A flood risk forecasting method and system considering index and weight uncertainty

Abstract

The application provides a flood risk prediction method and system considering index and weight uncertainty, and belongs to the technical field of risk analysis, and specifically comprises the following steps: determining the weight coefficients of flood monitoring indexes corresponding to different combinations based on the flood monitoring indexes of historical flood processes in different combinations, determining stable monitoring indexes based on the analysis results of the weight coefficients, determining the construction strategy of the influence model of the flood monitoring indexes based on the variation of the weight coefficients of the flood monitoring indexes between different combinations and based on the stable monitoring index data, and determining a flood risk prediction analysis method according to the influence model and the rainfall data of the rainfall process before the current rainfall process, so that the accuracy of flood risk prediction processing is improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of risk analysis, and particularly relates to a flood risk prediction method and system considering index and weight uncertainty. BACKGROUND

[0002] In order to realize the analysis and processing of flood risk, a risk assessment model and a key flood risk assessment index weight optimization model are constructed in the invention patent application CN202411713523.0 "Flood risk dynamic zoning method and system based on factor multiple optimization", an optimal weight combination scheme is calculated by using a simulated annealing optimization genetic-local search hybrid algorithm, and is input into the risk assessment model for calculation, so that the flood risk dynamic zoning of the research area is obtained, thereby scientific and reasonable dynamic risk assessment can be provided, but the following technical problems exist:

[0003] With the change of rainfall data, the indexes such as terrain and soil type will inevitably change, and thus the weight coefficients of different indexes causing floods will also change, so how to realize the updating and identification processing of the weight coefficients of different indexes, thereby improving the accuracy of flood risk analysis and processing, becomes a technical problem to be solved.

[0004] Therefore, a flood risk prediction method and system considering index and weight uncertainty are urgently needed. SUMMARY

[0005] To achieve the purpose of the application, the application adopts the following technical solutions:

[0006] Specifically, the application provides a flood risk prediction method considering index and weight uncertainty, which specifically comprises:

[0007] S1, based on historical flood data of a specific region, determining the variation of flood monitoring indexes between historical flood processes, when the variation does not meet the requirements, dividing the historical flood processes into combinations according to the variation of the flood monitoring indexes, determining the weight coefficients of the flood monitoring indexes corresponding to different combinations based on the flood monitoring indexes of the historical flood processes in different combinations, and determining stable monitoring indexes based on the analysis results of the weight coefficients.

[0008] S2, based on the stable monitoring index data, determining the construction strategy of the influence model of the flood monitoring indexes based on the variation of the weight coefficients of the flood monitoring indexes between different combinations, and determining the prediction and analysis method of the flood risk according to the influence model and the rainfall data of the rainfall process before the current rainfall process.

[0009] The application has the following beneficial effects:

[0010] The determination of the construction strategy of the influence model of the flood monitoring index is based on the change of the weight coefficient of the flood monitoring index between different combinations, realizes the determination of the flood monitoring target which needs to construct the influence model of the weight coefficient from the size of the weight coefficient of the flood monitoring target and the change risk, thereby improving the accuracy and reliability of the weight coefficient, and further combining the stable monitoring target data, realizes the determination of the construction strategy of the influence model of the different flood monitoring indexes in the case of the difference of the composition data of the stable monitoring target.

[0011] According to the influence model and the rainfall data of the rainfall process before the current rainfall process, the prediction analysis method of the flood risk not only considers the influence of the rainfall data on the probability of the change of the weight coefficient of the flood monitoring index, but also further combines the influence model to realize the reliable degree of the weight coefficient of the current flood monitoring target, and further realizes the determination of the evaluation scheme of the weight coefficient of other flood monitoring targets, thereby improving the accuracy of the flood monitoring analysis result.

[0012] Further, the historical flood data is the historical flood process of the specific region and the time of different historical flood processes.

[0013] Further, the flood monitoring index includes a short-time heavy rainfall index, a continuous cumulative rainfall index, a high-sand water flow, a water level critical value, a flow matching degree, a dam seepage flow and a soil water content.

[0014] Further, the change of the flood monitoring index between the historical flood processes is determined according to the change amount of the flood monitoring index between different historical flood processes, specifically according to the change of the monitoring data of the flood monitoring index when the flood occurs.

