Intelligent flood perception decision-making method based on multi-source rainfall data fusion

Abstract

The invention belongs to the technical field of disaster decision-making, and discloses an intelligent flood perception decision-making method based on multi-source rainfall data fusion. The method comprises the following steps: constructing a space integrated rainfall monitoring network, and collecting a multi-dimensional rainfall data set in real time; performing time alignment and space registration on the multi-dimensional rainfall data set to generate rainfall processing data; performing data fusion on the rainfall processing data to form fused rainfall data; hydrological environment data are obtained, and a hydrodynamic model is constructed; driving a hydrodynamic model to operate based on the fused rainfall data, and obtaining water flow characteristic data; evaluating flood risk levels of different urban areas in combination with the water flow characteristic data and the fused rainfall data; dynamically formulating differentiated emergency response schemes in combination with a historical disaster database; according to the invention, intelligent sensing and response to urban flood disasters are realized, emergency response requirements in a dynamic environment can be effectively supported, and the urban flood prevention and control capability and the disaster resistance level are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of disaster decision-making, and more specifically, to an intelligent flood perception and decision-making method for multi-source rainfall data fusion. Background Art

[0002] With the intensification of climate change, extreme rainfall events occur frequently, and flood disasters have become a major challenge faced globally; accurate rainfall data is the basis for flood warning and emergency decision-making. However, traditional methods rely on single-source data such as ground rain gauges, meteorological radars, and remote sensing satellites, which have problems such as limited coverage, insufficient accuracy, and data delay, and are difficult to meet the requirements of rapid response and precise decision-making; therefore, there is an urgent need for an intelligent flood perception and decision-making method to fuse multi-source rainfall data, realize early perception, dynamic monitoring, and scientific response to flood disasters, thereby effectively improving the scientificity and reliability of flood disaster monitoring and response, and enhancing the efficiency and effectiveness of disaster response.

[0003] The patent with the publication number CN116070918B discloses a method for urban flood safety assessment and flood disaster prevention and control; it includes obtaining urban hydrological basic data; obtaining urban historical rainfall data and calculating based on the urban historical rainfall data and urban hydrological basic data to obtain designed rainfall process data; calculating based on the designed rainfall process data to obtain flood process data; constructing an urban flood model based on the flood process data and urban hydrological basic data; evaluating the inundation results of the urban flood model to generate flood inundation result data; determining the flood risk level according to the flood inundation result data; obtaining the flood safety adaptability analysis result according to the flood risk level; generating flood disaster prevention and control measures according to the flood safety adaptability analysis result; this invention proposes corresponding disaster prevention and control methods based on the flood inundation results, making the flood safety risk level of the plot suitable for the construction use.

[0004] However, although the above technology realizes flood perception and decision-making, it mainly relies on historical rainfall data and static hydrological basic data, lacks a perception and response mechanism for real-time rainfall changes, and cannot respond to sudden flood disasters in a timely manner; in addition, the disaster prevention and control measures are generated based on static analysis results, mainly for disaster prevention and mitigation measures, focusing on pre-disaster prevention and reducing the impact of disasters, rather than emergency response plans after flood disasters occur. Therefore, it is difficult to effectively support the emergency response requirements in a dynamic environment, thus limiting the actual effect of refined flood management in modern cities.

[0005] In view of this, the present invention proposes an intelligent flood perception and decision-making method for multi-source rainfall data fusion to solve the above problems. Summary of the Invention

[0006] To overcome the above defects of the prior art and achieve the above object, the present invention provides the following technical solutions: An intelligent flood perception and decision-making method for multi-source rainfall data fusion, including: S1: Adopt multi-source data acquisition technology to construct a spatially integrated rainfall monitoring network and collect multi-dimensional rainfall data sets in real time; S2: Perform time alignment and spatial registration on the multi-dimensional rainfall data sets to generate rainfall processed data; S3: Adopt a data fusion algorithm to perform multi-dimensional data fusion on the rainfall processed data to form fused rainfall data; S4: Obtain hydrological environment data and construct a hydrodynamic model based on the hydrological environment data; S5: Based on the fused rainfall data, drive the hydrodynamic model to run, simulate the water flow evolution process, and obtain water flow characteristic data; S6: Combine the water flow characteristic data and the fused rainfall data to construct a flood risk assessment system based on fuzzy comprehensive evaluation, and intelligently evaluate the flood risk levels of different urban areas; S7: Based on the flood risk levels of different urban areas, and combined with a pre-constructed historical disaster database, use a multi-objective decision-making optimization algorithm to dynamically formulate differentiated emergency response plans.

[0007] Further, the method for constructing the spatially integrated rainfall monitoring network includes: Set monitoring stations, where is an integer greater than 1; randomly select monitoring stations from the monitoring stations and use them as a set of station sets, and a total of sets of station sets are obtained, , ; obtain the urban range and the monitoring range of each monitoring station, merge the monitoring ranges of each monitoring station in each set of station sets, and obtain the total monitoring range of each station set; perform overlay analysis on the total monitoring range of each station set and the urban range, and mark the station set with a total monitoring range greater than or equal to the urban range as a candidate set, and the station set with a total monitoring range less than the urban range is not marked; count the number of monitoring stations in each candidate set and mark it as the number of stations, and mark the candidate set with the smallest number of stations as the selected set; set a rain gauge for each monitoring station in the selected set, and combine meteorological radar and remote sensing satellites to construct a spatially integrated rainfall monitoring network; The multi-dimensional rainfall data sets include sets of monitoring data, radar data, and remote sensing data; the monitoring data is the rainfall collected by the monitoring stations, the radar data is the rainfall collected by the meteorological radar, and the remote sensing data is the rainfall collected by the remote sensing satellites.

[0008] Further, the method for time alignment of the multi-dimensional rainfall dataset includes: Obtain the acquisition time of the monitoring data in the multi-dimensional rainfall dataset and mark it as the current time; obtain the acquisition time of the radar data in the multi-dimensional rainfall dataset and mark it as the radar time; obtain the acquisition time of the remote sensing data in the multi-dimensional rainfall dataset and mark it as the remote sensing time; subtract the radar time from the current time to obtain the radar difference time; subtract the remote sensing time from the current time to obtain the remote sensing difference time; obtain historical data, where the historical data includes groups of historical radar data and groups of historical remote sensing data. The historical radar data is the radar data obtained at a historical moment, and the historical remote sensing data is the remote sensing data obtained at a historical moment. is an integer greater than 1; Input the preset radar sampling period, the radar difference time, and groups of historical radar data into the trained radar prediction model in sequence to predict the corresponding real-time radar data. The real-time radar data is the radar data corresponding to the current time; input the preset remote sensing sampling period, the remote sensing difference time, and groups of historical remote sensing data into the trained remote sensing prediction model in sequence to predict the corresponding real-time remote sensing data. The real-time remote sensing data is the remote sensing data corresponding to the current time. Both the radar prediction model and the remote sensing prediction model are deep neural network models.

