A method and system for snowmelt simulation and risk early warning

Abstract

This invention provides a snowmelt simulation and risk early warning method and system, belonging to the field of flood early warning technology. The method includes: collecting and preprocessing multi-source meteorological, geographic information, and snow cover characteristic data of the target area; constructing a snowmelt simulation model considering multiple factors, using the CEEMDAN algorithm and LSTM network to predict snowmelt amount, runoff, and soil moisture content, and introducing a multi-head attention mechanism; dividing the spatiotemporal grid for hourly simulation calculations to obtain spatiotemporal distribution results; setting a risk assessment index system and calculating a snowmelt risk index; determining whether the risk index exceeds a threshold and outputting an early warning result; if it exceeds, matching the risk level and drawing a risk zoning map; if it does not exceed, marking it as low risk or safe. This invention, employing the above-mentioned snowmelt simulation and risk early warning method and system, achieves accurate prediction and timely early warning of snowmelt flood risks, effectively improving disaster prevention and mitigation capabilities and reducing potential losses and hazards caused by snowmelt floods.

Description

Technical Field

[0001] This invention relates to the field of flood early warning technology, and in particular to a snowmelt simulation and risk warning method and system. Background Technology

[0002] Snowmelt floods are a common natural disaster, especially in high-altitude and cold mountainous areas, where melting snow can lead to severe flooding. Accurately predicting snowmelt flood risks is of great significance for disaster prevention and mitigation.

[0003] In existing technologies, some progress has been made in methods for early warning of snowmelt flood risks. For example, patent publication number CN111080030B discloses a method, device, electronic device, and storage medium for predicting snowmelt floods. This method obtains rain and snowfall distribution data and temperature distribution data for a target area, extracts precipitation characteristic data and temperature characteristic data, and determines the risk level of snowmelt floods. This method combines current temperature and precipitation conditions to assess and warn of snowmelt flood risks over a longer period, providing visual assistance for flood monitoring, early warning, and emergency response in areas prone to snowmelt floods.

[0004] Furthermore, patent CN116341208A discloses a snowmelt flood emergency early warning method based on snowmelt simulation. This method generates a three-dimensional snow model by acquiring snow cover and environmental characteristics of a preset area, and then combines this with weather forecast information to simulate snowmelt and obtain a snowmelt flood risk index. This method quantifies risk through model simulation, improving the accuracy and timeliness of early warnings.

[0005] However, existing technologies still have some shortcomings. For example, some methods still have room for improvement in data fusion and model building, failing to fully utilize the comprehensive advantages of multi-source data; in terms of risk assessment and early warning response, the reliability of early warning data in some methods is low, and they cannot fully reflect the degree of risk of snowmelt floods; moreover, the early warning information dissemination and emergency response processes are not perfect, making it difficult to achieve accurate and timely early warnings and effective emergency response. Summary of the Invention

[0006] The purpose of this invention is to provide a snowmelt simulation and risk warning method and system, which realizes accurate prediction and timely warning of snowmelt flood risk, effectively improves disaster prevention and mitigation capabilities, and reduces potential losses and hazards caused by snowmelt floods.

[0007] To achieve the above objectives, the present invention provides a snow melting simulation and risk warning method, comprising the following steps:

[0008] Collect multi-source meteorological data, geographic information data, and snow cover characteristic data of the target area, and perform preprocessing to obtain preprocessed data;

[0009] A snow melting simulation model is established by comprehensively considering the energy input to the snow surface from solar radiation, air temperature, and wind speed, as well as the heat conduction and phase change processes inside the snow layer.

[0010] The preprocessed data was used as input to the snowmelt simulation model. The model was divided into spatiotemporal grids and time-by-time simulation calculations were performed to obtain the spatiotemporal distribution results of snowmelt amount, runoff and soil moisture content.

[0011] A snowmelt risk assessment index system was established. Hourly snowmelt rate data was extracted from snowmelt simulation records, and the first, second, and third snowmelt rates were calculated. Combined with the spatiotemporal distribution results of the obtained snowmelt amount, runoff, and soil moisture content, the snowmelt risk index was calculated.

[0012] Obtain the preset risk threshold, determine whether the snow melting risk index exceeds the preset threshold, and output the warning result.

[0013] Preferably, the multi-source meteorological data includes temperature, precipitation, wind speed, and humidity; the geographic information data includes topography, landforms, and soil type; and the snow cover characteristic data includes snow depth, density, and water content.

[0014] Preferably, preprocessing includes data cleaning, spatial interpolation, data standardization, and data fusion.

