Flood control four-pre system based on digital twinning

Abstract

The invention relates to the technical field of flood control forecasting, in particular to a flood control four-pre system based on digital twinning, which comprises a database construction module used for constructing a drainage basin database and an extreme meteorological database; the data analysis module is used for constructing a hydrological twinborn model of the target area, and determining a plurality of key early warning areas and comprehensive influence indexes corresponding to the associated extreme meteorological data; the prediction simulation module is used for performing flood prediction simulation based on the adjusted hydrological twinborn model and the extreme meteorological database so as to obtain flood propulsion parameters of the flood inundation area and each key early warning area; and the data judgment module is used for determining flood control early warning parameters of the target region based on the flood risk level of the target region, and determining regional flood control indexes of the target region based on the flood control early warning parameters and the regional characteristics of the key early warning regions. The flood control early warning accuracy and the emergency response efficiency can be improved.

Description

Technical Field

[0001] This invention relates to the field of flood forecasting technology, and in particular to a flood four-prevention system based on digital twins. Background Technology

[0002] With the intensification of global climate change and the acceleration of urbanization, the frequency and intensity of flood disasters are constantly increasing, seriously threatening people's lives and property and the normal operation of cities, posing a severe challenge to traditional flood control systems. Flood control work is of paramount importance to ensuring the safety of people's lives and property and social stability. Traditional flood control systems mainly rely on historical data and experience, using indicators such as water levels and flow rates for flood warnings, which has limitations such as insufficient accuracy in warnings and untimely emergency response. The flood control "four-prevention" system refers to a comprehensive system that enables flood control departments to conduct flood forecasting, early warning, rehearsals, and contingency plan development when facing flood disasters.

[0003] Chinese patent application publication number CN117726031A discloses a data and model-based four-prevention system. Using base plate data of the target monitoring area acquired by the base plate data acquisition unit as a foundation, it utilizes a simulation engine to construct water conservancy professional models for the target monitoring area, including flood forecasting, flood evolution, flood control, and flood inundation early warning. A digital twin base platform is built to develop flood control "four-prevention" applications for the target monitoring area, supporting accurate decision-making for flood control and disaster reduction. It gathers knowledge such as forecasting and control schemes, historical scenarios, business rules, and expert experience, and through extraction, fusion, and reasoning, develops a business-specific knowledge engine to support the flood control "four-prevention" business of the target monitoring area, providing knowledge support for basin flood forecasting, sluice gate optimization scheduling, and safe operation management.

[0004] The existing technology has the following problems: it is difficult to guarantee the accuracy of flood warning and the efficiency of emergency response by only constructing water conservancy professional models such as flood forecasting, flood evolution, flood control and flood inundation early warning for regional flood control and disaster reduction decisions. Summary of the Invention

[0005] To address this, the present invention provides a flood prevention four-prevention system based on digital twins, which overcomes the problem in the prior art that only considers flood prevention and disaster reduction decisions, making it difficult to guarantee the accuracy of flood warnings and the efficiency of emergency response.

[0006] To achieve the above objectives, the present invention provides a flood prevention four-prevention system based on digital twins, comprising:

[0007] The database construction module is used to acquire watershed hydrological data, geographic data, and meteorological data of the target area in order to build a watershed database and an extreme weather database.

[0008] The data analysis module, which is connected to the database construction module, is used to construct a hydrological twin model of the target area based on the watershed database, determine several key early warning areas based on the hydrological twin model, and determine the associated extreme weather data based on the extreme weather database, and determine the comprehensive impact index corresponding to the associated extreme weather data.

[0009] The prediction simulation module is connected to the data analysis module and the database construction module respectively. It is used to adjust the model parameters of the hydrological twin model based on the comprehensive impact index, and to perform flood prediction simulation based on the adjusted hydrological twin model and the extreme weather database to obtain the flood propagation parameters of the flood inundation area and each of the key early warning areas. The flood propagation parameters include flood flow, water depth and flow velocity.