[0009] Further, the method for spatial registration of the multi-dimensional rainfall dataset includes: Obtain the geographical coordinates of each monitoring site corresponding to the monitoring data in the multi-dimensional rainfall dataset and mark them as site coordinates; combine the monitoring data of each monitoring site with the site coordinates to generate monitoring distribution data; project the real-time radar data onto the WGS84 coordinate system to obtain projected radar data; obtain the geographical coordinates corresponding to each rainfall amount in the real-time remote sensing data and mark them as remote sensing coordinates; obtain the geographical coordinates corresponding to each rainfall amount in the projected radar data and mark them as radar coordinates; mark all site coordinates that are different from the remote sensing coordinates as first coordinates, and mark all site coordinates that are different from the radar coordinates as second coordinates; calculate the rainfall amount of each first coordinate using a spatial interpolation method based on the real-time remote sensing data; calculate the rainfall amount of each second coordinate using a spatial interpolation method based on the projected radar data; add each first coordinate and the corresponding rainfall amount to the real-time remote sensing data to generate remote sensing distribution data; add each second coordinate and the corresponding rainfall amount to the projected radar data to generate radar distribution data; Generate rainfall processing data based on the remote sensing distribution data, the radar distribution data, and the monitoring distribution data.

[0010] Further, the method for forming the fused rainfall data includes: Take the rainfall with the same geographical coordinates in the remote sensing distribution data, radar distribution data, and monitoring distribution data as a set of data. The data set corresponds one-to-one with the geographical coordinates. Preset a weight set, which includes the weight coefficients corresponding to the remote sensing distribution data, radar distribution data, and monitoring distribution data. Multiply each data in each data set by the corresponding weight coefficient in the weight set and add them in sequence to obtain the fused rainfall corresponding to each data set. Based on the fused rainfall corresponding to each data set, form the fused rainfall data.

[0011] Furthermore, the hydrological environment data includes meteorological data, topographical data, soil and vegetation data, basin hydrological data, and groundwater data; The method for constructing a hydrodynamic model of hydrology includes: Construct a surface runoff model, where the input of the surface runoff model is the fused rainfall data and the output is the net rainfall. Construct a shallow water hydrodynamic model, where the input of the shallow water hydrodynamic model is the net rainfall and the output is the water flow characteristic data, and the water flow characteristic data includes the water accumulation depth and water flow velocity. Couple the surface runoff model with the shallow water hydrodynamic model to construct a hydrodynamic model of hydrology; The steps for constructing a shallow water hydrodynamic model include: Step S401: Use the Saint-Venant equations as the basic equations, and the Saint-Venant equations include the continuity equation and the momentum equation; Step S402: Convert the hydrological environment data into model parameters; Step S403: Divide the city into grid cells, and each grid cell corresponds to a monitoring station and a set of state variables, and the state variables include the water accumulation depth and water flow velocity; Step S404: Set boundary conditions, and the boundary conditions include upstream boundary conditions, downstream boundary conditions, and lateral boundary conditions; among them, the upstream boundary condition is the depth time series, the downstream boundary condition is the depth-velocity relationship curve, and the lateral boundary condition is the net rainfall; Step S405: Set initial conditions for each grid cell in sequence, and the initial conditions include the initial water accumulation depth and the initial water flow velocity; Step S406: Based on the model parameters, boundary conditions, and initial conditions, use numerical calculation methods to solve the Saint-Venant equations to construct a shallow water hydrodynamic model; Input the fused rainfall data into the hydrodynamic model of hydrology to calculate the water flow characteristic data corresponding to each monitoring station.

[0012] Furthermore, the steps for intelligently evaluating the flood risk levels of different urban areas include: Step S601: According to the water flow characteristic data, divide the city into regions to obtain a city area; Step S602: Obtain the rainfall amount corresponding to each city area according to the fused rainfall data; count the number of rainfall amounts corresponding to each city area and mark it as the number of rainfall points; add up the rainfall amounts of each city area in sequence, and then divide by the corresponding number of rainfall points to obtain the average rainfall amount of each city area; Step S603: Construct multiple fuzzy sets for the waterlogging depth, water flow velocity, and average rainfall amount respectively; Step S604: Convert the fused feature data corresponding to each city area into the membership degrees of the corresponding fuzzy sets respectively through the fuzzification technique, and the fused feature data includes the waterlogging depth, water flow velocity, and average rainfall amount; Step S605: Define fuzzy rules; Step S606: Match each group of fuzzified fused feature data with the fuzzy rules respectively, and perform fuzzy inference using the fuzzy inference method to obtain the fuzzy inference result corresponding to each city area. The fuzzy inference result includes the membership degree corresponding to each flood risk level, and the flood risk levels include extreme risk, high risk, medium risk, and low risk; Step S607: Compare each membership degree in each fuzzy inference result, and take the flood risk level corresponding to the membership degree with the largest value as the flood risk level of the corresponding city area.

[0013] Further, in the step S601, obtaining the steps of a city area include: Step S610: Take each group of water flow feature data as a node, and randomly select nodes as the center points, and take the nodes that are not used as the center points as the sample points, where is an integer greater than 1; Step S611: Construct corresponding groups according to the center points, calculate the Euclidean distance from each sample point to each center point in sequence, and mark it as the point distance; Step S612: Preset a distance threshold, compare each point distance corresponding to each sample point with the distance threshold respectively, mark the center point corresponding to the point distance with a value less than the distance threshold as the classification point, and do not mark the point distance with a value greater than or equal to the distance threshold, and divide each sample point into the group corresponding to the corresponding classification point in sequence; Step S613: Calculate the new center point corresponding to each group, and replace the center point of each group with the corresponding new center point; Step S613: Calculate the new center point corresponding to each group, and replace the center point of each group with the corresponding new center point; Step S614: Repeat steps S611 to S613 until the newly calculated center points for each group in step S613 are the same as the center points calculated in the previous loop. Then, the loop ends and obtain groups; Step S615: Perform connectivity analysis on the nodes in groups to obtain sets of regions; According to sets of regions, divide the city into city regions; In the said step S613, the method for calculating the new center point includes: Count the number of nodes in each group and mark it as the node count; Add up the nodes in each group in sequence and then divide by the corresponding node count to obtain the average point for each group; Calculate the point distance from each node in each group to the corresponding average point and mark it as the average distance; Compare the average distances corresponding to the same group, and take the node corresponding to the minimum average distance value as the new center point for the corresponding group.

[0014] Furthermore, in the said step S615, the steps for obtaining sets of regions include: Step S621: Randomly select a node that is not marked as a selected node and mark it as the current node; Step S622: Construct a set of regions and add the current node to the set of regions; Step S623: Obtain the adjacent nodes of the current node, mark the adjacent nodes with the same group as the current node as similar nodes, and add the similar nodes to the set of regions; Step S624: Obtain the adjacent nodes of the similar nodes and mark them as co - adjacent nodes; Mark the co - adjacent nodes with the same group as the current node as similar nodes, and add the similar nodes to the set of regions; Step S625: Repeat step S624 until the groups corresponding to the adjacent nodes of all nodes in the set of regions are all different from the group corresponding to the current node. Then, the loop ends, obtain a set of regions, and mark all the nodes in the set of regions as selected nodes; Step S626: Repeat steps S621 to S625 until all nodes are marked as selected nodes. Then, the loop ends and obtain sets of regions.