[0015] Preferably, a snowmelt simulation model is established by comprehensively considering the energy input to the snow surface from solar radiation, air temperature, and wind speed, as well as the heat conduction and phase change processes within the snow layer. The specific operation is as follows:

[0016] Establish a set of equations for the physical process of snow melting:

[0017]

[0018] Among them, Q in T represents the total energy input to the snow surface, R represents solar radiation, and T represents solar radiation. a V represents air temperature. w T represents wind speed, α and β represent empirical coefficients, and T represents wind speed. s Let Q represent the temperature inside the snow layer, t represent time, z represent the snow layer depth, K represent the thermal conductivity, L represent the latent heat of phase change, θ represent the water content of the snow layer, and Q represent the temperature inside the snow layer. out This represents the long-wave radiation loss from the snow surface;

[0019] The preprocessed data is decomposed into multiple IMF components using the CEEMDAN algorithm;

[0020] Each IMF component is predicted using an LSTM network. The input to the LSTM network is the decomposed IMF component, and the output is the predicted snowmelt amount, runoff, and soil moisture content.

[0021] Introducing a multi-head attention mechanism enhances the model's attention to different features;

[0022] The specific formula for the snow melting simulation model is as follows:

[0023]

[0024] in, Let represent the amount of snow melt at time t and spatial location (i,j), and γ represent the weighting coefficient. This represents the integrated data at time t-1 and spatial location (i,j), where i and j represent the row and column of the spatial grid, and P represents the set of equations for the snow melting physical process.

[0025] Preferably, the preprocessed data is used as input to the snowmelt simulation model, and hourly simulation calculations are performed by dividing the spatiotemporal grid to obtain the spatiotemporal distribution results of snowmelt amount, runoff, and soil moisture content. The specific operation is as follows:

[0026] Divide the spacetime into grids, with each grid cell corresponding to a specific spatial location (i,j);

[0027] For each time step t, meteorological data, geographic information data, and snow cover characteristic data for the current time step are extracted from the preprocessed data and then input into the CEEMDAN-LSTM-ATTE model to obtain the predicted values ​​of the IMF components.

[0028] By combining the predicted values ​​of the IMF components with the calculation results of the snowmelt physical process equations, the predicted values ​​of snowmelt amount, runoff and soil moisture content are obtained.

[0029] Store the predicted values ​​as the spatiotemporal distribution results at the current time step t;

[0030] Repeat the above steps until the simulation calculations for all time steps are completed and the snowmelt amount is obtained. Runoff and soil moisture content The spatiotemporal distribution results.

[0031] Preferably, the snowmelt risk assessment index system includes snowmelt rate, peak runoff, water depth, topographic slope, and soil saturation.

[0032] The preferred formula for calculating the snowmelt risk index is as follows:

[0033]

[0034] in, R represents the snowmelt risk index. m Q represents the snowmelt rate. p D represents the peak runoff. a S represents the depth of the water.s S represents soil saturation. t The slope of the terrain is represented by ω1, ω2, ω3, ω4, ω5, and ω6, which are all weighting coefficients.

[0035] The formula for calculating the snow melting rate is as follows:

[0036]

[0037] Among them, R m1 R m2 R m3 ω represents the first snowmelt rate, the second snowmelt rate, and the third snowmelt rate, respectively. m1 ω m2 ω m3 These represent the weighting coefficients for the first, second, and third snow melting rates, respectively.

[0038] Snowmelt is usually a gradual process, and the rate of snowmelt and related hydrological processes can vary significantly over different time periods.

[0039] The first 12 hours: In the early stage of snow melting, the snow begins to melt and the amount of snow melting gradually increases. The melting rate in this stage is relatively low, but it has an important impact on the subsequent snow melting process.

[0040] 12 to 36 hours: With changes in factors such as temperature, the snowmelt rate usually increases significantly, reaching its peak, and this stage contributes the most to runoff.

[0041] 36 to 72 hours: The snow melting process enters a stable phase, the snow melting rate tends to be stable, and the snow accumulation gradually decreases. This phase has an important impact on soil moisture content and groundwater recharge.

[0042] In flood warnings, it is necessary to pay attention to the contribution of different stages of the snowmelt process to runoff and flood risk. Initial snowmelt leads to increased soil moisture, mid-stage snowmelt leads to peak runoff, and late-stage snowmelt leads to the sustained impact of floods.

[0043] Understanding the temporal distribution of snowmelt processes is crucial for water resource management, as it helps in the rational allocation of water resources, prevention of floods, and ensuring the sustainable use of water resources.

[0044] The formula for calculating the first snow melting rate is as follows:

[0045]

[0046] in, This represents the amount of snow melt at time t+12 and spatial location (i,j).

[0047] The formula for calculating the second snow melt rate is as follows:

[0048]

[0049] in, This represents the amount of snow melt at time t+36 and spatial location (i,j).

[0050]

[0051] in, This represents the amount of snow melt at time t+72 and spatial location (i,j).

[0052] The formula for calculating peak runoff is as follows:

[0053]

[0054] The formula for calculating soil saturation is as follows:

[0055]

[0056] Among them, S max This indicates the maximum water holding capacity of the soil.