[0015] Further, the determination that the change does not meet the requirements specifically includes:

[0016] According to the change of the flood monitoring index between the historical flood processes, the monitoring data of the flood monitoring target when the flood occurs in the historical flood process is determined;

[0017] According to the monitoring data, the change amount of the monitoring data of the historical flood process and the previous historical flood process is determined.

[0018] Based on the change amount, it is determined whether the change meets the requirements.

[0019] Further, the determination method of the prediction analysis method of the flood risk is:

[0020] Determine a flood monitoring index for constructing the influence model based on the influence model;

[0021] Determine rainfall data before the current rainfall process according to the rainfall data, and determine rainfall of the rainfall process before the current rainfall process based on the rainfall data before the current rainfall process;

[0022] Determine the prediction analysis method of the flood risk based on the flood monitoring index for constructing the influence model and the rainfall of the rainfall process before the current rainfall process.

[0023] In a second aspect, the present application provides a computer system, comprising a memory and a processor connected in communication, and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to perform the flood risk prediction method considering the uncertainty of indexes and weights.

[0024] Other features and advantages will be set forth in the accompanying description, and in part will be apparent from the description and the drawings, or can be learned by practice of the application.

[0025] In order to make the above-mentioned objects, features and advantages of the present application more apparent, the following preferred embodiments are specifically described with reference to the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0026] The above and other features and advantages of the present application will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings in which:

[0027] Figure 1 A flow chart of a flood risk prediction method considering the uncertainty of indexes and weights;

[0028] Figure 2 A flow chart of determining that the change condition does not meet the requirement;

[0029] Figure 3 A flow chart of a method for determining a stable monitoring index;

[0030] Figure 4 A flow chart of a method for determining a construction strategy of an influence model of a flood monitoring index;

[0031] Figure 5 A framework diagram of a computer system. DETAILED DESCRIPTION

[0032] In order for those skilled in the art to better understand the technical solutions in the specification, the technical solutions in the specification will be clearly and completely described in the following with reference to the drawings in the specification. Obviously, the described embodiments are only part of the embodiments of the specification, not all. Based on the embodiments of the specification, all other embodiments obtained by those skilled in the art without creative labor should belong to the protection scope of the specification.

[0033] In the present application, by changing the variation of different flood monitoring indicators with rainfall data, the determination of the flood monitoring indicators requiring the construction of the influence model is carried out, so as to specifically correct the weight coefficient of the flood monitoring indicators, and further improve the reliability of the flood risk prediction processing, and avoid the technical problems of the weight coefficient of the flood monitoring indicators without dynamic updating due to the changes of topography caused by rainfall.

[0034] Embodiment 1

[0035] As Figure 1 shown, the present application provides a flood risk prediction method considering index and weight uncertainty, specifically comprising:

[0036] S1, based on the historical flood data of a specific region, the variation of the flood monitoring indicators between the historical flood processes is determined, when the variation does not meet the requirements, according to the variation of the flood monitoring indicators, the historical flood processes are divided into at least two combinations, according to the flood monitoring indicators of the historical flood processes in different combinations, the weight coefficients of the flood monitoring indicators corresponding to different combinations are determined, and the stable monitoring indicators are determined based on the analysis results of the weight coefficients.

[0037] Further, the historical flood data is the historical flood process of the specific region and the time of different historical flood processes.

[0038] Further, the flood monitoring indicators include short-time heavy rainfall indicators, continuous cumulative rainfall indicators, high-sand water flow, water level critical value, flow matching degree, dam seepage flow and soil moisture content.

[0039] Further, the variation of the flood monitoring indicators between the historical flood processes is determined according to the variation of the flood monitoring indicators between different historical flood processes, specifically according to the variation of the monitoring data of the flood monitoring indicators when the flood occurs.

[0040] Specifically, as Figure 2 shown, it is judged that the variation does not meet the requirements, specifically comprising:

[0041] determining monitoring data of the flood monitoring target when the historical flood process occurs according to variation of the flood monitoring indexes between the historical flood processes;

[0042] determining the variation amount of the monitoring data of the historical flood process and the monitoring data of the previous historical flood process according to the monitoring data;

[0043] determining whether the variation condition meets the requirement based on the variation amount.