[0010] The data determination module is connected to the database construction module, the data analysis module, and the prediction simulation module, respectively. It is used to determine the flood risk level of the target area based on the flood propagation parameters of each of the key early warning areas, and to determine the flood prevention early warning parameters of the target area based on the flood risk level. It also determines the regional characteristics of each of the key early warning areas based on the watershed database, and determines the regional flood control index of the target area based on the flood prevention early warning parameters of the target area and the regional characteristics of each key early warning area.

[0011] Furthermore, the data analysis module also includes:

[0012] The regional analysis submodule, which is connected to the database construction module, is used to divide several watershed sub-regions based on the hydrological twin model, perform sensitivity analysis on each watershed sub-region, and determine several key early warning areas based on the sensitivity analysis results.

[0013] Furthermore, the data analysis module also includes:

[0014] An extreme weather analysis submodule, connected to the database construction module, is used to determine several key extreme weather data based on the comparison results of individual extreme weather data and standard weather data in the extreme weather database, determine related extreme weather data based on the correlation relationship of each key extreme weather data, and determine the comprehensive impact index corresponding to the related extreme weather data based on the comparison results of each related extreme weather data and standard weather data.

[0015] Furthermore, the prediction simulation module includes:

[0016] The model adjustment submodule, which is connected to the extreme weather analysis submodule, is used to determine the model parameter adjustment coefficient based on the comprehensive impact index corresponding to the associated extreme weather data, and to adjust the model parameters of the hydrological twin model based on the model parameter adjustment coefficient to obtain the adjusted hydrological twin model.

[0017] The condition determination submodule, which is connected to the database construction module, is used to determine the predicted simulated meteorological data based on the extreme weather database;

[0018] The prediction simulation submodule is connected to the regional analysis submodule, the condition determination submodule, and the model adjustment submodule, respectively, and is used to perform flood prediction simulation based on the adjusted hydrological twin model and the prediction simulation meteorological data to obtain the flood inundation area and the flood propagation parameters of each of the key early warning areas.

[0019] Furthermore, the data determination module also includes:

[0020] The risk analysis submodule, which is connected to the prediction simulation submodule, is used to determine the flood risk level of the target area based on the comparison results between the flood-inundated area and the target area, as well as the comparison results between the flood propagation parameters and the standard propagation parameters of each key early warning area.

[0021] Furthermore, the data determination module also includes:

[0022] The parameter analysis submodule, which is connected to the risk analysis submodule, is used to determine the early warning thresholds corresponding to each watershed parameter in the target area based on the flood risk level of the target area, and to determine the flood control early warning parameters based on the comparison results between the early warning thresholds corresponding to each watershed parameter and the current watershed parameters.

[0023] Furthermore, the data determination module also includes:

[0024] The regional feature determination submodule is connected to the database construction module and the regional analysis submodule, respectively, and is used to determine the regional features of each of the key early warning areas based on the watershed database.

[0025] The flood control index determination submodule is connected to the parameter analysis submodule and the regional feature determination submodule, respectively, to determine the regional flood control assessment model based on the regional characteristics of each key early warning area, and to determine the regional flood control index of the target area based on the flood early warning parameters of the target area and the regional flood control assessment model.

[0026] Furthermore, the regional analysis submodule is also used to perform correlation analysis between regional characteristic parameters and flood risk of a single watershed sub-region based on the hydrological twin model to determine the degree of correlation for sensitivity analysis.

[0027] Furthermore, the regional analysis submodule determines the corresponding watershed sub-region as a key early warning area based on the sensitivity analysis results of the correlation between the regional characteristic parameters of a single watershed sub-region and the flood risk being greater than a preset correlation level.

[0028] Furthermore, the data determination module determines whether to update the preset correlation level based on the flood risk level.