[0057] Preferably, when the snowmelt risk index exceeds the preset threshold, the corresponding risk level is matched according to the extent of the exceedance, and a snowmelt risk zoning map is drawn on the GIS map, marking the risk level and warning signal of each area;

[0058] If the snowmelt risk index does not exceed the preset threshold, a snowmelt risk zoning map is drawn on the GIS map, and each area is marked as low risk or safe.

[0059] This invention also provides a snow melting simulation and risk early warning system, comprising:

[0060] Data acquisition and preprocessing module: used to acquire multi-source meteorological data, geographic information data and snow cover characteristic data of the target area, and to preprocess the data to obtain preprocessed data;

[0061] Snowmelt simulation model building module: used to comprehensively consider the energy input of solar radiation, air temperature, and wind speed to the snow surface, as well as the heat conduction and phase change process inside the snow layer, to establish a snowmelt simulation model;

[0062] Simulation Calculation Module: This module takes the preprocessed data as input to the snowmelt simulation model, divides the spatiotemporal grid, performs hourly simulation calculations, and obtains the spatiotemporal distribution results of snowmelt amount, runoff, and soil moisture content.

[0063] Risk assessment and early warning classification module: used to set up the snow melting risk assessment index system, extract hourly snow melting rate data from snow melting simulation records as the first snow melting rate, the second snow melting rate and the third snow melting rate, and combine the spatiotemporal distribution results of snow melting amount, runoff and soil moisture content obtained by the simulation calculation module to calculate the snow melting risk index.

[0064] Early warning and emergency response module: Used to obtain preset risk thresholds, determine whether the snow melting risk index exceeds the preset thresholds, and output early warning results. If it exceeds the thresholds, the corresponding risk level is matched according to the extent of the exceedance, and a snow melting risk zoning map is drawn on the GIS map, marking the risk level and early warning signal of each area. If it does not exceed the thresholds, a snow melting risk zoning map is drawn on the GIS map, marking each area as low risk or safe.

[0065] Preferably, the snow melting simulation model construction module includes a physical equation set establishment unit, a data decomposition unit, a model prediction unit, and an attention mechanism introduction unit, which are respectively used to establish a physical equation set for the snow melting process, decompose the preprocessed data into multiple IMF components through the CEEMDAN algorithm, predict each IMF component through an LSTM network, and introduce a multi-head attention mechanism.

[0066] Therefore, the present invention employs the above-mentioned snow melting simulation and risk warning method and system, and the beneficial technical effects are as follows:

[0067] (1) This invention integrates multi-source meteorological data, geographic information data, and snow cover characteristic data. Compared with relying solely on meteorological data or a single data source, it provides richer data dimensions and can more comprehensively depict the driving factors and basic conditions of the snowmelt process, providing a more solid data foundation for accurate simulation and early warning. For example, by combining meteorological elements such as temperature, precipitation, and wind speed, as well as geographic information such as topography and soil type, it is possible to more accurately analyze the snowmelt characteristics and risk differences in different regions.

[0068] (2) The physical equations of the snow melting process established based on the principles of energy balance and phase change take into account the influence of solar radiation, air temperature, wind speed and other factors on the energy input of the snow surface, as well as the heat conduction and phase change process inside the snow layer. Compared with some simple models that only consider the single influence of some meteorological factors on snow melting, this set of equations can more accurately describe the physical mechanism of the snow melting process, thereby improving the scientificity and accuracy of the simulation.

[0069] Advantages of the CEEMDAN algorithm: The CEEMDAN algorithm decomposes snowmelt time series data to obtain multiple IMF components and residual terms. Compared with traditional decomposition methods such as EEMD, CEEMDAN effectively avoids mode mixing problems by adding white noise of different amplitudes and performing ensemble empirical mode decomposition, followed by noise removal through least squares fitting. The decomposition results are more stable and reliable, and can more accurately extract different frequency features from snowmelt data, providing a more favorable foundation for subsequent separate modeling and prediction.

[0070] The combination of LSTM networks and multi-head attention mechanisms: LSTM networks are constructed for each IMF component and residual term, and a multi-head attention mechanism is introduced. LSTM networks can effectively handle long-term dependencies in time series data, while the multi-head attention mechanism further enhances the model's attention to different feature dimensions and time steps, enabling the model to automatically learn and highlight important feature information. Compared to single LSTM models or other traditional time series models, such as ARIMA, it has stronger feature representation capabilities and predictive performance, and can more accurately capture the complex dynamic changes of the snowmelt process.

[0071] (3) A risk assessment index system including snowmelt rate, peak runoff, water depth, topographic slope and soil saturation was set up to comprehensively assess snowmelt risk from multiple perspectives. Compared with assessment methods that rely solely on single indicators such as snowmelt amount or runoff, this system can more comprehensively and deeply reflect the risk level and potential impact of snowmelt floods, providing a more sufficient basis for early warning decisions.