[0044] It can be understood that, determining whether the variation condition meets the requirement based on the variation amount specifically comprises:

[0045] determining an average of variation rates of the monitoring data of the flood monitoring target between the different historical flood processes and the monitoring data of the previous historical flood process based on the variation amount, and taking the average as an index variation rate;

[0046] determining whether the variation condition meets the requirement according to the index variation rate of the flood monitoring index.

[0047] It should be noted that, when there is a flood monitoring index with an index variation rate greater than a preset variation rate threshold, it is determined that the variation condition does not meet the requirement.

[0048] In one possible embodiment, the variation rate is determined according to a ratio of an absolute value of the variation amount of the monitoring data of the flood monitoring target between the historical flood process and the monitoring data of the previous historical flood process to the monitoring data of the historical flood process.

[0049] In another embodiment, determining that the variation condition does not meet the requirement specifically comprises:

[0050] determining monitoring data of the flood monitoring target when the historical flood process occurs according to variation of the flood monitoring indexes between the historical flood processes;

[0051] determining the variation rate of the monitoring data of the historical flood process and the monitoring data of the previous historical flood process according to the monitoring data;

[0052] determining whether the variation condition meets the requirement according to the variation rate of the monitoring data of the historical flood process and the monitoring data of the previous historical flood process.

[0053] Specifically, when there are multiple historical flood processes whose variation rate of monitoring data of the flood monitoring target during the flood does not meet the requirement, for example, when there are 2 or more historical flood processes whose variation rate of monitoring data of the flood monitoring target during the flood is greater than 0.03 than the previous historical flood process, the variation of the flood monitoring index at this time is more serious, and therefore, the construction method of using a unified weight coefficient may not accurately determine the weight coefficient of the current flood monitoring index, and therefore it is determined that the variation does not meet the requirement.

[0054] Further, the historical flood processes are divided into a plurality of combinations, specifically including:

[0055] If the variation rate of monitoring data of the flood monitoring target during the flood of the historical flood process and the previous historical flood process meets the requirement, the historical flood process and the previous historical flood process are divided into the same combination.

[0056] Further, the weight coefficient of the flood monitoring index is determined according to the flood monitoring index of the historical flood process in the combination, the monitoring data during the flood, and the weight coefficient of different flood monitoring indexes is determined by using a correlation analysis method.

[0057] It can be understood that the correlation analysis method includes Pearson correlation analysis method and Spearman rank correlation analysis method.

[0058] Specifically, as shown in Figure 3 The method for determining the stable monitoring index is:

[0059] The weight coefficient of the flood monitoring index in different combinations is determined according to the analytical result of the weight coefficient;

[0060] According to the similarity of the weight coefficient of the flood monitoring index in different combinations, it is determined whether the flood monitoring index is a stable monitoring index.

[0061] It can be understood that when the weight coefficient of the flood monitoring index in different combinations is in the same range, the water supply monitoring index is determined to be a stable monitoring index.

[0062] It should be noted that the weight coefficient has a value range of 0 to 1, and specifically, the weight coefficient is equally divided into a plurality of ranges based on a preset interval, for example, the preset monitoring is 0.05.

[0063] S2 determines a construction strategy of an influence model of the flood monitoring index based on the stable monitoring index data and based on a variation of the weight coefficients of the flood monitoring index between different combinations, and determines a prediction analysis method of the flood risk according to the influence model and rainfall data of a rainfall process before a current rainfall process.

[0064] Specifically, as shown in Figure 4 the method for determining the construction strategy of the influence model of the flood monitoring index is:

[0065] based on the stable monitoring index data, determine a composition of the stable monitoring index among the flood monitoring indexes;

[0066] based on a variation of the weight coefficients of the flood monitoring index between different combinations, determine distribution data of the weight coefficients of the flood monitoring index in different ranges;

[0067] determine the construction strategy of the influence model of the flood monitoring index based on the distribution data of the weight coefficients of the flood monitoring index in different ranges and the composition of the stable monitoring index among the flood monitoring indexes.

[0068] It can be understood that when the composition of the stable monitoring index among the flood monitoring indexes does not meet the requirements, that is, the number of stable monitoring indexes is small, if the influence model is not constructed for all monitoring indexes, the accuracy of the overall flood risk will inevitably be affected, and the influence model is constructed for all flood monitoring indexes.