[0029] Compared with existing technologies, the beneficial effects of this invention are as follows: By setting up a database construction module to build a watershed database and an extreme weather database respectively, this invention provides a data foundation for subsequent flood prediction simulation and risk warning assessment. By setting up a data analysis module to construct a hydrological twin model, it can accurately simulate the hydrological processes of the target area, providing model support for flood prediction and risk assessment. By identifying related extreme weather data based on the extreme weather database and determining the comprehensive impact index corresponding to the related extreme weather data, it provides a quantitative assessment of the impact of extreme weather for subsequent flood prediction and risk warning, and improves the model's adaptability through dynamic adjustments. By setting up a prediction simulation module to adjust the hydrological twin model according to the comprehensive impact index corresponding to the related extreme weather data, the accuracy of flood prediction can be improved, thereby improving the accuracy of subsequent flood prevention warnings. By setting a data judgment module based on flood propagation parameters of key early warning areas, the flood risk level of the target area can be accurately determined, thereby determining whether it meets the early warning criteria. When the criteria are met, different flood risk levels have corresponding flood control early warning parameters. By combining the regional characteristics of key early warning areas with the flood control early warning parameters of the target area, the regional flood control indicators of the target area can be determined. This can break through the limitations of fixed early warning thresholds, dynamically adjust regional flood control indicators, further improve the accuracy of flood control early warnings and the efficiency of emergency response, and enable timely response during flood forecasting, avoiding false alarms and missed alarms.

[0030] Furthermore, the data analysis module of this invention, by setting up a regional analysis sub-module, divides the target area into several watershed sub-regions, which can more accurately simulate the hydrological response of each watershed sub-region. By performing sensitivity analysis on each watershed sub-region to determine key early warning areas, the accuracy of key early warning area identification can be improved and flood control resource allocation can be optimized.

[0031] Furthermore, the data analysis module of this invention, by setting up an extreme weather analysis sub-module, can accurately identify key extreme weather data, comprehensively evaluate key extreme weather data through the correlation of key extreme weather data, accurately screen out related extreme weather data, and quantify the overall impact of extreme weather on flood processes by determining the comprehensive impact index corresponding to the related extreme weather data, thereby improving the accuracy of flood prediction and simulation.

[0032] Furthermore, the prediction and simulation module of this invention sets up a model adjustment submodule to determine model parameter adjustment coefficients based on the comprehensive impact index, thereby adjusting the model parameters of the hydrological twin model. This improves the accuracy of flood prediction simulation and enhances the model's adaptability. The condition determination submodule determines the meteorological data for prediction simulation, providing accurate meteorological input and ensuring the accuracy and reliability of the simulation results. By setting up the prediction and simulation submodule to determine the flood inundation area and flood propagation parameters for each key early warning area, detailed flood information is provided for flood warnings, offering effective data for subsequent regional flood control indicators and improving the accuracy of flood warnings. Attached Figure Description

[0033] Figure 1 This is a structural block diagram of the flood control four-prevention system based on digital twins according to an embodiment of the present invention;

[0034] Figure 2 This is a structural block diagram of the data analysis module in an embodiment of the present invention;

[0035] Figure 3 This is a structural block diagram of the prediction simulation module according to an embodiment of the present invention;

[0036] Figure 4 This is a structural block diagram of the data determination module in an embodiment of the present invention. Detailed Implementation

[0037] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0038] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0039] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0040] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0041] Please see Figures 1-4 As shown, Figure 1 This is a structural block diagram of the flood control four-prevention system based on digital twins according to an embodiment of the present invention; Figure 2 This is a structural block diagram of the data analysis module in an embodiment of the present invention; Figure 3 This is a structural block diagram of the prediction simulation module according to an embodiment of the present invention; Figure 4 This is a structural block diagram of the data determination module in an embodiment of the present invention. The present invention provides a flood prevention four-prevention system based on digital twins, comprising:

[0042] The database construction module is used to acquire watershed hydrological data, geographic data, and meteorological data of the target area in order to build a watershed database and an extreme weather database.

[0043] In practice, the watershed hydrological data includes data on water resource distribution within the watershed, river water level, river flow, river velocity, sediment, and runoff. Geographic data includes topographic data, soil data, and vegetation data. Meteorological data includes precipitation data, cloud cover data, temperature data, air pressure data, wind direction data, wind speed data, humidity data, and atmospheric circulation data.