[0072] Precise early warning and emergency response: The system can accurately determine the risk level based on whether the snowmelt risk index exceeds the preset threshold, and intuitively display the risk zones through a GIS map. At the same time, it can accurately push early warning information through multiple communication channels and preset emergency response procedures and measures under different risk levels. This achieves timely and accurate release of early warning information and effective emergency response. Compared with the existing technologies where the early warning information release and emergency response procedures are not perfect, it significantly improves the ability to prevent and respond to snowmelt flood disasters. Attached Figure Description

[0073] Figure 1 This is a flowchart of a snow melting simulation and risk warning method according to the present invention;

[0074] Figure 2 A flowchart for snow melting simulation;

[0075] Figure 3 This is a structural diagram of a snow melting simulation and risk warning system according to the present invention. Detailed Implementation

[0076] The technical solution of the present invention will be further described below with reference to the accompanying drawings and embodiments.

[0077] Unless otherwise defined, the technical or scientific terms used in this invention shall have the ordinary meaning as understood by one of ordinary skill in the art to which this invention pertains.

[0078] Example 1

[0079] like Figure 1 As shown, the present invention provides a snow melting simulation and risk warning method, comprising the following steps:

[0080] 1. Taking a mountainous area as the target region, collect multi-source meteorological data, geographic information data and snow cover characteristic data of the target region, and perform preprocessing to obtain preprocessed data.

[0081] 1.1 Experimental data.

[0082] Meteorological data: temperature, precipitation, wind speed and humidity, with a time resolution of 1 hour. The experimental period was from January 1, 2022 to April 30, 2022, a total of 121 days. The data came from 10 meteorological stations in the region.

[0083] Geographic information data: topography (elevation, slope, aspect), landforms (mountains, plains, valleys) and soil types (sand, loam, clay), with a spatial resolution of 30 meters. The data are sourced from geographic information databases and field surveys.

[0084] Snow cover characteristics data: snow depth, density and water content, with a time resolution of 1 day. A total of 90 sets of data were acquired during the experimental period, and the data came from snow monitoring stations and field sampling.

[0085] 1.2 Data preprocessing.

[0086] Data cleaning: Remove outliers and erroneous records from meteorological data; supplement missing soil type information in geographic information data; smooth snow cover characteristic data and remove obviously deviating outliers.

[0087] Spatial interpolation: The spatial distribution data of the entire region is generated by using the Kriging interpolation method to analyze meteorological station data.

[0088] Data standardization: Standardize all data to the [0,1] range to facilitate model input.

[0089] Data fusion: The processed meteorological, geographic information and snow cover characteristics data are fused to form a complete dataset.

[0090] 2. Taking into account the energy input to the snow surface from solar radiation, air temperature, and wind speed, as well as the heat conduction and phase change process inside the snow layer, a snow melting simulation model is established. The preprocessed data is used as the input to the snow melting simulation model, and the spatiotemporal grid is divided to perform hourly simulation calculations to obtain the spatiotemporal distribution results of snow melting amount, runoff, and soil moisture content.

[0091] Establishment of physical equations: Based on the principles of energy balance and phase transition, establish a set of physical equations for the snow melting process, including equations on the energy input to the snow surface from solar radiation, air temperature, and wind speed, as well as equations on heat conduction and phase transition within the snow layer.

[0092]

[0093] Among them, Q in T represents the total energy input to the snow surface, R represents solar radiation, and T represents solar radiation. a V represents air temperature. w T represents wind speed, α and β represent empirical coefficients, and T represents wind speed. s Let Q represent the temperature inside the snow layer, t represent time, z represent the snow layer depth, K represent the thermal conductivity, L represent the latent heat of phase change, θ represent the water content of the snow layer, and Q represent the temperature inside the snow layer. out This represents the long-wave radiation loss on the snow surface.

[0094] like Figure 2 The diagram shows the snowmelt simulation flowchart. In this embodiment, the CEEMDAN algorithm is used to decompose the snowmelt time series data into 5 IMF components and 1 residual term. The CEEMDAN algorithm adds white noise of different amplitudes and performs ensemble empirical modulus decomposition (EEMD). Finally, the added noise is removed by least squares fitting, resulting in more stable IMF components. For example, white noise with an amplitude of 0.2 is added to the snowmelt time series data, and 100 EEMD decompositions are performed to obtain multiple IMF component sets. Then, the noise effect is removed by fitting, ultimately resulting in 5 stable IMF components and 1 residual term.

[0095] For each IMF component and residual term, a separate LSTM network is constructed for prediction. The LSTM network structure consists of 10 neurons in the input layer, 50 neurons in the hidden layer, and 1 neuron in the output layer. A multi-head attention mechanism is introduced, with four attention heads to enhance the model's attention to different features. The multi-head attention mechanism calculates attention weights for different combinations of features in the input data, enabling the model to simultaneously focus on multiple important feature dimensions. For example, for each IMF component, the multi-head attention mechanism calculates its importance weight at different time steps, and then applies these weights to the hidden layer output of the LSTM network, highlighting important time step features and thus improving prediction accuracy.