[0069] In addition, it can be understood that when the composition of the stable monitoring index among the flood monitoring indexes meets the requirements, the distribution data of the weight coefficients of the flood monitoring index in different ranges is determined, and if the maximum value of the weight coefficients is within a preset interval, that is, the weight coefficients of the flood monitoring index are small, the influence on the flood risk is small, and therefore the flood monitoring index does not need to be constructed.

[0070] Further, if the maximum value of the weight coefficients of the flood monitoring index is not within the preset interval, if the flood monitoring index has a range number of weight coefficients greater than a preset number threshold, it means that the distribution of the weight coefficients of the flood monitoring index is relatively dispersed, and therefore the flood monitoring index needs to be constructed.

[0071] It should be noted that if the range of the weight coefficient of the flood monitoring index is not greater than the preset number threshold, the sum of the weight coefficients of the flood monitoring index after normalization processing of the monitoring data of different historical flood processes is used as the basis to determine the sum of the weight coefficients of the flood monitoring index that needs to be processed by the influence model, and if the sum of the weight coefficients of the flood monitoring index that needs to be processed by the influence model is greater than the preset weight coefficient threshold in different historical flood processes, the remaining flood monitoring index does not need to be processed by the influence model.

[0072] In addition, it can be understood that if the sum of the weight coefficients of the flood monitoring index that needs to be processed by the influence model is not greater than the preset weight coefficient threshold in different historical flood processes, the weight coefficient of the flood monitoring index in the historical flood process in which the sum of the weight coefficients of the flood monitoring index that needs to be processed by the influence model is not greater than the preset weight coefficient threshold is used as the basis to determine the monitoring demand value of the flood monitoring index, and when the monitoring demand value of the flood monitoring index is greater than the preset demand threshold, it is determined that the flood monitoring index needs to be processed by the influence model, and if the monitoring demand value of the flood monitoring index is not greater than the preset demand threshold, it is determined that the flood monitoring index does not need to be processed by the influence model.

[0073] In a possible embodiment, the monitoring demand value of the flood monitoring index is determined according to the average value of the weight coefficient of the flood monitoring index in the historical flood process in which the sum of the weight coefficients of the flood monitoring index that needs to be processed by the influence model is not greater than the preset weight coefficient threshold.

[0074] It should be noted that the influence model uses the rainfall amount between the last historical flood process and the weight coefficient of the flood monitoring index of the last historical flood process as the input, and uses the weight coefficient of the flood monitoring index of the current historical flood process as the output, so as to realize the evaluation processing of the influence of the rainfall data on the weight coefficient. In a possible embodiment, the influence model is constructed by using one or more of a BP neural network and an LSTM neural network.

[0075] Embodiment 2

[0076] Optionally, the method for determining the construction strategy of the influence model of the flood monitoring index is as follows:

[0077] Based on the stable monitoring index data, the composition of the stable monitoring index in the flood monitoring index is determined.

[0078] The distribution data of the weight coefficients of the flood monitoring indicators in different ranges is determined based on the variation of the weight coefficients of the flood monitoring indicators between different combinations, and the distribution discrete value of the flood monitoring indicators is determined based on the distribution data of the weight coefficients in different ranges.

[0079] The construction strategy of the influence model of the flood monitoring indicators is determined based on the distribution discrete value of the flood monitoring indicators and the composition of the stable monitoring indicators in the flood monitoring indicators.

[0080] In a possible embodiment, the distribution discrete value is determined according to the number of ranges of the weight coefficients of the flood monitoring indicators, and in a possible embodiment, the distribution discrete value is determined according to the product of the number of ranges of the weight coefficients of the flood monitoring indicators and a preset proportion factor, for example, the preset proportion factor is 0.1.

[0081] It can be understood that when the composition of the stable monitoring indicators in the flood monitoring indicators does not meet the requirements, that is, the number of stable monitoring indicators is small, for example, the proportion of the number in all flood monitoring indicators is less than 0.5, if the influence model is not constructed for all monitoring indicators, the accuracy of the overall flood risk will be inevitably affected, and the influence model is constructed for all flood monitoring indicators.