[0015] Furthermore, the method for dynamically formulating a differentiated emergency response plan includes: Obtain the number of monitoring stations in each urban area and label it as the monitoring quantity; regard the monitoring quantity and the flood risk level of each urban area as a set of regional characteristic data; from the pre-constructed historical disaster database, obtain the set of rescue characteristic data corresponding to each set of regional characteristic data, where \(k\) is an integer greater than 1; the rescue characteristic data includes the number of rescue personnel and the quantity of various rescue materials; according to the set of rescue characteristic data corresponding to each set of regional characteristic data, obtain the regional range corresponding to each set of regional characteristic data; randomly select a value from each range within each regional range, and construct a set of alternative sets, with a total of sets of alternative sets constructed; add up the number of rescue personnel in each set of alternative sets in sequence to obtain the total number of rescue personnel; add up the quantities of the same rescue materials in each set of alternative sets in sequence to obtain the total quantity of each rescue material corresponding to it; obtain the deployment data, where the deployment data includes the number of deployed personnel and the deployment quantity of each rescue material; compare the total number of rescue personnel in each set of alternative sets with the number of deployed personnel respectively, and compare each total quantity of rescue materials with the corresponding deployment quantity respectively; mark the alternative sets where the total number of rescue personnel is less than or equal to the number of deployed personnel and each total quantity of rescue materials is less than or equal to the corresponding deployment quantity as rescue sets; do not mark the alternative sets where the total number of rescue personnel is greater than the number of deployed personnel or there is a total quantity of rescue materials greater than the corresponding deployment quantity. Set different digital labels for different flood risk levels and label them as level labels; replace the flood risk levels in all regional characteristic data with the corresponding level labels, and add them to each set of rescue sets in sequence to obtain the rescue characteristic sets; input each set of rescue characteristic sets into the trained effect prediction model respectively to predict the corresponding rescue data; the rescue data includes rescue efficiency, casualty rate, and response cost; the effect prediction model is a deep neural network model; preset a ratio set, where the ratio set includes the ratio coefficients corresponding to rescue efficiency, casualty rate, and response cost; multiply the rescue efficiency, casualty rate, and response cost corresponding to each set of rescue sets by the corresponding ratio coefficients in the ratio set respectively to obtain the efficiency coefficient, casualty coefficient, and cost coefficient in sequence; subtract the casualty coefficient from the efficiency coefficient, and then subtract the cost coefficient to obtain the rescue effect; mark the rescue characteristic set with the largest rescue effect as the best characteristic set, and use the rescue set in the best characteristic set as the emergency response plan.

[0016] The technical effects and advantages of an intelligent flood perception and decision-making method for multi-source rainfall data fusion according to the present invention: By constructing a spatially integrated rainfall monitoring network, multi-source rainfall monitoring data such as rain gauges, meteorological radars, and remote sensing satellites can be integrated to achieve comprehensive and real-time monitoring of rainfall within the urban area, improving the spatio-temporal resolution and continuity of rainfall information; by using time alignment and spatial registration techniques, the time differences and coordinate inconsistencies between data sources of different monitoring means can be effectively solved to ensure the spatio-temporal consistency of the fused rainfall data; based on the fused rainfall data to drive the hydrodynamic model, the urban surface hydrological process can be accurately simulated, and water flow characteristic data can be extracted to lay a reliable foundation for flood risk assessment; by constructing a flood risk assessment system based on fuzzy comprehensive evaluation, the flood risk levels of different urban areas can be intelligently evaluated to provide a scientific basis for emergency response; by combining the historical disaster database and using a multi-objective decision-making optimization algorithm to dynamically formulate differentiated emergency response plans, while ensuring rescue efficiency and reducing response costs, the casualty rate can be minimized, thus significantly improving the accuracy and effectiveness of emergency rescue; by realizing the intelligent perception and response to urban flood disasters, the emergency response requirements in a dynamic environment can be effectively supported, the urban flood prevention and control ability and disaster resistance level can be improved, and thus the scientific nature and efficiency of flood disaster response can be significantly enhanced. Brief Description of the Drawings

[0017] Figure 1 It is a flow chart of an intelligent flood perception and decision-making method for multi-source rainfall data fusion according to Embodiment 1 of the present invention. Detailed Embodiment

[0018] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0019] Embodiment 1 Please refer to Figure 1 As shown, the intelligent flood perception and decision-making method for multi-source rainfall data fusion in this embodiment includes: S1: Adopt multi-source data acquisition technology to construct a spatially integrated rainfall monitoring network and collect multi-dimensional rainfall data sets in real time.

[0020] The method for constructing a spatially integrated rainfall monitoring network includes: Those skilled in the art comprehensively analyze factors such as the geographical environment of the city (i.e., the natural topographical features of the city, including undulations, low-lying areas, river distributions, etc.), climate characteristics (i.e., the climate type of the city and meteorological characteristics such as rainfall amount and rainfall cycle), drainage system (i.e., various facilities built in the city to guide rainwater out, such as drainage pipe networks, drainage pumping stations, etc.), flood history (i.e., the frequency and time of past flood disasters in the city), infrastructure layout (i.e., the distribution of important facilities in the city, such as transportation hubs, bridges, tunnels, etc.), and in combination with the actual situation, set monitoring stations, is an integer greater than 1, and a rain gauge can be installed at each monitoring station to monitor rainfall; randomly select monitoring stations from monitoring stations, and use them as a set of station collections, and a total of sets of station collections are obtained. , ; Obtain the urban area and the monitoring area of each monitoring station. The urban area is the administrative boundary of the city, and the urban area is obtained through open-source map data (such as AutoNavi Map, Baidu Map, etc.). The monitoring area is determined by those skilled in the art according to the measurement range of the rain gauge, that is, the monitoring area is equal to the measurement range; use GIS tools (such as ArcGIS, QGIS, etc.) to merge the monitoring areas of each monitoring station in each set of station collections to obtain the total monitoring area of each station collection; use GIS tools to perform overlay analysis on the total monitoring area of each station collection and the urban area (that is, overlap the total monitoring area and the urban area and compare the spatial relationship between them), and mark the station collection with a total monitoring area greater than or equal to the urban area as a candidate collection (that is, the total monitoring area can completely cover the entire urban area, and each spatial position within the urban area is at least covered by the monitoring area of one monitoring station), and the station collection with a total monitoring area less than the urban area is not marked; count the number of monitoring stations in each candidate collection and mark it as the number of stations, and mark the candidate collection with the smallest number of stations as the screening collection; install a rain gauge at each monitoring station in the screening collection, and combine meteorological radar and remote sensing satellites to construct a spatially integrated rainfall monitoring network.

[0021] The multi-dimensional rainfall dataset includes Group of monitoring data, radar data, and remote sensing data; the monitoring data is the rainfall collected by monitoring stations, the radar data is the rainfall collected by meteorological radars, and the remote sensing data is the rainfall collected by remote sensing satellites; it should be noted that the monitoring data can provide high-precision rainfall information, but the spatial coverage is limited and can only represent the rainfall conditions within the corresponding monitoring range of the monitoring stations; the radar data can provide mesoscale and quasi-real-time rainfall distribution information with relatively high spatial resolution, but it will be affected by terrain occlusion, reducing the estimation accuracy of rainfall at long distances; the remote sensing data provides large-scale and full-coverage rainfall distribution information without being restricted by terrain, but the time resolution is relatively low, making it difficult to effectively capture short-term heavy rainfall events; therefore, it is necessary to effectively integrate the monitoring data, radar data, and remote sensing data, overcome the limitations of a single monitoring method, and achieve comprehensive monitoring of rainfall, thereby improving the spatio-temporal continuity and integrity of rainfall.

