th moment, and n is the total number of time steps.

[0135] The edge weights are adjusted inversely according to the error, and the network structure is updated.

[0136] Iterate the training until the reward function converges (i.e. the error reaches the minimum value), and output the optimized watershed hydrological network data.

[0137] (3) The optimized watershed hydrological network data includes the final edge weights of each node variable and its connection relationship. For example, the edge weight from precipitation to runoff is optimized to 0.85, and the lag time is still 6 hours; the edge weight from temperature to evapotranspiration is 0.7, and the lag time is 12 hours. These optimized parameters will be used in the subsequent runoff simulation process.

[0138] The basin hydrological network optimized through reinforcement learning more accurately reflects the causal relationship between meteorological, hydrological and ecological variables, making the network structure more consistent with the actual characteristics of the basin.

[0139] Since the reinforcement learning process uses the runoff simulation error as the optimization target, the optimized network significantly improves the prediction accuracy in subsequent runoff simulations. For example, in actual tests, the mean square error of runoff prediction after optimization was reduced by 20% compared with the initial network.

[0140] Reinforcement learning enables the network to adapt to changes in watershed characteristics and input data. For example, when precipitation intensity increases significantly or vegetation cover changes drastically, the network can respond quickly by adjusting edge weights, providing more robust support for subsequent model predictions.

[0141] In the study of a watershed, the input causal path data includes node variables such as precipitation, temperature, runoff, and groundwater level and their initial edge weights. During the optimization process, the reinforcement learning agent recognizes that the impact of groundwater level changes on runoff is more significant than the initial assumption, and optimizes its edge weight from 0.5 to 0.75. At the same time, the agent detects that the effect of vegetation cover on evapotranspiration has a lag time of 12 hours, and adjusts its edge weight to 0.6.

[0142] The optimized basin hydrological network data was input into the enhanced hydrological model for runoff simulation, and the mean square error between the simulation results and the measured runoff was reduced to 2%. The study showed that the optimized network not only improved the simulation accuracy, but also accurately captured the comprehensive impact of meteorological and ecological variables on basin hydrology, providing important support for subsequent scenario analysis.

[0143] Preferably, the steps of performing runoff simulation using the enhanced hydrological model include:

[0144] Input the optimized watershed hydrological network data into the enhanced hydrological model;

[0145] Dynamically adjust soil permeability, evapotranspiration ratio and groundwater recharge rate;

[0146] The optimization algorithm is combined to minimize the error between the runoff simulation results and the historical measured runoff data, and the optimized runoff prediction data is generated.

[0147] The optimized basin hydrological network data provides the causal relationship between variables in the basin optimized by reinforcement learning, including nodes (such as precipitation, temperature, runoff, etc.) and their edge weights (such as the direct impact of precipitation on runoff) and lag time parameters. These data are input into the enhanced hydrological model as initial conditions and driving data to provide accurate starting state and dynamic association information for runoff simulation.

[0148] The enhanced hydrological model introduces dynamically adjusted key parameters that directly affect the simulation accuracy of the runoff process:

[0149] Soil permeability (P s ): A parameter that indicates the soil's ability to infiltrate precipitation, which is affected by soil type, pore structure, etc. Adjusting this parameter can accurately simulate the precipitation infiltration process and its effect on reducing surface runoff.

[0150] Evaporation ratio (E r ): describes the ratio of precipitation lost through evaporation and plant transpiration. Dynamic adjustment of the evapotranspiration ratio can reflect the comprehensive impact of vegetation coverage, temperature, etc. on the evapotranspiration process.

[0151] Groundwater recharge rate (G r ): Quantifies the contribution of groundwater to surface runoff recharge. Adjusting this parameter helps simulate groundwater-surface water interactions.

[0152] The runoff simulation results are compared with the historical measured runoff data through the optimization algorithm, the error (such as mean square error) is calculated, and the model parameters are adjusted inversely to minimize the error. The optimization algorithm can use the gradient descent method or the genetic algorithm. Taking the gradient descent method as an example, its update formula is:

[0153]

[0154] Among them, θ represents the parameter to be optimized (such as P s 、E r , G r ), J(θ) represents the objective function (such as runoff simulation error), and α represents the learning rate. Through continuous iterative updates, the model parameters gradually converge to the optimal value.