[0096] The specific formula for the snow melting simulation model is as follows:

[0097]

[0098] in, Let represent the amount of snow melt at time t and spatial location (i,j), and γ represent the weighting coefficient. This represents the integrated data at time t-1 and spatial location (i,j), where i and j represent the row and column of the spatial grid, and P represents the set of equations for the snow melting physical process.

[0099] Model training: Data from 2017-2021 was used as the training set, and data from 2022 was used as the test set. Training lasted 100 epochs with a learning rate of 0.001 and a loss function of mean squared error. During training, batch gradient descent was used with a batch size of 32. The loss on the validation set was calculated after each epoch. If the validation loss did not decrease for five consecutive epochs, training was stopped early to prevent overfitting.

[0100] Third, establish a snowmelt risk assessment index system, extract hourly snowmelt rate data from snowmelt simulation records as the first snowmelt rate, second snowmelt rate and third snowmelt rate, and calculate the snowmelt risk index by combining the spatiotemporal distribution results of snowmelt amount, runoff and soil moisture content.

[0101] Spatiotemporal grid division: The target area is divided into a 1000×1000 spatiotemporal grid, with each grid cell measuring 5km×5km.

[0102] Hourly simulation calculation: The preprocessed data is input into the model and hourly simulation calculation is performed to obtain the spatiotemporal distribution results of snow melt, runoff and soil moisture content.

[0103] Risk assessment indicator system is set as follows: snowmelt rate, peak runoff, water depth, topographic slope, and soil saturation.

[0104] Snowmelt risk index calculation: Calculate the snowmelt risk index for each grid unit according to the indicator system;

[0105] The formula for calculating the snowmelt risk index is as follows:

[0106]

[0107] in, R represents the snowmelt risk index. m Q represents the snowmelt rate. p D represents the peak runoff. a S represents the depth of the water. s S represents soil saturation. tThe slope of the terrain is represented by ω1, ω2, ω3, ω4, ω5, and ω6, which are all weighting coefficients.

[0108] Snowmelt is usually a gradual process, and the rate of snowmelt and related hydrological processes can vary significantly over different time periods.

[0109] The first 12 hours: In the early stage of snow melting, the snow begins to melt and the amount of snow melting gradually increases. The melting rate in this stage is relatively low, but it has an important impact on the subsequent snow melting process.

[0110] 12 to 36 hours: With changes in factors such as temperature, the snowmelt rate usually increases significantly, reaching its peak, and this stage contributes the most to runoff.

[0111] 36 to 72 hours: The snow melting process enters a stable phase, the snow melting rate tends to be stable, and the snow accumulation gradually decreases. This phase has an important impact on soil moisture content and groundwater recharge.

[0112] In flood warnings, it is necessary to pay attention to the contribution of different stages of the snowmelt process to runoff and flood risk. Initial snowmelt leads to increased soil moisture, mid-stage snowmelt leads to peak runoff, and late-stage snowmelt leads to the sustained impact of floods.

[0113] Understanding the temporal distribution of snowmelt processes is crucial for water resource management, as it helps in the rational allocation of water resources, prevention of floods, and ensuring the sustainable use of water resources.

[0114] The formula for calculating the first snow melting rate is as follows:

[0115]

[0116] in, This represents the amount of snow melt at time t+12 and spatial location (i,j).

[0117] The formula for calculating the second snow melt rate is as follows:

[0118]

[0119] in, This represents the amount of snow melt at time t+36 and spatial location (i,j).

[0120]

[0121] in, This represents the amount of snow melt at time t+72 and spatial location (i,j).

[0122] The formula for calculating peak runoff is as follows:

[0123]

[0124] The formula for calculating soil saturation is as follows:

[0125]

[0126] Among them, S max This indicates the maximum water holding capacity of the soil.

[0127] IV. Obtain the preset risk threshold, determine whether the snow melting risk index exceeds the preset threshold, and output the warning result.

[0128] Warning result: On March 15, 2022, the model predicted that the snow melting risk index in some areas of the target region would be high within the next 48 hours, exceeding the preset threshold. The system automatically drew a snow melting risk zoning map on the GIS map, marked the high-risk areas, and pushed warning information to relevant departments and residents via SMS and APP.

[0129] The root mean square error (RMSE) between the prediction results and the actual observations obtained by the method proposed in this invention is 0.25, the mean absolute error (MAE) is 0.18, and the coefficient of determination (R²) is [missing value]. 2 The R² value was 0.89; the RMSE for multiple linear regression was 0.45, the MAE was 0.36, and the R² value was 0.89. 2 The RSE is 0.72; the RMSE of the support vector machine is 0.38, the MAE is 0.30, and the R... 2 The value is 0.78. This indicates that the method of the present invention can more accurately simulate the snowmelt process, providing a more reliable basis for early warning of snowmelt flood risks.