[0022] S2: Perform time alignment and spatial registration on the multi-dimensional rainfall dataset to generate rainfall processed data.

[0023] The methods for performing time alignment on the multi-dimensional rainfall dataset include: Obtain the collection time of the monitoring data in the multi-dimensional rainfall dataset and mark it as the current time, which is obtained through the real-time clock module built into the rain gauge; obtain the collection time of the radar data in the multi-dimensional rainfall dataset and mark it as the radar time, which is obtained through the real-time clock module built into the meteorological radar; obtain the collection time of the remote sensing data in the multi-dimensional rainfall dataset and mark it as the remote sensing time, which is obtained through the real-time clock module built into the remote sensing satellite; subtract the radar time from the current time to obtain the radar difference time; subtract the remote sensing time from the current time to obtain the remote sensing difference time; obtain historical data from the rainfall database of the urban meteorological bureau, and the historical data includes a group of historical radar data and a group of historical remote sensing data, where the historical radar data is the radar data obtained at historical moments, and the historical remote sensing data is the remote sensing data obtained at historical moments. is an integer greater than 1; it should be noted that the collection times corresponding to the group of historical radar data are continuous, and the latest collection time in the group of historical radar data is adjacent to the radar time; that is, the group of historical radar data is the consecutive group of radar data collected before the meteorological radar collects radar data; the collection times corresponding to the group of historical remote sensing data are continuous, and the latest collection time in the group of historical remote sensing data is adjacent to the remote sensing time; that is, the group of historical remote sensing data is the consecutive Group of remote sensing data; Input the preset radar sampling period, radar difference time, and group of historical radar data into the trained radar prediction model in sequence to predict the corresponding real-time radar data, where the real-time radar data is the radar data corresponding to the current time; input the preset remote sensing sampling period, remote sensing difference time, and group of historical remote sensing data into the trained remote sensing prediction model in sequence to predict the corresponding real-time remote sensing data, where the real-time remote sensing data is the remote sensing data corresponding to the current time; the radar sampling period is the time interval between each acquisition of radar data, and the remote sensing sampling period is the time interval between each acquisition of remote sensing data. Both the radar sampling period and the remote sensing sampling period are pre-set by those skilled in the art according to the actual situation; both the radar prediction model and the remote sensing prediction model are deep neural network models, and the deep neural network model is prior art. The specific training method will not be elaborated here.

[0024] It should be understood that the purpose of time alignment is to compensate for the time differences between different data sources (such as monitoring data, radar data, and remote sensing data); due to the relatively long sampling periods of radar data and remote sensing data, the acquisition times of radar data and remote sensing data are inconsistent with the acquisition time of monitoring data, resulting in a mismatch in time among different data sources; through time alignment, it can be ensured that rainfall amounts from different sources are comparable within the same time frame, thereby improving the temporal continuity of rainfall amounts.

[0025] The method for spatially registering the multi-dimensional rainfall dataset includes: Obtain the geographical coordinates (including longitude and latitude) of the monitoring station corresponding to each monitoring data in the multi-dimensional rainfall dataset and mark them as station coordinates, where the station coordinates are obtained by those skilled in the art through on-site measurement; combine the monitoring data of each monitoring station with the station coordinates to generate monitoring distribution data; project the real-time radar data onto the WGS84 coordinate system to obtain the projected radar data; projection methods such as equidistant conic projection, equidistant cylindrical projection, Mercator projection, etc., are used to make the spatial positions of the monitoring distribution data, real-time radar data, and real-time remote sensing data consistent; it should be understood that since the coordinate systems of the monitoring distribution data and the real-time remote sensing data are the WGS84 coordinate system, there is no need to project the monitoring distribution data and the real-time remote sensing data, and only the real-time radar data needs to be projected onto the WGS84 coordinate system; Obtain the geographical coordinates corresponding to each rainfall amount in the real-time remote sensing data and mark them as remote sensing coordinates; obtain the geographical coordinates corresponding to each rainfall amount in the projected radar data and mark them as radar coordinates; mark all the site coordinates that are different from the remote sensing coordinates as the first coordinates, and mark all the site coordinates that are different from the radar coordinates as the second coordinates; according to the real-time remote sensing data, use spatial interpolation methods (such as Inverse Distance Weighting IDW, Kriging, Spline, etc.) to calculate the rainfall amount at each first coordinate; according to the projected radar data, use spatial interpolation methods to calculate the rainfall amount at each second coordinate; add each first coordinate and the corresponding rainfall amount to the real-time remote sensing data to generate remote sensing distribution data; add each second coordinate and the corresponding rainfall amount to the projected radar data to generate radar distribution data.

[0026] Based on the remote sensing distribution data, radar distribution data, and monitoring distribution data, generate rainfall processing data.

[0027] S3: Use a data fusion algorithm to perform multi-dimensional data fusion on the rainfall processing data to form fused rainfall data.

[0028] The method for forming the fused rainfall data includes: Take the rainfall amounts with the same corresponding geographical coordinates in the remote sensing distribution data, radar distribution data, and monitoring distribution data as a set of data, and each set of data corresponds one-to-one with the geographical coordinates; preset a weight set, which includes the weight coefficients corresponding to the remote sensing distribution data, radar distribution data, and monitoring distribution data. The weight set is pre-set by those skilled in the art according to the actual rainfall monitoring accuracy of rain gauges, meteorological radars, and remote sensing satellites; multiply each data in each set of data by the corresponding weight coefficient in the weight set and add them up in sequence to obtain the fused rainfall amount corresponding to each set of data; based on the fused rainfall amounts corresponding to each set of data, form the fused rainfall data.

[0029] S4: Obtain hydrological environment data and construct a hydrodynamic model based on the hydrological environment data.

[0030] Hydrological environment data refers to all key environmental factors that affect hydrological processes, which directly influence hydrological processes such as water flow, runoff, groundwater, evaporation, etc.; hydrological environment data includes meteorological data, topographic data, soil and vegetation data, basin hydrological data, and groundwater data; meteorological data such as rainfall, temperature, wind speed, humidity, etc.; topographic data such as slope, elevation, basin shape, surface roughness, etc.; soil and vegetation data such as soil type, soil moisture, soil hydraulic conductivity, vegetation cover type, etc.; basin hydrological data such as river flow, reservoir water level, river cross-section, etc.; groundwater data such as groundwater level, groundwater flow, permeability, etc.; hydrological environment data is obtained by those skilled in the art through methods such as on-site monitoring, hydrological data collection, remote sensing technology, geographic information system, etc.