[0082] In addition, it should be noted that when the composition of the stable monitoring indicators in the flood monitoring indicators meets the requirements, if the distribution discrete value of the flood monitoring indicators is greater than a preset discrete threshold, for example, greater than 0.3, it is determined that the flood monitoring indicators need to be constructed.

[0083] Further, if the distribution discrete value of the flood monitoring indicators is not greater than the preset discrete threshold, a model construction matching value of the flood monitoring indicators is determined based on the maximum value of the weight coefficients of the flood monitoring indicators and the distribution discrete coefficient, and when the model construction matching value of the flood monitoring indicators is greater than a preset matching threshold, it is determined that the flood monitoring indicators need to be constructed.

[0084] In a possible embodiment, the model construction matching value of the flood monitoring indicators is determined according to the average value of the maximum value of the weight coefficients of the flood monitoring indicators and the distribution discrete coefficient, and when the model construction matching value of the flood monitoring indicators is greater than 0.3, it is determined that the flood monitoring indicators need to be constructed.

[0085] It can be understood that when the model construction matching value of the flood monitoring index is not greater than the preset matching threshold, when the number of the stable monitoring indexes requiring the construction of the influence model and the number of the flood monitoring indexes requiring the construction of the influence model both meet the requirements, it is determined that the flood monitoring index does not require the construction of the influence model.

[0086] In a possible embodiment, if the proportion of the number of the flood monitoring indexes requiring the construction of the influence model in the number of the flood monitoring indexes and the proportion of the number of the stable monitoring indexes requiring the construction of the influence model in the number of the stable monitoring indexes are both greater than 0.9, it is determined that the number of the stable monitoring indexes requiring the construction of the influence model and the number of the flood monitoring indexes requiring the construction of the influence model both meet the requirements.

[0087] Further, when either the number of the stable monitoring indexes requiring the construction of the influence model or the number of the flood monitoring indexes requiring the construction of the influence model does not meet the requirements, the flood monitoring indexes that do not belong to the stable monitoring indexes are all subjected to the construction of the influence model.

[0088] Optionally, the method for determining the prediction analysis method of the flood risk comprises the following steps.

[0089] Based on the influence model, the flood monitoring index subjected to the construction of the influence model is determined.

[0090] According to the rainfall data, the rainfall data before the current rainfall process is determined, and based on the rainfall data before the current rainfall process, the rainfall amount of the rainfall process before the current rainfall process is determined.

[0091] Based on the proportion of the flood monitoring index subjected to the construction of the influence model in all the flood monitoring targets, the model construction matching value is determined, and based on the model construction matching value and the rainfall amount of the rainfall process before the current rainfall process, the prediction analysis method of the flood risk is determined.

[0092] It can be understood that when the model construction matching value is greater than the preset matching threshold, for example, 0.9, and all the flood monitoring targets except the stable monitoring targets have constructed the influence model, the risk weight coefficient of the flood monitoring target is determined by using the influence model, the risk weight coefficient of the flood monitoring target is determined by using the maximum weight coefficient of the stable monitoring target which does not have the influence model, the monitoring data of different flood monitoring targets is subjected to normalization processing to obtain normalized monitoring data, and based on the sum of the risk weight coefficients of the normalized monitoring data, the prediction analysis result of the flood risk is determined.

[0093] Further, when the model construction matching value is not greater than the preset matching threshold value and all flood monitoring targets except the stable monitoring target do not construct the influence model, the influence of the flood monitoring indicators is determined based on the rainfall, wherein when the number of the flood monitoring targets which do not construct the influence model and whose variation does not meet the requirement is greater than a preset target number threshold value, for example, greater than 2, the risk weight coefficient of the flood monitoring target is determined by using the influence model, the risk weight coefficient of the flood monitoring target which does not exist in the influence model is determined by using a preset manner, the monitoring data of different flood monitoring targets is normalized to obtain normalized monitoring data, and the prediction analysis result of the flood risk is determined based on the sum of the risk weight coefficients of the normalized monitoring data.

[0094] It should be noted that the flood monitoring target which does not construct the influence model and whose variation does not meet the requirement under the rainfall is determined according to the variation of the weight coefficient of the flood monitoring target between the combination with the minimum absolute value of the deviation of the rainfall, wherein if the absolute value of the deviation of the rainfall in the interval date between two adjacent combinations is the minimum, the difference between the weight coefficient of the flood monitoring target of the previous combination is determined as the variation of the weight coefficient of the flood monitoring target under the rainfall, wherein when the variation is greater than 0.03, the flood monitoring target is determined as the flood monitoring target which does not construct the influence model and whose variation does not meet the requirement under the rainfall.