[0155] In practical applications, the optimized basin hydrological network data includes node variables such as precipitation and runoff and their edge weights (such as the weight of precipitation on runoff is 0.85, and the lag time is 6 hours). These data are input into the enhanced hydrological model as initial conditions to guide the simulation of the runoff process.

[0156] Initialize soil permeability P s , evaporation ratio E rand groundwater recharge rate G r For example, P s =0.3 (sand characteristics), E r =0.5 (medium vegetation cover), G r =0.1mm / h.

[0157] During the simulation, the parameter values ​​are adjusted dynamically according to the input data and model output. For example, when the precipitation increases significantly and the runoff response lag time exceeds the expectation, P is appropriately reduced. s Improve penetration capacity and shorten lag time.

[0158] The simulation results are compared with the historical measured runoff data, and the error (such as mean square error) is calculated: The parameter values ​​are adjusted in reverse through the optimization algorithm, the model is rerun and the above process is repeated until the error meets the convergence condition.

[0159] The optimized runoff prediction data finally generated includes time series data such as surface runoff and groundwater recharge, which can accurately reflect the comprehensive impact of meteorological and ecological changes on runoff dynamics.

[0160] Dynamic adjustment of soil permeability, evapotranspiration ratio and groundwater recharge rate makes the model highly adaptable to watershed characteristics and input conditions, significantly reducing the error between runoff simulation results and measured data.

[0161] The enhanced hydrological model combined with the optimization algorithm can accurately capture the runoff dynamics under different climatic conditions and watershed characteristics, for example, it is particularly prominent under high-intensity precipitation or long-term drought scenarios.

[0162] The optimized runoff prediction data can be directly used as basic data for basin hydrological assessment and risk analysis, providing a scientific basis for water resources allocation, drought warning, etc.

[0163] In this embodiment, in a basin with severe precipitation fluctuations, the optimized basin hydrological network data is input, and the initial parameters are set to P s =0.3, E r =0.6, G r =0.15mm / h. During the runoff simulation, the model dynamically adjusts the parameter values ​​according to the input data, for example:

[0164] When the precipitation intensity increases, the P s To 0.2, reducing the precipitation infiltration ratio.

[0165] When vegetation cover decreases, increase E rto 0.7, reflecting a higher evapotranspiration ratio. After 50 optimization iterations, the mean square error between the model output runoff prediction data and the measured runoff data increased from 10 mm to 2.5 mm. 2 / h reduced to 2mm 2 / h, which verifies the effectiveness of the optimization process and the reliability of the prediction results.

[0166] Based on the optimized runoff prediction data, the drought severity and duration are quantified by the standardized runoff index, and the characteristics of drought events are extracted by combining the run theory to generate drought characteristic data. In addition, the drought characteristic data and the optimized runoff prediction data are combined to generate scenario data describing extreme scenarios through a path-constrained generative adversarial network.

[0167] The Standardized Runoff Index (SRI) is a standardized indicator used to measure whether the runoff condition is abnormal. By standardizing the optimized runoff prediction data, the runoff data is converted into a dimensionless standardized indicator to describe whether the runoff state at different time steps deviates from the normal value (such as higher or lower than the long-term average). Drought severity is defined as the cumulative value of runoff anomaly, while drought duration indicates the length of time that runoff continues to be below a certain threshold.

[0168] Run theory is a statistical method used to analyze the occurrence characteristics of continuous events. In this scheme, based on run theory, when the standardized runoff index is lower than the set drought threshold, it is marked as the beginning of a drought event until the index rises above the threshold. By analyzing the intensity (accumulated runoff anomaly) and duration (duration of the drought state) of each drought event, data describing the characteristics of drought are generated.

[0169] Generative Adversarial Network (GAN) generates high-quality extreme scenario data through adversarial training of generators and discriminators. Path-constrained GAN introduces physical constraints to ensure that the generated scenario data conforms to the actual basin hydrological dynamics and physical laws:

[0170] Generator: Generates potential extreme scenario data based on input drought characteristic data and optimized runoff prediction data.

[0171] Discriminator: Determines whether the generated data is consistent with the real scene data, and improves the performance of the generator through adversarial training.

[0172] Path constraints: Ensure that the temporal and spatial characteristics of the generated data are consistent with the actual hydrological processes, for example, the changing trend of runoff should be consistent with the dynamics of precipitation and evapotranspiration.

[0173] In practical applications, the specific implementation steps include:

[0174] (1) The optimized runoff prediction data is standardized to generate a standardized runoff index time series. The index value of each time step indicates the degree of deviation of the current runoff state. For example, a standardized runoff index below -1 indicates a drought state.