[0031] The method for constructing a hydrological dynamics model includes: Construct a surface runoff model (such as the SCS-CN model, Green-Ampt infiltration model, etc.), the input of the surface runoff model is the integrated rainfall data, and the output is the net rainfall amount (i.e., the amount of water actually forming surface runoff); construct a shallow water dynamics model, the input of the shallow water dynamics model is the net rainfall amount, and the output is the water flow characteristic data, and the water flow characteristic data includes the ponding depth and the water flow velocity; couple the surface runoff model and the shallow water dynamics model to construct a hydrological dynamics model.

[0032] The steps for constructing a shallow water dynamics model include: Step S401: Adopt the Saint-Venant equations (shallow water equations) as the basic equations to describe the surface water flow movement; the Saint-Venant equations include the continuity equation (i.e., the mass conservation equation) and the momentum equation (i.e., the momentum conservation equation); the Saint-Venant equations are prior art, and the specific equations corresponding to the continuity equation and the momentum equation will not be elaborated here too much; Step S402: Those skilled in the art convert the hydrological environment data into model parameters through systematic processing, professional analysis, and scientific transformation of the hydrological environment; the model parameters include slope coefficient, Manning roughness coefficient, digital elevation model, permeability, rainfall, etc.; Step S403: Divide the city into grid cells, each grid cell corresponds to a monitoring station and a set of state variables, and the state variables include the ponding depth and the water flow velocity; Step S404: Set boundary conditions, and the boundary conditions include upstream boundary conditions, downstream boundary conditions, and lateral boundary conditions; among them, the upstream boundary condition is the depth time series (i.e., the ponding depth changing with time), the downstream boundary condition is the depth-velocity relationship curve (i.e., the functional relationship between the ponding depth and the water flow velocity), and the lateral boundary condition is the net rainfall amount; the boundary conditions are set by those skilled in the art through various methods such as on-site observation, theoretical calculation, and numerical simulation; Step S405: Set initial conditions for each grid cell in sequence. The initial conditions include the initial water accumulation depth and the initial water flow velocity, which are obtained by those skilled in the art through on-site measurement or empirical calculation. Step S406: Based on the model parameters, boundary conditions, and initial conditions, use numerical calculation methods (such as finite difference, finite volume, etc.) to solve the Saint-Venant equations and construct a shallow water dynamics model. The shallow water dynamics model can simulate and output the water accumulation depth and water flow velocity of each grid cell changing with time.

[0033] S5: Based on the fused rainfall data, drive the operation of the hydrological dynamics model, simulate the water flow evolution process, and obtain water flow characteristic data.

[0034] Input the fused rainfall data into the hydrological dynamics model to calculate the water flow characteristic data corresponding to each monitoring station.

[0035] S6: Combine the water flow characteristic data and the fused rainfall data to construct a flood risk assessment system based on fuzzy comprehensive evaluation, and intelligently evaluate the flood risk levels of different urban areas.

[0036] The steps for intelligently evaluating the flood risk levels of different urban areas include: Step S601: According to the water flow characteristic data, divide the city into regions to obtain urban areas. Step S602: According to the fused rainfall data, obtain the rainfall amount corresponding to each urban area; count the number of rainfall amounts corresponding to each urban area and mark it as the number of rainfall points; add up the rainfall amounts of each urban area in sequence, and then divide by the corresponding number of rainfall points to obtain the average rainfall amount of each urban area. Step S603: Construct multiple fuzzy sets for the water accumulation depth, water flow velocity, and average rainfall amount respectively. For example, the fuzzy sets corresponding to the water accumulation depth are deep water accumulation, medium water accumulation, shallow water accumulation, etc., and the fuzzy sets corresponding to the water flow velocity are fast speed, medium speed, slow speed, etc. Step S604: Respectively convert the fused characteristic data corresponding to each urban area into the membership degrees of the corresponding fuzzy sets through fuzzy technology. The fused characteristic data includes the water accumulation depth, water flow velocity, and average rainfall amount. Fuzzy technology is the process of converting accurate numerical values into the membership degrees corresponding to fuzzy sets. Fuzzy technologies such as triangular membership functions and trapezoidal membership functions, etc. For example, if the numerical value of the water accumulation depth is low, it is inferred that the membership degree of shallow water accumulation is 0.9, the membership degree of medium water accumulation is 0.1, and the membership degree of deep water accumulation is 0. Step S605: Define fuzzy rules, which are defined based on expert knowledge or relevant literature. For example, if the water accumulation is deep, the speed is fast, and the rainfall is large, it is inferred that the probability of the corresponding urban area being at extreme risk is high; if the water accumulation is shallow, the speed is slow, and the rainfall is small, it is inferred that the probability of the corresponding urban area being at low risk is high. Step S606: Match each group of fused feature data after fuzzification with the fuzzy rules respectively, and perform fuzzy reasoning using fuzzy reasoning methods (such as Mamdani fuzzy inference model, Sugeno fuzzy inference model, etc.) to obtain the fuzzy reasoning results corresponding to each urban area. The fuzzy reasoning results include the membership degrees corresponding to each flood risk level. The flood risk levels include extreme risk, high risk, medium risk, and low risk. For example, the membership degree of extreme risk in the fuzzy reasoning result is 0.3, the membership degree of high risk is 0.0, the membership degree of medium risk is 0.1, and the membership degree of low risk is 0. Step S607: Compare each membership degree in each fuzzy reasoning result, and take the flood risk level corresponding to the membership degree with the largest value as the flood risk level of the corresponding urban area.

[0037] In the above step S601, the steps for obtaining the urban areas include: Step S610: Take each group of water flow feature data as a node, and randomly select nodes as the center points, and take the nodes that are not used as the center points as the sample points. is an integer greater than 1. The specific value of is preset by those skilled in the art according to the actual situation. Step S611: Construct corresponding groups according to the center points, calculate the Euclidean distance from each sample point to each center point in turn, and mark it as the point distance. The calculation method of the Euclidean distance is prior art, and the specific calculation process will not be elaborated here. Step S612: Preset a distance threshold, compare each point distance corresponding to each sample point with the distance threshold respectively, mark the center point corresponding to the point distance with a value less than the distance threshold as the classification point, and do not mark the point distance with a value greater than or equal to the distance threshold. Divide each sample point into the group corresponding to the corresponding classification point in turn. The distance threshold is preset by those skilled in the art according to the actual situation. Step S613: Calculate the new center point corresponding to each group, and replace the center point of each group with the corresponding new center point. Step S614: Loop through steps S611 to S613 until the newly calculated center points corresponding to each group in step S613 are the same as the newly calculated center points in the previous loop, then the loop ends and obtain groups; Step S615: Conduct a connectivity analysis on the nodes in groups to obtain sets of regions; According to sets of regions, divide the city into city regions, and the city regions correspond one-to-one with the sets of regions.

[0038] In the above step S613, the method for calculating the new center point includes: Count the number of nodes in each group and mark it as the number of nodes; Add up the nodes in each group in turn and then divide by the corresponding number of nodes to obtain the average point corresponding to each group; Calculate the point distance from each node in each group to the corresponding average point and mark it as the average distance; Compare the average distances corresponding to the same group, and take the node corresponding to the smallest average distance value as the new center point of the corresponding group.