[0130] like Figure 3 As shown, a snowmelt simulation and risk early warning system includes:

[0131] Data acquisition and preprocessing module: used to acquire multi-source meteorological data, geographic information data and snow cover characteristic data of the target area, and to preprocess the data to obtain preprocessed data;

[0132] Snowmelt simulation model building module: used to comprehensively consider the energy input of solar radiation, air temperature, and wind speed to the snow surface, as well as the heat conduction and phase change process inside the snow layer, to establish a snowmelt simulation model;

[0133] Simulation Calculation Module: This module takes the preprocessed data as input to the snowmelt simulation model, divides the spatiotemporal grid, performs hourly simulation calculations, and obtains the spatiotemporal distribution results of snowmelt amount, runoff, and soil moisture content.

[0134] Risk assessment and early warning classification module: used to set up the snow melting risk assessment index system, extract hourly snow melting rate data from snow melting simulation records as the first snow melting rate, the second snow melting rate and the third snow melting rate, and combine the spatiotemporal distribution results of snow melting amount, runoff and soil moisture content obtained by the simulation calculation module to calculate the snow melting risk index.

[0135] Early warning and emergency response module: Used to obtain preset risk thresholds, determine whether the snow melting risk index exceeds the preset thresholds, and output early warning results. If it exceeds the thresholds, the corresponding risk level is matched according to the extent of the exceedance, and a snow melting risk zoning map is drawn on the GIS map, marking the risk level and early warning signal of each area. If it does not exceed the thresholds, a snow melting risk zoning map is drawn on the GIS map, marking each area as low risk or safe.

[0136] The early warning issuance and emergency response module is implemented as follows:

[0137] Risk level classification.

[0138] Level I (Extremely High Risk): When the snowmelt risk index exceeds 30% or more of the preset threshold, it indicates that the area faces an extremely high risk of snowmelt flooding, which may cause severe flooding disasters.

[0139] Level II (High Risk): When the snowmelt risk index exceeds the preset threshold by 15% to 30%, it means that the area has a high risk of snowmelt floods and may experience significant flooding.

[0140] Level III (Medium Risk): When the snowmelt risk index exceeds the preset threshold of 5% to 15%, it indicates that there is a moderate risk of snowmelt flooding in the area, and there may be some degree of flooding.

[0141] Level IV (Low Risk): When the snowmelt risk index exceeds the preset threshold but is within 5%, it means that the risk of snowmelt floods in the area is low, but vigilance is still required.

[0142] Draw a map showing the risk zones for snowmelt.

[0143] Map data preparation: Obtain GIS map data of the target area, including geographic information (such as topography, landforms, water systems, etc.), administrative boundaries, and the distribution of settlements, so as to accurately mark risk areas and related details on the map.

[0144] Risk area coloring: Based on the calculated snow melt risk index of each grid cell, and according to the risk level classification standard mentioned above, different colors are used to color each grid cell. For example, Level I (extremely high risk) areas are represented by red, Level II (high risk) areas by orange, Level III (medium risk) areas by yellow, Level IV (low risk) areas by blue, and areas not exceeding the threshold are represented by green.

[0145] Mark risk levels and warning signals: On the colored map, clearly mark the risk level of each risk area, such as "extremely high risk (level I)" and "high risk (level II)".

[0146] Map Output and Display: The drawn snowmelt risk zoning map is output through geographic information system software to generate maps of different scales to meet the decision-making needs at different levels.

[0147] Early warning information dissemination and emergency response.

[0148] Early Warning Information Push: When the risk index exceeds the threshold, the system automatically matches the corresponding early warning information template according to the risk level and accurately pushes the early warning information to relevant departments (such as emergency management departments, water resources departments, meteorological departments, etc.) and residents in the risk area through various communication channels such as SMS, email, mobile APP push, and social media. The early warning information includes the location of the risk area, risk level, expected impact time, possible disaster types, and corresponding preventive measures.

[0149] Emergency Response Activation: Upon the issuance of the early warning information, the system automatically triggers the preset emergency response procedures. For different levels of risk, the corresponding emergency plan is activated. Emergency plans are implemented according to the actual conditions in each region.

[0150] Warning Lifting and Summary Assessment: Once the snowmelt process is over, the warning will be lifted based on the actual flood situation and changes in risk.

[0151] When the snowmelt risk index does not exceed the preset threshold, a snowmelt risk zoning map is drawn on the GIS map, marking each area as low-risk or safe. The specific implementation is as follows:

[0152] Map data preparation: Similar to the above procedure when the threshold is exceeded, obtain GIS map data of the target area, including geographic information, administrative boundaries, and the distribution of settlements.