[0175] (2) Setting a drought threshold (e.g., normalized runoff index below -1).

[0176] According to the run theory, the time periods that are continuously below the threshold are marked as drought events. The intensity (accumulated runoff anomaly) and duration (the length of time that is continuously below the threshold) of each drought event are calculated.

[0177] (3) Drought characteristic data (including intensity and duration) and optimized runoff prediction data are spliced ​​as input to the generator. Potential extreme scenario data are generated, such as generating runoff anomaly sequences for a specific watershed under a historical drought event. The generated scenario data are compared with the real historical data, and the generator parameters are adjusted through feedback. Runoff dynamics and watershed physical constraints (such as water conservation conditions) are introduced to ensure that the generated scenario data are physically consistent.

[0178] (4) The final output scenario data includes extreme runoff dynamics and regional hydrological status descriptions in time series format, such as runoff anomaly amplitude and drought impact range. These data can be directly used to assess the risk and response capacity of the basin under extreme scenarios.

[0179] Through the standardized runoff index and run theory, the intensity and duration of drought events can be quantified into high-dimensional characteristic data, significantly improving the detailed description of the drought process.

[0180] The scenario data generated by the path-constrained GAN is not only consistent with the actual historical data in statistical distribution, but also can generate high-confidence scenarios that conform to hydrological dynamics under the physical constraints of the basin.

[0181] The generated scenario data provides an important basis for subsequent basin hydrological assessment and extreme scenario response analysis, and supports practical applications such as drought early warning and resource scheduling.

[0182] In an implementation example, in a river basin with frequent droughts, the optimized runoff prediction data is used to generate a standardized runoff index, the drought threshold is set to -1, and the characteristics of drought events in the past 10 years are extracted. For example:

[0183] In 2012, a drought event had an intensity of -15 and lasted 30 days;

[0184] A drought event in 2015 had an intensity of -25 and lasted 50 days.

[0185] These drought characteristic data and runoff prediction data are input into the path-constrained GAN together, and extreme scenario data is generated through multiple rounds of adversarial training to simulate possible drought scenarios in the future. For example, GAN generated an extreme drought scenario that may occur in the next 50 years, in which the runoff anomaly reaches -40 and the impact range covers 70% of the area in the basin. These data verify the generation ability of the path-constrained GAN and provide a reliable scenario basis for formulating future basin drought response strategies.

[0186] Preferably, the step of extracting drought event characteristics comprises:

[0187] The standardized runoff index is calculated based on the optimized runoff prediction data. The calculation formula of the standardized runoff index is:

[0188]

[0189] Among them, SRI is the standardized runoff index, Q is the time series runoff value, μ is the mean of the time series runoff value, and σ is the standard deviation of the time series runoff value;

[0190] The Standardized Runoff Index (SRI) is an indicator used to measure the degree to which runoff data deviates from the historical average level. By standardizing the optimized runoff prediction data, runoff data at different time scales are converted into dimensionless standardized indicators. The standardization formula is as follows: The formula makes the runoff data statistically consistent by removing the mean (μ) and normalizing the standard deviation (σ). A negative SRI indicates a drought state, and a lower value indicates a more severe drought; a positive value indicates a wet state.

[0191] The cumulative intensity S and duration D of drought events are calculated in combination with the run theory. The calculation formula of the cumulative intensity is:

[0192]

[0193] Where S is the cumulative intensity of drought events, SRI i is the normalized runoff index during the i-th period of the drought period, and D is the duration of the drought event.

[0194] Run theory is a statistical tool for analyzing the characteristics of continuous events in time series. In this scheme, run theory is used to identify the time periods in the standardized runoff index series that are continuously below the set drought threshold (such as SRI < 1), the cumulative intensity S is the sum of the absolute values ​​of the standardized runoff index during the drought period; the duration D is the total length of time from the beginning to the end of the drought event, that is, the length of the run.

[0195] In practical applications, the specific implementation steps include:

[0196] (1) The optimized runoff prediction data is a high-precision runoff time series generated after correction by the enhanced hydrological model, with a consistent time step (such as daily or hourly) and basin range.