[0039] In the above step S615, the steps for obtaining sets of regions include: Step S621: Randomly select a node that is not marked as a selected node and mark it as the current node; Step S622: Construct a set of regions and add the current node to the set of regions; Step S623: Obtain the adjacent nodes of the current node, mark the adjacent nodes with the same group as the current node as similar nodes, and add the similar nodes to the set of regions; Step S624: Obtain the adjacent nodes of the similar nodes and mark them as co - adjacent nodes; Mark the co - adjacent nodes with the same group as the current node as similar nodes and add the similar nodes to the set of regions; Step S625: Loop through step S624 until the groups corresponding to the adjacent nodes of all nodes in the set of regions are all different from the group corresponding to the current node, then the loop ends, obtain a set of regions, and mark all the nodes in the set of regions as selected nodes; Step S626: Loop through steps S621 to S625 until all nodes are marked as selected nodes, then the loop ends, and obtain sets of regions.

[0040] S7: Based on the flood risk levels of different city regions and combined with a pre - constructed historical disaster database, use a multi - objective decision - making optimization algorithm to dynamically formulate differentiated emergency response plans.

[0041] A method for dynamically formulating a differentiated emergency response plan includes: Obtain the number of monitoring stations in each urban area and mark it as the monitoring quantity; regard the monitoring quantity and the flood risk level of each urban area as a set of regional characteristic data, and the regional characteristic data corresponds one-to-one with the urban area; from the pre-constructed historical disaster database, obtain the set of rescue characteristic data corresponding to each set of regional characteristic data, where \(k\) is an integer greater than 1; the rescue characteristic data includes the number of rescue personnel and the quantity of various rescue materials, such as lifeboats, life jackets, sandbags, drainage pumps, etc.; the historical disaster database is constructed by those skilled in the art by collecting the rescue characteristic data corresponding to the urban areas with different regional characteristic data when historical flood disasters occur; according to the set of rescue characteristic data corresponding to each set of regional characteristic data, obtain the regional scope corresponding to each set of regional characteristic data, and the regional scope includes the number range and the material range; among them, the maximum value of the number range is the largest number of rescue personnel in the set of rescue characteristic data, and the minimum value of the number range is the smallest number of rescue personnel in the set of rescue characteristic data; the material range includes the quantity range corresponding to each rescue material, and the maximum value of the quantity range is the largest quantity of the corresponding rescue material in the set of rescue characteristic data, and the minimum value of the quantity range is the smallest quantity of the corresponding rescue material in the set of rescue characteristic data; Randomly select a value from each range within each regional scope and construct a set of alternative sets, and a total of sets of alternative sets are constructed, and the sets of alternative sets are all different, where \(m\) is an integer greater than 1; add up the number of rescue personnel in each set of alternative sets in turn to obtain the total number of rescue personnel; add up the quantities of the same rescue materials in each set of alternative sets in turn to obtain the total quantity of each rescue material; according to the city's emergency resource management system, obtain the deployment data, and the deployment data includes the number of deployed personnel and the deployment quantity of each rescue material; among them, the number of deployed personnel is the total number of rescue personnel that the city can call, and the deployment quantity is the total number of various rescue materials that the city can call; compare the total number of rescue personnel in each set of alternative sets with the number of deployed personnel respectively, and compare each total material quantity with the corresponding deployment quantity respectively; mark the alternative sets in which the total number of rescue personnel is less than or equal to the number of deployed personnel and each total material quantity is less than or equal to the corresponding deployment quantity as rescue sets; if the total number of rescue personnel is greater than the number of deployed personnel, or there is an alternative set in which the total material quantity is greater than the corresponding deployment quantity, it is not marked; Set different digital tags for different flood risk levels and mark them as level tags; replace the flood risk levels in all regional feature data with the corresponding level tags and add them to each group of rescue sets in turn to obtain a rescue feature set; input each group of rescue feature sets into a trained effect prediction model respectively to predict the corresponding rescue data; the rescue data includes rescue efficiency, casualty rate and response cost; the effect prediction model is a deep neural network model; preset a ratio set, and the ratio set includes the ratio coefficients corresponding to the rescue efficiency, casualty rate and response cost, and the ratio set is preset by those skilled in the art according to the actual situation; multiply the rescue efficiency, casualty rate and response cost corresponding to each group of rescue sets by the corresponding ratio coefficients in the ratio set respectively to obtain the efficiency coefficient, casualty coefficient and cost coefficient in turn; subtract the casualty coefficient from the efficiency coefficient, and then subtract the cost coefficient to obtain the rescue effect; compare the rescue effects corresponding to each group of rescue feature sets respectively, and mark the rescue feature set with the largest rescue effect as the best feature set; use the rescue set in the best feature set as the emergency response plan.

[0042] In this embodiment, by constructing a spatially integrated rainfall monitoring network, it is possible to integrate multi-source rainfall monitoring data such as rain gauges, weather radars and remote sensing satellites, realize comprehensive real-time monitoring of rainfall within the urban area, and improve the spatio-temporal resolution and continuity of rainfall information; adopt time alignment and spatial registration technologies to effectively solve the time differences and coordinate inconsistencies between data sources of different monitoring means, and ensure the spatio-temporal consistency of the fused rainfall data; drive a hydrodynamic model based on the fused rainfall data to accurately simulate the urban surface hydrological process and extract water flow feature data, laying a reliable foundation for flood risk assessment; construct a flood risk assessment system based on fuzzy comprehensive evaluation, which can intelligently evaluate the flood risk levels of different urban areas and provide a scientific basis for emergency response; combine with the historical disaster database, adopt a multi-objective decision-making optimization algorithm to dynamically formulate differentiated emergency response plans, while ensuring rescue efficiency and reducing response costs, minimize the casualty rate to the greatest extent, thereby significantly improving the accuracy and effectiveness of emergency rescue; realize intelligent perception and response to urban flood disasters, which can effectively support the emergency response requirements in a dynamic environment, improve the urban flood prevention and control ability and disaster resistance level, and thus significantly improve the scientificity and efficiency of flood disaster response.

[0043] Embodiment 2 This application also provides an electronic device. The electronic device may include one or more processors and one or more memories. Among them, computer-readable code is stored in the memory, and when the computer-readable code is run by one or more processors, it can execute a method for intelligent flood perception and decision-making of multi-source rainfall data fusion as described above.

[0044] The method or system according to an embodiment of the present application can also be implemented by means of the architecture of the electronic device shown in the present application. The electronic device may include a bus, one or more CPUs, a ROM, a RAM, a communication port connected to a network, an input / output, a hard disk, etc. The storage device in the electronic device, such as the ROM or the hard disk, can store a method for intelligent flood perception and decision-making for multi-source rainfall data fusion provided by the present application. Further, the electronic device may further include a user interface. Of course, the architecture shown in the present application is only exemplary. When implementing different devices, one or more components shown in the electronic device of the present application may be omitted according to actual needs.

[0045] Embodiment 3 Referring to the figure shown, an embodiment of the present application discloses a computer-readable storage medium. A computer-readable instruction is stored on the computer-readable storage medium. When the computer-readable instruction is run by a processor, it can execute a method for intelligent flood perception and decision-making for multi-source rainfall data fusion according to an embodiment of the present application as described with reference to the above drawings. The storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory, etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0046] In addition, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the present application provides a non-transitory machine-readable storage medium storing machine-readable instructions that can be run by a processor to execute instructions corresponding to the method steps provided by the present application, such as: a method for intelligent flood perception and decision-making for multi-source rainfall data fusion. When the computer program is executed by a central processing unit (CPU), the above functions defined in the method of the present application are executed.