[0044] It is understandable that there are no restrictions on the methods or equipment used to obtain watershed hydrological data, geographic data, and meteorological data for the target area; these data can be obtained through hydrological monitoring stations, geographic information systems, remote sensing images, weather stations, meteorological satellites, etc.

[0045] Understandably, the acquired watershed hydrological, geographical, and meteorological data undergo data cleaning, calibration, and format conversion to ensure data accuracy and consistency, and are then stored in the watershed database.

[0046] Understandably, the acquired meteorological data is compared with the preset meteorological range, and meteorological data that does not conform to the preset meteorological range is identified as extreme meteorological data and stored in the extreme meteorological database.

[0047] Understandably, implementers can set preset meteorological ranges based on actual conditions or historical meteorological data that has caused disasters such as floods. For example, the minimum value of the preset meteorological range corresponding to 12-hour precipitation can be set to 30mm to 50mm, and the maximum value of the preset meteorological range corresponding to 12-hour precipitation can be set to 200mm to 250mm.

[0048] The data analysis module, which is connected to the database construction module, is used to construct a hydrological twin model of the target area based on the watershed database, determine several key early warning areas based on the hydrological twin model, and determine the associated extreme weather data based on the extreme weather database, and determine the comprehensive impact index corresponding to the associated extreme weather data.

[0049] In implementation, a hydrological model framework, such as SWMM, HEC-HMS, or MIKE SHE, is selected, and the model parameters are initialized based on the watershed data in the watershed database to obtain a hydrological twin model.

[0050] Specifically, the data analysis module also includes:

[0051] The regional analysis submodule, which is connected to the database construction module, is used to divide several watershed sub-regions based on the hydrological twin model, perform sensitivity analysis on each watershed sub-region, and determine several key early warning areas based on the sensitivity analysis results.

[0052] Specifically, the regional analysis submodule is also used to perform correlation analysis between regional characteristic parameters and flood risk of a single watershed sub-region based on the hydrological twin model to determine the degree of correlation for sensitivity analysis.

[0053] Specifically, the regional analysis submodule determines the corresponding watershed sub-region as a key early warning area based on the sensitivity analysis results of the correlation between the regional characteristic parameters of a single watershed sub-region and the flood risk being greater than a preset correlation level.

[0054] In implementation, the target area is generalized into several grids based on the hydrological twin model of the target area, and corresponding grid edges are generated based on the grid data. Grids and grid edges are used to construct areal and linear land cover models, respectively. Both possess attributes related to runoff generation and confluence, and work together to construct the surface runoff generation and confluence model. The surface grid is the foundation of the two-dimensional surface hydraulic model and can be structured or unstructured. The attribute information of the surface grid includes grid elevation, initial water level, roughness, grid building area ratio, initial loss, maximum infiltration capacity, stable infiltration capacity, and drainage capacity. Regional geographical assessment indicators are constructed based on geographical parameters (topography, river system distribution, soil type, vegetation type, etc.), and the geographical parameters of each grid are determined. Each grid is clustered to obtain several cluster sets. The smallest region formed by connecting grids within the same cluster set is determined as a watershed sub-region, thus obtaining several watershed sub-regions.

[0055] Understandably, regional characteristic parameters include rainfall, soil permeability coefficient, vegetation interception, river channel Manning roughness, and topographic slope. The correlation between regional characteristic parameters and flood risk is determined based on the regional characteristic parameter data corresponding to flood events in historical data, and the probability of each regional characteristic parameter triggering a flood event in historical data (determined by the ratio of the number of flood events triggered by each regional characteristic parameter to the total number of flood events. For example, if the rainfall in historical data that triggered flood events was 30mm, 40mm, 50mm, and 100mm, then the probability of 30mm rainfall triggering a flood event is 1 / 4 = 0.25, and the correlation between 30mm rainfall and flood risk is 0.25).