[0197] (2) Calculate the mean μ and standard deviation σ of the runoff data; apply the standardization formula to the runoff value Q at each time step to generate the corresponding SRI sequence. For example, for the runoff data recorded daily during a certain period of time:

[0198] The average daily runoff μ = 50 mm / day; the standard deviation σ = 10 mm / day; if the runoff value on a certain day is Q = 30 mm / day, then SRI = (30-50) / 10 = -2.0, indicating that the runoff on that day is significantly lower than the historical average.

[0199] (3) setting a drought threshold (e.g., SRI < -1) to mark the time step of entering a drought state;

[0200] The time period that is continuously below the threshold is identified as a drought event; for each drought event, the cumulative intensity S and duration D are calculated. For example, the SRI sequence of a drought event is -1.5, -2.0, -1.8, -1.2, -1.1, then:

[0201] Cumulative intensity S = |-1.5 |+ |-2.0 |+ |-1.8 |+ |-1.2 |+ |-1.1 |= 7.6;

[0202] Duration D = 5 days.

[0203] (4) The characteristics of each drought event (cumulative intensity S and duration D) are stored as drought characteristic data to form a structured output. For example:

[0204] Drought event 1: cumulative intensity 7.6, duration 5 days;

[0205] Drought event 2: cumulative intensity 12.3, duration 10 days.

[0206] By combining the standardized runoff index and run theory, drought events can be effectively distinguished from normal fluctuations, and the start and end time and intensity of each drought event can be identified.

[0207] The cumulative intensity and duration of drought events provide a quantitative description of the drought conditions in the basin. These indicators can not only reflect the severity of a single drought event, but also reveal the long-term drought trend through statistical analysis.

[0208] Drought characteristic data provide key inputs for subsequent scenario generation, risk assessment and decision support. For example, by analyzing historical drought events, the possible frequency and impact of future droughts can be inferred.

[0209] In this embodiment, in a typical drought basin, the standardized runoff index sequence is generated using daily runoff prediction data, and the characteristics of drought events in the past five years are extracted:

[0210] Event 1: duration 7 days, cumulative intensity 9.1;

[0211] Event 2: duration 14 days, cumulative intensity 15.7;

[0212] Event 3: Duration: 5 days, cumulative intensity: 5.4.

[0213] These data are further used for extreme scenario analysis to predict more severe drought events that may occur in the future, providing a scientific basis for watershed managers to formulate drought response strategies.

[0214] Preferably, Figure 3 As shown, the steps of generating scenario data through a path-constrained generative adversarial network include:

[0215] The generator combines the node and edge weights of the watershed hydrological network to generate extreme scenario data that meets the constraints;

[0216] The discriminator verifies the credibility of the generated scenario data through optimal transmission theory to ensure the physical consistency of the scenario data.

[0217] The Generative Adversarial Network consists of two parts: the generator and the discriminator. It generates high-quality data through adversarial training:

[0218] Generator: Generates potential extreme scenario data based on the input watershed hydrological network data (including node and edge weights). Discriminator: Compares the distribution of generated data with real data, and guides the generator to generate more credible data through feedback. In this solution, GAN not only generates scenario data, but also improves the rationality and consistency of the data by introducing path constraints and physical rules.

[0219] Path constraints are the innovation of this solution, ensuring that the generated scenario data conforms to the physical constraints and dynamic characteristics of the basin hydrological network. The key to path constraints include:

[0220] Node constraints: The dynamic changes of node variables (such as precipitation and runoff) must conform to historical observations and statistical laws. Edge weight constraints: Edge weights (such as the intensity of the impact of precipitation on runoff) must be consistent with the optimized basin hydrological network data to ensure that the causal relationship between variables remains stable.

[0221] The discriminator verifies the credibility of the generated scenario data through the optimal transmission theory. The optimal transmission theory calculates the transmission distance between the generated data distribution and the real data distribution. The closer the generated data is to the real data, the smaller the transmission distance and the higher the credibility. This process ensures that the generated data is not only consistent with the real data in terms of statistical characteristics, but also conforms to the hydrological laws of the basin in terms of physical characteristics.

[0222] In practical applications, the specific implementation steps include:

[0223] (1) The optimized watershed hydrological network data, including node variables (such as precipitation, temperature, runoff, etc.) and edge weights (such as the intensity of the direct impact of precipitation on runoff), serve as the initial input of the generator.

[0224] (2) The node variables and edge weights are used as input feature vectors and input into the generator model;

[0225] Based on the input features, the generator generates potential extreme scenario data. For example, the precipitation intensity in the node variable is simulated as 1.2 times the historical extreme value; the runoff change is simulated as a downward trend for 5 consecutive days in combination with historical observations.