[0047] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

[0048] It should be noted that, in this text, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device including a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including one..." does not exclude the presence of additional identical elements in the process, method, article or device including said element.

[0049] In the description of the present invention, it should be understood that terms such as "first", "second", etc. are only used for distinguishing descriptions and cannot be construed as indicating or implying relative importance.

[0050] In the description of the present invention, unless otherwise specified, the meaning of "a plurality" is two or more.

[0051] In the description of the present invention, the meaning of "several" is one or more, and the meaning of "a large number" is two or more.

[0052] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0053] For the formulas in this specification, the dimension is removed and only the numerical values are calculated. The formula is obtained by collecting a large amount of data and performing software simulation to get a formula closest to the actual situation. The preset parameters and threshold values in the formula are set by those skilled in the art according to the actual situation.

[0054] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the claims and their equivalents.

Claims

1. An intelligent flood perception decision-making method based on multi-source rainfall data fusion, characterized in that: include: S1: Adopt multi-source data collection technology to build a spatially integrated rainfall monitoring network and collect multi-dimensional rainfall data sets in real time; S2: Temporal alignment and spatial registration of multidimensional rainfall datasets to generate rainfall processing data; S3: Using data fusion algorithm, multi-dimensional data fusion is performed on rainfall processing data to form fused rainfall data; S4: Obtain hydrological environment data and build a hydrological dynamics model based on the hydrological environment data; S5: Drive the hydrological dynamics model based on the fused rainfall data to simulate the flow evolution process and obtain the flow characteristic data; S6: Combine water flow characteristic data and fused rainfall data to build a flood risk assessment system based on fuzzy comprehensive evaluation to intelligently assess the flood risk level of different urban areas; S7: Based on the flood risk levels of different urban areas and combined with the pre-built historical disaster database, a multi-objective decision-making optimization algorithm is used to dynamically formulate differentiated emergency response plans.

2. The intelligent flood perception decision-making method based on multi-source rainfall data fusion according to claim 1 is characterized in that: The method for constructing a spatial integrated rainfall monitoring network comprises: set up Monitoring sites, is an integer greater than 1; Randomly select from monitoring sites monitoring sites, and as a set of sites, a total of Group site collections, , ; Obtain the monitoring range of the city range and each monitoring site, merge the monitoring range of each monitoring site in each site set, and obtain the total monitoring range of each site set; Superimpose the total monitoring range of each site set with the city range, mark the site set whose total monitoring range is greater than or equal to the city range as the candidate set, and do not mark the site set whose total monitoring range is less than the city range; Count the number of monitoring sites in each candidate set and mark it as the number of sites, and mark the candidate set with the smallest number of sites as the screening set; Set a rain gauge for each monitoring site in the screening set, and build a spatial integrated rainfall monitoring network in combination with meteorological radar and remote sensing satellite; Multidimensional rainfall datasets include The monitoring data is the rainfall collected by the monitoring stations, the radar data is the rainfall collected by the meteorological radar, and the remote sensing data is the rainfall collected by the remote sensing satellite.

3. The intelligent flood perception decision-making method based on multi-source rainfall data fusion according to claim 2 is characterized in that: Methods for temporal alignment of multidimensional rainfall datasets include: Get the acquisition time of monitoring data in the multidimensional rainfall data set and mark it as the current time; get the acquisition time of radar data in the multidimensional rainfall data set and mark it as radar time; get the acquisition time of remote sensing data in the multidimensional rainfall data set and mark it as remote sensing time; subtract radar time from current time to get radar difference time; subtract remote sensing time from current time to get remote sensing difference time; get historical data, which includes Set historical radar data and The historical remote sensing data is the historical radar data, the historical remote sensing data is the remote sensing data obtained at the historical moment, is an integer greater than 1; Set the preset radar sampling period, radar difference time and The historical radar data of the group are input into the trained radar prediction model in turn to predict the corresponding real-time radar data. The real-time radar data is the radar data corresponding to the current time. The preset remote sensing sampling period, remote sensing difference time and The historical remote sensing data of the group are input into the trained remote sensing prediction model in turn to predict the corresponding real-time remote sensing data. The real-time remote sensing data is the remote sensing data corresponding to the current time. Both the radar prediction model and the remote sensing prediction model are deep neural network models.

4. The intelligent flood perception decision-making method based on multi-source rainfall data fusion according to claim 3 is characterized in that: Methods for spatial registration of multidimensional rainfall datasets include: Obtain the geographic coordinates of the monitoring site corresponding to each monitoring data in the multidimensional rainfall data set, and mark them as site coordinates; combine the monitoring data and site coordinates of each monitoring site to generate monitoring distribution data; project the real-time radar data to the WGS84 coordinate system to obtain projected radar data; obtain the geographic coordinates corresponding to each rainfall in the real-time remote sensing data, and mark them as remote sensing coordinates; obtain the geographic coordinates corresponding to each rainfall in the projected radar data, and mark them as radar coordinates; mark the site coordinates that are different from the remote sensing coordinates as the first coordinates, and mark the site coordinates that are different from the radar coordinates as the second coordinates; calculate the rainfall of each first coordinate based on the real-time remote sensing data using the spatial difference method; calculate the rainfall of each second coordinate based on the projected radar data using the spatial difference method; add each first coordinate and the corresponding rainfall to the real-time remote sensing data to generate remote sensing distribution data; add each second coordinate and the corresponding rainfall to the projected radar data to generate radar distribution data; Generate rainfall processing data based on remote sensing distribution data, radar distribution data and monitoring distribution data.

5. The intelligent flood perception decision-making method based on multi-source rainfall data fusion according to claim 4 is characterized in that: The method for forming fused rainfall data comprises: The rainfall corresponding to the same geographical coordinates in the remote sensing distribution data, radar distribution data and monitoring distribution data is taken as a group of data sets, and the data sets correspond to the geographical coordinates one by one; a weight set is preset, and the weight set includes weight coefficients corresponding to the remote sensing distribution data, radar distribution data and monitoring distribution data; each data in each data set is multiplied by the corresponding weight coefficient in the weight set, and the results are added in sequence to obtain the fused rainfall corresponding to each data set; based on the fused rainfall corresponding to each data set, fused rainfall data is formed.