[0056] The data analysis module of this invention divides the target area into several watershed sub-regions by setting up a regional analysis sub-module, which can more accurately simulate the hydrological response of each watershed sub-region. By performing sensitivity analysis on each watershed sub-region, key early warning areas can be identified, thereby improving the accuracy of key early warning area identification and optimizing the allocation of flood control resources.

[0057] Specifically, the data analysis module also includes:

[0058] An extreme weather analysis submodule, connected to the database construction module, is used to determine several key extreme weather data based on the comparison results of individual extreme weather data and standard weather data in the extreme weather database, determine related extreme weather data based on the correlation relationship of each key extreme weather data, and determine the comprehensive impact index corresponding to the related extreme weather data based on the comparison results of each related extreme weather data and standard weather data.

[0059] In implementation, practitioners can set standard meteorological data based on actual conditions or critical meteorological data of flood events from historical data. For example, the average of meteorological data within a preset time period (15-30 minutes) before a flood event can be set as the standard meteorological data. If the number of single extreme meteorological data exceeding the standard meteorological data is greater than the preset number, then that extreme meteorological data is identified as critical extreme meteorological data. Based on the critical extreme meteorological data corresponding to each critical extreme meteorological parameter, the feature vectors corresponding to each critical extreme meteorological parameter are determined. Correlation analysis is performed on any two feature vectors to determine the corresponding correlation coefficients. If any correlation coefficient is greater than the preset correlation coefficient, then the corresponding critical extreme meteorological data is identified as associated extreme meteorological data. Practitioners can set preset numbers and preset correlation coefficients based on actual conditions. Preferably, the preset number ranges from 1% to 5% of the total number of extreme meteorological data in the database, and the preset correlation coefficient ranges from 0.6 to 0.7.

[0060] Understandably, the meteorological impact factor corresponding to each associated extreme meteorological parameter is determined based on the average ratio of each associated extreme meteorological data to the corresponding standard meteorological data. The comprehensive impact index corresponding to the associated extreme meteorological data is then determined based on the average of the meteorological impact factors corresponding to each associated extreme meteorological parameter. For example, the associated extreme meteorological data corresponding to any associated extreme meteorological parameter are Y1, Y2, ..., Y... j , ..., Y m If the standard meteorological data A corresponds to the associated extreme meteorological parameter, then the meteorological impact factor P corresponding to the associated extreme meteorological parameter is (∑ m j＝1 Y j ) / (A×m), where j=1,2,…,m, and m is the number of associated extreme meteorological data corresponding to the associated extreme meteorological parameter. Practitioners can set standard meteorological data based on actual conditions or the average of meteorological data that have passed compliance checks in historical data.

[0061] The data analysis module of this invention, by setting up an extreme weather analysis sub-module, can accurately identify key extreme weather data. Through the correlation of key extreme weather data, it can comprehensively evaluate key extreme weather data, accurately screen out related extreme weather data, and by determining the comprehensive impact index corresponding to the related extreme weather data, it can quantify the overall impact of extreme weather on flood processes and improve the accuracy of flood prediction and simulation.

[0062] The prediction simulation module is connected to the data analysis module and the database construction module respectively. It is used to adjust the model parameters of the hydrological twin model based on the comprehensive impact index, and to perform flood prediction simulation based on the adjusted hydrological twin model and the extreme weather database to obtain the flood propagation parameters of the flood inundation area and each of the key early warning areas. The flood propagation parameters include flood flow, water depth and flow velocity.

[0063] Specifically, the prediction simulation module includes:

[0064] The model adjustment submodule, which is connected to the extreme weather analysis submodule, is used to determine the model parameter adjustment coefficient based on the comprehensive impact index corresponding to the associated extreme weather data, and to adjust the model parameters of the hydrological twin model based on the model parameter adjustment coefficient to obtain the adjusted hydrological twin model.