[0226] The generated scenario data include time series runoff changes, watershed responses under extreme weather conditions, etc.

[0227] (3) The discriminator calculates the distance (transmission distance) between the distribution of generated scenario data and the distribution of real data based on the optimal transmission theory. The generated data is fed back through the discriminator. If the credibility is low, the generator adjusts the parameters and regenerates the data until the transmission distance reaches the set threshold to ensure the credibility of the generated data.

[0228] (4) In the process of generator generation, a path constraint function is added to impose physical rules on the generated data. For example, the conversion of precipitation to runoff must comply with the edge weight constraint to reflect the true contribution of precipitation to runoff. The runoff dynamics must satisfy the water conservation relationship to avoid abnormal data that does not conform to physical laws.

[0229] (5) The final output scenario data includes the basin hydrological dynamics under extreme meteorological conditions, such as the runoff change sequence under continuous drought conditions, the flood response caused by extreme precipitation, etc. These data can be directly used for basin hydrological risk assessment and decision support.

[0230] The generated scenario data can truly reflect the hydrological dynamics of the basin under extreme meteorological conditions, with high credibility and physical consistency. The introduction of path constraints ensures that the generated data conforms to the physical laws of the basin hydrological network and avoids invalid data due to instability in GAN training. High-quality scenario data can be used to analyze the potential impact of climate change on the basin and provide a scientific basis for drought response, flood warning and water resources scheduling.

[0231] In an embodiment, in a drought basin, the optimized basin hydrological network data is input, and the generator generates extreme scenario data, for example:

[0232] The 30-day continuous precipitation was 0.8 times the historical minimum, the runoff decreased by 50%, and the groundwater level decreased by 20%; under the extreme precipitation scenario, the single-day precipitation reached 1.5 times the historical record, and the runoff peak increased by 30%.

[0233] The discriminator verifies the credibility of the generated data through the optimal transmission theory. After the generator adjusts the parameters several times, the distribution error between the final output scenario data and the real historical data is reduced to 5%. The generated scenario data is used to analyze the impact of extreme meteorological events that may occur in the next 50 years on the basin hydrology, providing a decision-making basis for regional water resources planning.

[0234] like Figure 4 As shown, based on the scenario data, a dynamic joint distribution model of drought characteristics is constructed, and a multi-scenario risk assessment is performed on the scenario data in combination with the dynamic joint distribution model. Based on the assessment results, basin hydrological assessment data is generated to evaluate the comprehensive response of drought characteristics and hydrological conditions in the basin.

[0235] Preferably, the step of constructing a dynamic joint distribution model of drought characteristics based on scenario data comprises:

[0236] The probability distribution of drought characteristics is calculated using the dynamic kernel density estimation method. The calculation formula of the dynamic kernel density estimation is:

[0237]

[0238] Among them, f(x) is the probability density value at the point x to be estimated, n is the number of samples, h is the smoothing parameter, and x i is the value of the i-th sample point, K is the kernel function;

[0239] The dynamic joint distribution model performs multi-scenario risk assessment on scenario data and calculates the occurrence probability and distribution characteristics of drought characteristics under different scenarios.

[0240] The dynamic joint distribution model is used to quantify the joint probability distribution of drought characteristics (such as intensity and duration) under different scenarios. By considering the dynamic change characteristics of time series data, the model not only describes the marginal probability distribution of drought characteristics, but also describes the dependencies between them (such as the positive correlation between intensity and duration).

[0241] Dynamic Kernel Density Estimation is a non-parametric method for calculating probability distribution. Its core is to use the kernel function KKK to smooth sample data and calculate the probability density of the point to be estimated. Its expression is:

[0242] Dynamic kernel density estimation generates a dynamic joint distribution model by performing probability density estimation on historical scenario data, which is used to describe the distribution characteristics of drought characteristics under different scenarios.

[0243] Based on the dynamic joint distribution model, multi-scenario risk assessment is performed on scenario data to calculate the probability of occurrence and distribution characteristics of drought characteristics under different scenarios. For example:

[0244] In scenario A, the distribution of drought severity is concentrated in the lower value range and the duration is shorter;

[0245] In scenario B, the distribution of drought severity is concentrated in the higher value range and the duration is significantly prolonged. Multi-scenario risk assessment helps quantify the risk level and potential impact by calculating the probability distribution of drought characteristics under each scenario.