6. The intelligent flood perception decision-making method based on multi-source rainfall data fusion according to claim 5 is characterized in that: The hydrological environment data include meteorological data, topographic data, soil and vegetation data, watershed hydrological data and groundwater data; Methods for constructing hydrodynamic models include: Construct a surface runoff model, the input of which is the fused rainfall data, and the output is the net rainfall; construct a shallow water dynamics model, the input of which is the net rainfall, and the output is the water flow characteristic data, which includes the water depth and water flow velocity; couple the surface runoff model with the shallow water dynamics model to construct a hydrological dynamics model; The steps to construct a shallow water dynamics model include: Step S401: using the Saint-Venant equations as basic equations, where the Saint-Venant equations include a continuity equation and a momentum equation; Step S402: converting hydrological environment data into model parameters; Step S403: Divide the city into grid cells, each of which corresponds to a monitoring site and a set of state variables, including water depth and water flow velocity; Step S404: setting boundary conditions, which include upstream boundary conditions, downstream boundary conditions, and lateral boundary conditions; wherein the upstream boundary condition is a depth time series, the downstream boundary condition is a depth-velocity relationship curve, and the lateral boundary condition is net rainfall; Step S405: setting initial conditions for each grid unit in turn, the initial conditions including initial water depth and initial water flow velocity; Step S406: Based on the model parameters, boundary conditions and initial conditions, a numerical calculation method is used to solve the Saint-Venant equations to construct a shallow water dynamics model; The fused rainfall data are input into the hydrological dynamics model to calculate the water flow characteristic data corresponding to each monitoring station.

7. The intelligent flood perception decision-making method based on multi-source rainfall data fusion according to claim 6 is characterized in that: The steps of intelligently assessing the flood risk levels of different urban areas include: Step S601: Divide the city into regions based on water flow characteristic data to obtain urban areas; Step S602: Obtain the corresponding rainfall amount of each urban area according to the fused rainfall data; count the number of corresponding rainfall amounts of each urban area and mark them as rainfall points; add the rainfall amounts of each urban area in turn, and then divide them by the corresponding rainfall points to obtain the average rainfall amount of each urban area; Step S603: construct multiple fuzzy sets for the water depth, water flow velocity and average rainfall respectively; Step S604: convert the fused feature data corresponding to each urban area into the membership degree of each corresponding fuzzy set respectively through fuzzification technology, and the fused feature data includes water depth, water flow velocity and average rainfall; Step S605: define fuzzy rules; Step S606: Match each group of fuzzified fusion feature data with fuzzy rules respectively, and use fuzzy reasoning method to perform fuzzy reasoning to obtain fuzzy reasoning results corresponding to each urban area, and the fuzzy reasoning results include the membership degree corresponding to each flood risk level, and the flood risk levels include extreme risk, high risk, medium risk and low risk; Step S607: Compare each membership degree in each fuzzy inference result, and take the flood risk level corresponding to the membership degree with the largest value as the flood risk level of the corresponding urban area.

8. The intelligent flood perception decision-making method based on multi-source rainfall data fusion according to claim 7 is characterized in that: In step S601, obtain The steps for each city region include: Step S610: Treat each set of water flow characteristic data as a node and randomly select nodes as the center point, and the nodes that are not the center point as the sample points. is an integer greater than 1; Step S611: According to The center points are constructed to correspond to For each group, calculate the Euclidean distance from each sample point to each center point in turn and mark it as point distance; Step S612: preset a distance threshold, compare each point distance corresponding to each sample point with the distance threshold, mark the center point corresponding to the point distance whose value is less than the distance threshold as a classification point, and do not mark the point distance whose value is greater than or equal to the distance threshold, and divide each sample point into the group corresponding to the corresponding classification point in turn; Step S613: Calculate a new center point corresponding to each group, and replace the center point of each group with the corresponding new center point; Step S614: loop through steps S611 to S613 until the new center point corresponding to each group calculated in step S613 is consistent with the corresponding new center point calculated in the previous loop, and the loop ends to obtain Groups; Step S615: Connectivity analysis is performed on the nodes in each group to obtain A collection of regions; A collection of regions, dividing the city into urban areas; In step S613, the method for calculating the new center point includes: Count the number of nodes in each group and mark them as the number of nodes; add up the nodes in each group in turn, and then divide by the corresponding number of nodes to obtain the average point corresponding to each group; calculate the point distance from each node in each group to the corresponding average point, and mark it as the average distance; compare the same average distances of corresponding groups, and take the node corresponding to the smallest average distance as the new center point of the corresponding group.

9. The intelligent flood perception decision-making method based on multi-source rainfall data fusion according to claim 8 is characterized in that: In step S615, obtain The steps for a region collection include: Step S621: randomly select a node that is not marked as a selected node, and mark it as the current node; Step S622: construct a region set and add the current node to the region set; Step S623: Obtain the neighboring nodes of the current node, mark the neighboring nodes of the same group as the current node as nodes of the same type, and add the nodes of the same type to the region set; Step S624: Obtain neighboring nodes of the same type of node and mark them as same-type neighboring nodes; mark the same-type neighboring nodes of the same group as the current node as the same-type nodes, and add the same-type nodes to the region set; Step S625: looping step S624 until the groups corresponding to the adjacent nodes of all nodes in the region set are different from the group corresponding to the current node, then the loop ends, obtaining a region set, and marking all nodes in the region set as selected nodes; Step S626: loop through steps S621 to S625 until all nodes are marked as selected nodes, then the loop ends and the A collection of regions.

10. The intelligent flood perception decision-making method based on multi-source rainfall data fusion according to claim 9 is characterized in that: The method for dynamically formulating differentiated emergency response plans includes: Obtain the number of monitoring stations in each urban area and mark them as the monitoring number; take the monitoring number and flood risk level of each urban area as a set of regional characteristic data; obtain the corresponding regional characteristic data of each set from the pre-built historical disaster database. Group rescue feature data, is an integer greater than 1; the rescue characteristic data includes the number of rescued people and the quantity of various rescue materials; according to the corresponding regional characteristic data of each group A set of rescue feature data is obtained, and the regional range corresponding to each set of regional feature data is obtained; a value is randomly selected from each range within each regional range, and a set of candidate sets is constructed to construct a total of Group alternative sets; add the number of rescued people in each alternative set in turn to obtain the total number of rescued people; add the number of materials with the same corresponding rescue materials in each alternative set in turn to obtain the total number of materials corresponding to each rescue material; obtain the deployment data, which includes the number of deployed people and the deployment quantity of each rescue material; compare the total number of rescued people with the deployment number in each alternative set, and compare each total number of materials with the corresponding deployment quantity; mark the alternative sets whose total number of rescued people is less than or equal to the deployment number and whose total number of materials is less than or equal to the corresponding deployment quantity as rescue sets; the alternative sets whose total number of rescued people is greater than the deployment number or whose total number of materials is greater than the corresponding deployment quantity will not be marked; Different digital labels are set for different flood risk levels and marked as level labels; the flood risk levels in all regional feature data are replaced with corresponding level labels, and added to each rescue set in turn to obtain a rescue feature set; each rescue feature set is input into the trained effect prediction model to predict the corresponding rescue data; the rescue data includes rescue efficiency, casualty rate and response cost; the effect prediction model is a deep neural network model; a preset proportion set includes proportional coefficients corresponding to rescue efficiency, casualty rate and response cost; the rescue efficiency, casualty rate and response cost corresponding to each rescue set are multiplied by the corresponding proportional coefficient in the proportion set, respectively, to obtain the efficiency coefficient, casualty coefficient and cost coefficient in turn; the efficiency coefficient is subtracted from the casualty coefficient, and then the cost coefficient is subtracted to obtain the rescue effect; the rescue feature set with the largest rescue effect is marked as the best feature set, and the rescue set in the best feature set is used as the emergency response plan.

Images