[0065] The condition determination submodule, which is connected to the database construction module, is used to determine the predicted simulated meteorological data based on the extreme weather database;

[0066] The prediction simulation submodule is connected to the regional analysis submodule, the condition determination submodule, and the model adjustment submodule, respectively, and is used to perform flood prediction simulation based on the adjusted hydrological twin model and the prediction simulation meteorological data to obtain the flood inundation area and the flood propagation parameters of each of the key early warning areas.

[0067] In implementation, considering the influence mechanisms of different meteorological parameters on the hydrological twin model, a model parameter adjustment model is constructed, and a model parameter adjustment function is set: θ new = f(Comprehensive Influence Index, θ0), where θ new θ0 and θ1 represent the adjusted model parameters and the initial model parameters, respectively. Assuming a linear or non-linear relationship exists between the comprehensive impact index and the adjustment range of the model parameters, historical data is used to fit the data to obtain a curve or equation relating the comprehensive impact index and the adjustment range of the model parameters.

[0068] In practice, the predicted simulated meteorological data are determined based on the mean of the associated extreme meteorological data in the extreme meteorological database.

[0069] This invention's prediction and simulation module includes a model adjustment submodule that determines model parameter adjustment coefficients based on the comprehensive impact index to adjust the model parameters of the hydrological twin model. This improves the accuracy of flood prediction simulations and enhances model adaptability. The condition determination submodule determines the meteorological data for prediction simulations, providing accurate meteorological input and ensuring the accuracy and reliability of the simulation results. By setting the flood prediction simulation submodule to determine the flood inundation area and flood propagation parameters for each key early warning area, detailed flood information is provided for flood warnings, offering effective data for subsequent regional flood control indicators and improving the accuracy of flood warnings.

[0070] The data determination module, which is connected to the database construction module, the data analysis module, and the prediction simulation module, is used to determine the flood risk level of the target area based on the flood propagation parameters of each of the key early warning areas, and to determine whether the flood risk level meets the early warning criteria. If it does, the module determines the flood control early warning parameters of the target area. The module also determines the regional characteristics of each of the key early warning areas based on the watershed database, and determines the regional flood control indicators of the target area based on the flood control early warning parameters of the target area and the regional characteristics of each key early warning area.

[0071] Specifically, the data determination module also includes:

[0072] The risk analysis submodule, which is connected to the prediction simulation submodule, is used to determine the flood risk level of the target area based on the comparison results between the flood-inundated area and the target area, as well as the comparison results between the flood propagation parameters and the standard propagation parameters of each key early warning area.

[0073] In implementation, the first characteristic value is determined based on the ratio of the flood-inundated area to the target area. The second characteristic value is determined based on the average ratio of the flood propagation parameters to the standard propagation parameters in each key early warning area. The flood risk level of the target area is determined based on the first and second characteristic values ​​and a pre-set flood risk level comparison table. It is understandable that implementers can set standard propagation parameters based on actual conditions or historical data that have passed compliance testing. Furthermore, implementers can set a pre-set flood risk level comparison table based on the difference between the flood propagation parameters corresponding to the losses caused by flood events that have passed compliance testing in actual conditions or historical data and the standard propagation parameters.

[0074] Specifically, the data determination module also includes:

[0075] The parameter analysis submodule, which is connected to the risk analysis submodule, is used to determine the early warning thresholds corresponding to each watershed parameter in the target area based on the flood risk level of the target area, and to determine the flood control early warning parameters based on the comparison results between the early warning thresholds corresponding to each watershed parameter and the current watershed parameters.

[0076] In practice, implementers can set early warning thresholds for watershed parameters corresponding to each flood risk level based on actual conditions or expert systems. The current watershed parameters are compared with the corresponding early warning thresholds. If the thresholds are exceeded, the watershed parameters are determined to be flood control early warning parameters.

[0077] Specifically, the data determination module also includes:

[0078] The regional feature determination submodule is connected to the database construction module and the regional analysis submodule, respectively, and is used to determine the regional features of each of the key early warning areas based on the watershed database.

[0079] In implementation, a training dataset is constructed by combining geographical data such as topography and soil type of each key early warning area in historical data with regional geographical assessment indicators to train the initial neural network model. The trained neural network model is then obtained by inputting data from the database into the trained neural network model to obtain the regional characteristics of each key early warning area output by the trained neural network model.