[0246] The specific implementation includes the following steps:

[0247] (1) The input data include optimized runoff prediction data and drought characteristic data, which contain key variables (such as precipitation intensity and runoff) under different scenarios. The data are standardized to eliminate the impact of dimensions and ensure the comparability of model calculation results.

[0248] (2) Probability density estimation of drought intensity and duration is performed through dynamic kernel density estimation. The Gaussian kernel function is used as a smoothing tool to calculate the joint distribution of drought characteristics under each scenario. The output dynamic joint distribution model includes a probability distribution matrix of drought characteristics, which is used to describe the distribution characteristics and interdependence of drought characteristics under different scenarios.

[0249] (3) Using the dynamic joint distribution model, calculate the joint probability of drought intensity and duration in each scenario. For example, in scenario C:

[0250] The probability of an extreme drought event with an intensity greater than 20 and lasting more than 10 days is 15%, and the probability of an extreme drought event with an intensity greater than 30 is 5%. The risk levels under different scenarios are quantified and ranked to provide a basis for assessing the occurrence trend and impact range of drought events.

[0251] (4) Based on the results of multi-scenario risk assessment, the basin hydrological assessment data is generated, including the distribution information of drought characteristics, analysis of differences between scenarios, and the comprehensive response of basin hydrological conditions. The output data can be presented as probability distribution maps, cumulative probability curves, or spatial distribution maps for easy visualization analysis.

[0252] The dynamic joint distribution model provides a clear mathematical description of the probability distribution of drought characteristics, and through multi-scenario risk assessment, it can quantify the intensity and scope of drought risks under different scenarios.

[0253] The watershed hydrological assessment data provides a scientific basis for watershed managers, such as predicting possible extreme drought events in the future and formulating response measures for water resource allocation and risk prevention and control.

[0254] Since the dynamic kernel density estimation method is highly adaptable to time series changes, the model can capture the nonlinear characteristics in scenario data and ensure the accuracy of the evaluation results.

[0255] In an embodiment, in a typical drought basin, scenario A and scenario B are generated based on historical data and optimized runoff prediction data:

[0256] Scenario A: 20% reduction in precipitation and 15% decrease in runoff;

[0257] Scenario B: 50% reduction in precipitation and 45% decrease in runoff.

[0258] The joint distribution model is constructed by dynamic kernel density estimation, and the calculation results show:

[0259] In scenario A, the probability of drought severity being 15 is 30%, and the probability of duration being 10 days is 25%;

[0260] In scenario B, the probability of drought severity exceeding 30 is 10%, and the probability of duration exceeding 20 days is 5%.

[0261] The assessment results were used to generate basin hydrological assessment data, which showed that the drought risk under scenario B was significantly higher than that under scenario A, which could lead to greater ecological and economic losses. Based on this, managers developed a zoning water restriction plan and an emergency water source scheduling plan.

[0262] like Figure 5 As shown, a system for implementing the watershed hydrological assessment method under climate change comprises:

[0263] The data acquisition module is used to collect meteorological data, geographic data, groundwater dynamics data, vegetation cover dynamics data and social water use behavior data, and clean and standardize the collected data; collect multi-source heterogeneous data such as meteorology, geography, groundwater dynamics, vegetation cover and social water use behavior, eliminate noise and dimensional differences through data cleaning and standardization, and provide high-quality input for subsequent analysis.

[0264] The data fusion module is connected to the data acquisition module and is used to generate fused feature data and causal path data through a multimodal fusion model, wherein the causal path data reflects the causal relationship and dynamic association between meteorological variables, hydrological variables and ecological variables; the multimodal fusion model is used to convert multi-source data into unified fused feature data, and the dynamic causal relationship between meteorological variables, hydrological variables and ecological variables is extracted in combination with causal analysis to generate causal path data for describing the complex interactions between variables in the basin.

[0265] The watershed network optimization module is connected to the data fusion module and is used to construct a directed graph structure of the watershed hydrological network based on the fused feature data and causal path data, optimize the node and edge weights in the directed graph by combining reinforcement learning, and generate optimized watershed hydrological network data; based on the fused feature data and causal path data, construct a directed graph structure of the watershed hydrological network. Through reinforcement learning, the node and edge weights are optimized and the network structure is dynamically adjusted to more accurately reflect the impact of climate change on watershed hydrology.