[0153] Area Coloring and Labeling: Based on the calculated snowmelt risk index, areas that do not exceed the threshold are uniformly labeled as low-risk or safe. These areas can be colored green and labeled with words such as "low-risk" or "safe" on the map.

[0154] Map output and display: Maps are also output using professional geographic information system software.

[0155] The snow melting simulation model construction module includes a physical equation establishment unit, a data decomposition unit, a model prediction unit, and an attention mechanism introduction unit. These units are used to establish the physical equations of the snow melting process, decompose the preprocessed data into multiple IMF components using the CEEMDAN algorithm, predict each IMF component using an LSTM network, and introduce a multi-head attention mechanism, respectively.

[0156] The data acquisition and preprocessing module includes a data cleaning unit, a spatial interpolation unit, a data standardization unit, and a data fusion unit, which are used to clean, interpolate, standardize, and fuse the acquired data, respectively.

[0157] The simulation calculation module is specifically used to input the preprocessed data as model input, divide the spatiotemporal grid for hourly simulation calculation, and obtain the spatiotemporal distribution results of snow melt, runoff and soil moisture content.

[0158] The snowmelt risk assessment index system in the risk assessment and early warning classification module includes snowmelt rate, peak runoff, water depth, topographic slope, and soil saturation.

[0159] It is worth noting that all contents not described in detail in this invention are existing technologies and are well known to those skilled in the art.

[0160] Therefore, this invention employs the aforementioned snowmelt simulation and risk warning method and system. By integrating multi-source meteorological data, geographic information data, and snow cover characteristic data, and comprehensively considering the influence of various factors such as solar radiation, air temperature, and wind speed on the energy input of the snow surface, as well as the heat conduction and phase change processes within the snow layer, an accurate snowmelt simulation model is constructed. The model uses the advanced CEEMDAN algorithm to decompose the data and combines it with an LSTM network and a multi-head attention mechanism for prediction, improving the accuracy and reliability of the simulation. Based on this, a comprehensive snowmelt risk assessment index system is established, assessing risks from multiple dimensions such as snowmelt rate, peak runoff, water depth, terrain slope, and soil saturation, and calculating the snowmelt risk index. By comparing with preset risk thresholds, accurate prediction and timely warning of snowmelt flood risks are achieved. When the risk index exceeds the threshold, the system can match the corresponding risk level according to the extent of the exceedance, draw a snowmelt risk zoning map on the GIS map, mark the risk level and warning signal of each area, and accurately push the warning information through multiple communication channels. It also presets emergency response procedures and measures under different risk levels to ensure that the corresponding plan is automatically activated after the warning is issued, effectively improving disaster prevention and mitigation capabilities and reducing the potential losses and hazards caused by snowmelt floods.

[0161] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for simulating snow melting and providing risk early warning, characterized in that, Includes the following steps: Collect multi-source meteorological data, geographic information data, and snow cover characteristic data of the target area, and perform preprocessing to obtain preprocessed data; Taking into account the energy input to the snow surface from solar radiation, air temperature, and wind speed, as well as the heat conduction and phase change processes within the snow layer, a snow melting simulation model is established. The specific operation is as follows: Establish a set of equations for the physical process of snow melting: Among them, Q in T represents the total energy input to the snow surface, R represents solar radiation, and T represents solar radiation. a V represents air temperature. w T represents wind speed, α and β represent empirical coefficients, and T represents wind speed. s Let Q represent the temperature inside the snow layer, t represent time, z represent the snow layer depth, K represent the thermal conductivity, L represent the latent heat of phase change, θ represent the water content of the snow layer, and Q represent the temperature inside the snow layer. out This represents the long-wave radiation loss from the snow surface; The preprocessed data is decomposed into multiple IMF components using the CEEMDAN algorithm; Each IMF component is predicted using an LSTM network. The input to the LSTM network is the decomposed IMF component, and the output is the predicted snowmelt amount, runoff, and soil moisture content. Introducing a multi-head attention mechanism enhances the model's attention to different features; The specific formula for the snow melting simulation model is as follows: in, Let represent the amount of snow melt at time t and spatial location (i,j), and γ represent the weighting coefficient. This represents the integrated data at time t-1 and spatial location (i,j), where i and j represent the row and column of the spatial grid, and P represents the set of equations for the snow melting physical process. The preprocessed data was used as input to the snowmelt simulation model. The model was divided into spatiotemporal grids and time-by-time simulation calculations were performed to obtain the spatiotemporal distribution results of snowmelt amount, runoff and soil moisture content. A snowmelt risk assessment index system was established. Hourly snowmelt rate data was extracted from snowmelt simulation records, and the first, second, and third snowmelt rates were calculated. Combined with the spatiotemporal distribution results of the obtained snowmelt amount, runoff, and soil moisture content, the snowmelt risk index was calculated. Obtain the preset risk threshold, determine whether the snow melting risk index exceeds the preset threshold, and output the warning result.