[0080] The flood control index determination submodule is connected to the parameter analysis submodule and the regional feature determination submodule, respectively, to determine the regional flood control assessment model based on the regional characteristics of each key early warning area, and to determine the regional flood control index of the target area based on the flood early warning parameters of the target area and the regional flood control assessment model.

[0081] In practice, an initial neural network model can be trained based on regions with the same regional characteristics as the key early warning area that have experienced flood events in historical data, as well as flood control early warning parameters and corresponding ideal regional flood control indicators in historical data, to obtain a regional flood control assessment model. By inputting the flood control early warning parameters of the target area into the regional flood control assessment model, the regional flood control indicators of the target area can be obtained.

[0082] Specifically, the data determination module determines that the flood risk level does not meet the early warning criteria based on the flood risk level being a potential risk level. The flood risk level includes potential risk level, low risk level, medium risk level, and high risk level. If the flood risk level is a low risk level, medium risk level, or high risk level, then the early warning criteria are met.

[0083] Specifically, the data determination module determines whether to update the preset correlation level based on the flood risk level.

[0084] It is understandable that implementers can set the preset correlation degree based on the actual situation. Preferably, the preset correlation degree corresponding to the potential risk level is set to a range of 0.9 to 0.95, the preset correlation degree corresponding to the low risk level is set to a range of 0.8 to 0.9, the preset correlation degree corresponding to the medium risk level is set to a range of 0.7 to 0.8, and the preset correlation degree corresponding to the high risk level is set to a range of 0.6 to 0.7.

[0085] This invention constructs a watershed database and an extreme weather database through a database construction module, providing a data foundation for subsequent flood prediction simulation and risk warning assessment. By setting up a data analysis module to build a hydrological twin model, it can accurately simulate hydrological processes in the target area, providing model support for flood prediction and risk assessment. By identifying relevant extreme weather data based on the extreme weather database and determining the corresponding comprehensive impact index, it provides a quantitative assessment of the impact of extreme weather for subsequent flood prediction and risk warning. Dynamic adjustments improve the model's adaptability. By setting up a prediction simulation module to adjust the hydrological twin model according to the comprehensive impact index corresponding to the relevant extreme weather data, the accuracy of flood prediction can be improved, thereby enhancing the accuracy of subsequent flood prevention and warning. By setting a data judgment module based on flood propagation parameters of key early warning areas, the flood risk level of the target area can be accurately determined, thereby determining whether it meets the early warning criteria. When the criteria are met, different flood risk levels have corresponding flood control early warning parameters. By combining the regional characteristics of key early warning areas with the flood control early warning parameters of the target area, the regional flood control indicators of the target area can be determined. This can break through the limitations of fixed early warning thresholds, dynamically adjust regional flood control indicators, further improve the accuracy of flood control early warnings and the efficiency of emergency response, and enable timely response during flood forecasting, avoiding false alarms and missed alarms.

[0086] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A flood control four-prevention system based on digital twins, characterized in that, include: The database construction module is used to acquire watershed hydrological data, geographic data, and meteorological data of the target area in order to build a watershed database and an extreme weather database. The data analysis module, which is connected to the database construction module, is used to construct a hydrological twin model of the target area based on the watershed database, determine several key early warning areas based on the hydrological twin model, and determine the associated extreme weather data based on the extreme weather database, and determine the comprehensive impact index corresponding to the associated extreme weather data. The prediction simulation module is connected to the data analysis module and the database construction module respectively. It is used to adjust the model parameters of the hydrological twin model based on the comprehensive impact index, and to perform flood prediction simulation based on the adjusted hydrological twin model and the extreme weather database to obtain the flood propagation parameters of the flood inundation area and each of the key early warning areas. The flood propagation parameters include flood flow, water depth and flow velocity. The data determination module is connected to the database construction module, the data analysis module, and the prediction simulation module, respectively. It is used to determine the flood risk level of the target area based on the flood propagation parameters of each of the key early warning areas, and to determine the flood prevention early warning parameters of the target area based on the flood risk level. It also determines the regional characteristics of each of the key early warning areas based on the watershed database, and determines the regional flood control index of the target area based on the flood prevention early warning parameters of the target area and the regional characteristics of each key early warning area.