[0266] The runoff simulation module is connected to the watershed network optimization module and is used to input the optimized watershed hydrological network data into the enhanced hydrological model for runoff simulation, and to correct the runoff simulation results by dynamically adjusting the model parameters to generate optimized runoff prediction data; the optimized watershed network data is input into the enhanced hydrological model, and the runoff simulation results are corrected by dynamically adjusting the model parameters (such as soil permeability, evapotranspiration ratio, etc.), and the optimized runoff prediction data are generated to ensure the reliability of the simulation results.

[0267] The drought characteristic extraction module is connected to the runoff simulation module and is used to calculate the standardized runoff index based on the optimized runoff prediction data, extract the characteristics of drought events in combination with the run theory, and generate drought characteristic data; use the optimized runoff prediction data, combined with the standardized runoff index and the run theory, to quantify the intensity and duration of drought events, generate drought characteristic data, and provide key input for subsequent extreme scenario analysis.

[0268] The scenario generation module is connected to the drought feature extraction module and is used to combine the drought feature data and the optimized runoff prediction data to generate scenario data describing extreme scenarios through a path-constrained generative adversarial network; generate extreme scenario data that conforms to physical consistency through a path-constrained generative adversarial network; and perform multi-scenario risk assessment on the scenario data based on a dynamic joint distribution model to quantify the probability of occurrence and distribution characteristics of drought features under different scenarios.

[0269] The assessment module is connected to the scenario generation module and is used to construct a dynamic joint distribution model of drought characteristics based on scenario data, conduct multi-scenario risk assessment on scenario data in combination with the dynamic joint distribution model, and generate basin hydrological assessment data based on the assessment results, wherein the basin hydrological assessment data includes distribution information of drought characteristics, dynamic changes of runoff, and comprehensive response analysis of multiple scenario superpositions. Combined with the outputs of all modules, comprehensive basin hydrological assessment data is generated, including drought characteristic distribution, dynamic changes of runoff, and response analysis of multiple scenario superpositions, providing a scientific basis for climate adaptive management and decision-making.

[0270] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware.

[0271] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for watershed hydrological assessment under climate change, characterized in that: The following steps are involved: Collect meteorological data, geographic data, groundwater dynamics data, vegetation cover dynamics data and social water use behavior data, clean and standardize the collected data, and generate fusion feature data and causal path data through a multimodal fusion model. The causal path data reflects the causal relationship and dynamic association between meteorological, hydrological and ecological variables; Based on the fusion of feature data and causal path data, a directed graph structure of the basin hydrological network is constructed. The node and edge weights in the directed graph are optimized by combining reinforcement learning to generate optimized basin hydrological network data, which is then input into the enhanced hydrological model for runoff simulation. The runoff simulation results are corrected by dynamically adjusting the model parameters to generate optimized runoff prediction data. Based on the optimized runoff prediction data, the drought severity and duration are quantified by the standardized runoff index, and the characteristics of drought events are extracted by combining the run theory to generate drought characteristic data. In addition, the drought characteristic data and the optimized runoff prediction data are combined to generate scenario data describing extreme scenarios through a path-constrained generative adversarial network. Based on the scenario data, a dynamic joint distribution model of drought characteristics is constructed. Multi-scenario risk assessment is carried out on the scenario data in combination with the dynamic joint distribution model. Based on the assessment results, basin hydrological assessment data is generated to evaluate the comprehensive response of drought characteristics and hydrological conditions in the basin.

2. The basin hydrological assessment method under climate change according to claim 1, characterized in that: The collected meteorological data include precipitation data, temperature data and humidity data recorded hourly; the geographic data include digital elevation models and land use type maps; the groundwater dynamics data include monitoring well water level data; the vegetation cover dynamics data include vegetation cover change data calculated based on the normalized vegetation index; the social water use behavior data include agricultural irrigation water volume and industrial water volume counted by region.

3. The method for watershed hydrological assessment under climate change according to claim 1, characterized in that: The multimodal fusion model generates fusion feature data through the following process: Extract spatial features through convolutional neural networks; Extract time series features using long short-term memory networks; The extracted spatial features and time series features are input into the multi-layer perceptron network for fusion to generate fused feature data.

4. The method for watershed hydrological assessment under climate change according to claim 1, characterized in that: The causal path data is generated through a causal network model, which is based on Granger causality analysis and a self-supervised learning algorithm to extract the causal relationship between meteorological data, hydrological data and ecological variables, and represents the causal path through a directed graph. The causal path data includes causal relationship weights and lag time parameters.