2. The snow melting simulation and risk warning method according to claim 1, characterized in that, Multi-source meteorological data includes temperature, precipitation, wind speed, and humidity; geographic information data includes topography, landforms, and soil type; snow cover characteristics data includes snow depth, density, and water content.

3. The snow melting simulation and risk warning method according to claim 1, characterized in that, Preprocessing includes data cleaning, spatial interpolation, data standardization, and data fusion.

4. The snow melting simulation and risk warning method according to claim 1, characterized in that, The preprocessed data is used as input to the snowmelt simulation model. Spatiotemporal grids are divided for hourly simulation calculations to obtain the spatiotemporal distribution results of snowmelt amount, runoff, and soil moisture content. The specific operations are as follows: Divide the spacetime into grids, with each grid cell corresponding to a specific spatial location (i,j); For each time step t, meteorological data, geographic information data, and snow cover characteristic data for the current time step are extracted from the preprocessed data and then input into the CEEMDAN-LSTM-ATTE model to obtain the predicted values ​​of the IMF components. By combining the predicted values ​​of the IMF components with the calculation results of the snowmelt physical process equations, the predicted values ​​of snowmelt amount, runoff and soil moisture content are obtained. Store the predicted values ​​as the spatiotemporal distribution results at the current time step t; Repeat the above steps until the simulation calculations for all time steps are completed and the snowmelt amount is obtained. Runoff and soil moisture content The spatiotemporal distribution results.

5. The snow melting simulation and risk warning method according to claim 1, characterized in that, The snowmelt risk assessment index system includes snowmelt rate, peak runoff, water depth, topographic slope, and soil saturation.

6. The snow melting simulation and risk warning method according to claim 1, characterized in that, The formula for calculating the snowmelt risk index is as follows: in, R represents the snowmelt risk index. m Q represents the snowmelt rate. p D represents the peak runoff. a S represents the depth of the water. s S represents soil saturation. t The slope of the terrain is represented by ω1, ω2, ω3, ω4, ω5, and ω6, which are all weighting coefficients. The formula for calculating the snow melting rate is as follows: Among them, R m1 R m2 R m3 ω represents the first snowmelt rate, the second snowmelt rate, and the third snowmelt rate, respectively. m1 ω m2 ω m3 These represent the weighting coefficients for the first snow melting rate, the second snow melting rate, and the third snow melting rate, respectively.

7. The snow melting simulation and risk warning method according to claim 1, characterized in that, When the snowmelt risk index exceeds the preset threshold, the corresponding risk level is matched according to the extent of the exceedance, and a snowmelt risk zoning map is drawn on the GIS map, marking the risk level and warning signal of each area; If the snowmelt risk index does not exceed the preset threshold, a snowmelt risk zoning map is drawn on the GIS map, and each area is marked as low risk or safe.

8. A snow melting simulation and risk early warning system, characterized in that, The method for performing snow melting simulation and risk warning as described in any one of claims 1-7 includes: The data acquisition and preprocessing module is used to collect multi-source meteorological data, geographic information data and snow cover characteristic data of the target area, and to preprocess the data to obtain the preprocessed data. The snow melting simulation model building module is used to comprehensively consider the energy input of solar radiation, air temperature, and wind speed to the snow surface, as well as the heat conduction and phase change process inside the snow layer, to establish a snow melting simulation model. The simulation calculation module is used to take the preprocessed data as input to the snowmelt simulation model, divide the spatiotemporal grid to perform hourly simulation calculations, and obtain the spatiotemporal distribution results of snowmelt amount, runoff and soil moisture content; The risk assessment and early warning classification module is used to set the snow melting risk assessment index system, extract hourly snow melting rate data from snow melting simulation records as the first snow melting rate, the second snow melting rate and the third snow melting rate, and combine the spatiotemporal distribution results of snow melting amount, runoff and soil moisture content obtained by the simulation calculation module to calculate the snow melting risk index. The early warning and emergency response module is used to obtain preset risk thresholds, determine whether the snow melting risk index exceeds the preset thresholds, and output early warning results. If it exceeds the thresholds, it matches the corresponding risk level according to the extent of the exceedance and draws a snow melting risk zoning map on the GIS map, marking the risk level and early warning signal of each area. If it does not exceed the thresholds, it draws a snow melting risk zoning map on the GIS map, marking each area as low risk or safe.

9. A snow melting simulation and risk early warning system according to claim 8, characterized in that, The snow melting simulation model construction module includes a physical equation establishment unit, a data decomposition unit, a model prediction unit, and an attention mechanism introduction unit. These units are used to establish the physical equations of the snow melting process, decompose the preprocessed data into multiple IMF components using the CEEMDAN algorithm, predict each IMF component using an LSTM network, and introduce a multi-head attention mechanism, respectively.

Images