2. The flood control four-prevention system based on digital twins according to claim 1, characterized in that, The data analysis module also includes: The regional analysis submodule, which is connected to the database construction module, is used to divide several watershed sub-regions based on the hydrological twin model, perform sensitivity analysis on each watershed sub-region, and determine several key early warning areas based on the sensitivity analysis results.

3. The flood control four-prevention system based on digital twins according to claim 2, characterized in that, The data analysis module also includes: An extreme weather analysis submodule, connected to the database construction module, is used to determine several key extreme weather data based on the comparison results of individual extreme weather data and standard weather data in the extreme weather database, determine related extreme weather data based on the correlation relationship of each key extreme weather data, and determine the comprehensive impact index corresponding to the related extreme weather data based on the comparison results of each related extreme weather data and standard weather data.

4. The flood control four-prevention system based on digital twins according to claim 3, characterized in that, The prediction simulation module includes: The model adjustment submodule, which is connected to the extreme weather analysis submodule, is used to determine the model parameter adjustment coefficient based on the comprehensive impact index corresponding to the associated extreme weather data, and to adjust the model parameters of the hydrological twin model based on the model parameter adjustment coefficient to obtain the adjusted hydrological twin model. The condition determination submodule, which is connected to the database construction module, is used to determine the predicted simulated meteorological data based on the extreme weather database; The prediction simulation submodule is connected to the regional analysis submodule, the condition determination submodule, and the model adjustment submodule, respectively, and is used to perform flood prediction simulation based on the adjusted hydrological twin model and the prediction simulation meteorological data to obtain the flood inundation area and the flood propagation parameters of each of the key early warning areas.

5. The flood control four-prevention system based on digital twins according to claim 4, characterized in that, The data determination module also includes: The risk analysis submodule, which is connected to the prediction simulation submodule, is used to determine the flood risk level of the target area based on the comparison results between the flood-inundated area and the target area, as well as the comparison results between the flood propagation parameters and the standard propagation parameters of each key early warning area.

6. The flood control four-prevention system based on digital twins according to claim 5, characterized in that, The data determination module also includes: The parameter analysis submodule, which is connected to the risk analysis submodule, is used to determine the early warning thresholds corresponding to each watershed parameter in the target area based on the flood risk level of the target area, and to determine the flood control early warning parameters based on the comparison results between the early warning thresholds corresponding to each watershed parameter and the current watershed parameters.

7. The flood control four-prevention system based on digital twins according to claim 6, characterized in that, The data determination module also includes: The regional feature determination submodule is connected to the database construction module and the regional analysis submodule, respectively, and is used to determine the regional features of each of the key early warning areas based on the watershed database. The flood control index determination submodule is connected to the parameter analysis submodule and the regional feature determination submodule, respectively, to determine the regional flood control assessment model based on the regional characteristics of each key early warning area, and to determine the regional flood control index of the target area based on the flood early warning parameters of the target area and the regional flood control assessment model.

8. The flood control four-prevention system based on digital twins according to claim 7, characterized in that, The regional analysis submodule is also used to determine the correlation between regional characteristic parameters and flood risk for a single watershed subregion based on the hydrological twin model in order to conduct sensitivity analysis.

9. The flood control four-prevention system based on digital twins according to claim 8, characterized in that, The regional analysis submodule determines the corresponding watershed sub-region as a key early warning area based on the sensitivity analysis results of the correlation between the regional characteristic parameters of a single watershed sub-region and the flood risk being greater than a preset correlation level.

10. The flood control four-prevention system based on digital twin according to claim 9, characterized in that, The data determination module determines whether to update the preset correlation level based on the flood risk level.

Images