5. The method for watershed hydrological assessment under climate change according to claim 1, characterized in that: The steps to construct the directed graph structure of the watershed hydrological network include: The meteorological variables, hydrological variables and ecological variables in the causal path data are defined as network nodes; The reinforcement learning agent adjusts the weights of the edges in the network to optimize the connection strength between nodes; Output optimized watershed hydrological network data for subsequent runoff simulation.

6. The method for watershed hydrological assessment under climate change according to claim 1, characterized in that: The steps of runoff simulation using the enhanced hydrological model include: Input the optimized watershed hydrological network data into the enhanced hydrological model; Dynamically adjust soil permeability, evapotranspiration ratio and groundwater recharge rate; The optimization algorithm is combined to minimize the error between the runoff simulation results and the historical measured runoff data, and the optimized runoff prediction data is generated.

7. The method for watershed hydrological assessment under climate change according to claim 1, characterized in that: The steps to extract drought event characteristics include: The standardized runoff index is calculated based on the optimized runoff prediction data. The calculation formula of the standardized runoff index is: Among them, SRI is the standardized runoff index, Q is the time series runoff value, μ is the mean of the time series runoff value, and σ is the standard deviation of the time series runoff value; The cumulative intensity S and duration D of drought events are calculated in combination with the run theory. The calculation formula of the cumulative intensity is: Where S is the cumulative intensity of drought events, SRI i is the normalized runoff index during the i-th period of the drought period, and D is the duration of the drought event.

8. The method for watershed hydrological assessment under climate change according to claim 1, characterized in that: The steps of generating scenario data through path-constrained generative adversarial networks include: The generator combines the node and edge weights of the watershed hydrological network to generate extreme scenario data that meets the constraints; The discriminator verifies the credibility of the generated scenario data through optimal transmission theory to ensure the physical consistency of the scenario data.

9. The method for watershed hydrological assessment under climate change according to claim 1, characterized in that: The steps of constructing a dynamic joint distribution model of drought characteristics based on scenario data include: The probability distribution of drought characteristics is calculated using the dynamic kernel density estimation method. The calculation formula of the dynamic kernel density estimation is: Among them, f(x) is the probability density value at the point x to be estimated, n is the number of samples, h is the smoothing parameter, and x i is the value of the i-th sample point, K is the kernel function; The dynamic joint distribution model performs multi-scenario risk assessment on scenario data and calculates the occurrence probability and distribution characteristics of drought characteristics under different scenarios.

10. A system for implementing the watershed hydrological assessment method under climate change according to any one of claims 1 to 9, characterized in that: include: Data collection module, used to collect meteorological data, geographic data, groundwater dynamic data, vegetation cover dynamic data and social water use behavior data, and clean and standardize the collected data; A data fusion module, connected to the data acquisition module, for generating fusion feature data and causal path data through a multimodal fusion model, wherein the causal path data reflects the causal relationship and dynamic association between meteorological variables, hydrological variables and ecological variables; A watershed network optimization module, connected to the data fusion module, is used to construct a directed graph structure of the watershed hydrological network based on the fused feature data and the causal path data, optimize the node and edge weights in the directed graph in combination with reinforcement learning, and generate optimized watershed hydrological network data; A runoff simulation module is connected to the watershed network optimization module and is used to input the optimized watershed hydrological network data into the enhanced hydrological model for runoff simulation, and to correct the runoff simulation results by dynamically adjusting the model parameters to generate optimized runoff prediction data; A drought feature extraction module, connected to the runoff simulation module, is used to calculate the standardized runoff index based on the optimized runoff prediction data, extract drought event features in combination with the run theory, and generate drought feature data; A scenario generation module, connected to the drought feature extraction module, for combining drought feature data and optimized runoff prediction data to generate scenario data describing extreme scenarios through a path-constrained generative adversarial network; An assessment module is connected to the scenario generation module, and is used to construct a dynamic joint distribution model of drought characteristics based on scenario data, perform multi-scenario risk assessment on the scenario data in combination with the dynamic joint distribution model, and generate watershed hydrological assessment data based on the assessment results, wherein the watershed hydrological assessment data includes distribution information of drought characteristics, dynamic changes in runoff, and comprehensive response analysis of multiple scenario superpositions.

Images