[0095] Further, when the number of the flood monitoring targets which do not construct the influence model and whose variation does not meet the requirement under the rainfall is not greater than the preset target number threshold value, the risk weight coefficient of the flood monitoring target is determined by using the influence model, the risk weight coefficient of the flood monitoring target which does not exist in the influence model is determined by using a second preset manner, the monitoring data of different flood monitoring targets is normalized to obtain normalized monitoring data, and the prediction analysis result of the flood risk is determined based on the sum of the risk weight coefficients of the normalized monitoring data.

[0096] Embodiment 3

[0097] In a second aspect, as shown in Figure 5 The present application provides a computer system, comprising a memory and a processor connected in communication, and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to perform the above-mentioned flood risk prediction method considering the uncertainty of indicators and weights.

[0098] Further, the method for determining the prediction analysis method of the flood risk is:

[0099] Based on the influence model, a flood monitoring index for constructing the influence model is determined.

[0100] According to the rainfall data, rainfall data before the current rainfall process is determined, and based on the rainfall data before the current rainfall process, rainfall amount of the rainfall process before the current rainfall process is determined.

[0101] Based on the flood monitoring index for constructing the influence model and the rainfall amount of the rainfall process before the current rainfall process, the prediction analysis method of the flood risk is determined.

[0102] Specifically, when the flood monitoring index for constructing the influence model meets the requirement, that is, all flood monitoring targets are constructed by the influence model or the flood monitoring targets except the stable monitoring targets are constructed by the influence model, the risk weight coefficient of the flood monitoring target is determined by using the influence model, the risk weight coefficient of the stable monitoring target without the influence model is determined by using the maximum weight coefficient, the monitoring data of different flood monitoring targets is normalized to obtain normalized monitoring data, the sum of the risk weight coefficients of the normalized monitoring data is used to determine the prediction analysis result of the flood risk.

[0103] Further, when the flood monitoring index for constructing the influence model does not meet the requirement, the number of the flood monitoring index without the construction of the influence model is determined, and when the number of the flood monitoring target without the construction of the influence model is greater than the preset monitoring target threshold, the risk weight coefficient of the flood monitoring target is determined by using the influence model, the risk weight coefficient of the stable monitoring target without the influence model is determined by using the preset method, the monitoring data of different flood monitoring targets is normalized to obtain normalized monitoring data, the sum of the risk weight coefficients of the normalized monitoring data is used to determine the prediction analysis result of the flood risk.

[0104] In addition, it can be understood that if the number of flood monitoring targets for which the influence model construction process is not performed is greater than the preset monitoring target number threshold, the weight sum of the flood monitoring targets for which the influence model construction process is not performed is determined according to the types of the flood monitoring targets for which the influence model construction process is not performed, and when the weight sum of the flood monitoring targets for which the influence model construction process is not performed does not meet the requirement, the risk weight coefficients of the flood monitoring targets are determined by using the influence model, the risk weight coefficients of the stable monitoring targets without the influence model are determined by using the preset method, the monitoring data of different flood monitoring targets are normalized to obtain normalized monitoring data, the prediction analysis result of the flood risk is determined according to the sum of the risk weight coefficients of the normalized monitoring data.

[0105] It should be noted that the weight sum of the flood monitoring targets for which the influence model construction process is not performed is determined according to the sum of the weight values of the flood monitoring targets for which the influence model construction process is not performed, and the weight values of the flood monitoring targets for which the influence model construction process is not performed are determined according to the types of the flood monitoring targets for which the influence model construction process is not performed, and the weight value of the stable monitoring target is less than that of the flood monitoring target not belonging to the stable monitoring target. In one possible embodiment, the weight values are 0.1 and 0.2, respectively.

[0106] In addition, it can be understood that when the weight sum of the flood monitoring targets for which the influence model construction process is not performed meets the requirement, the rainfall amount of the rainfall process before the current rainfall process, i.e., the rainfall amount of the rainfall process between the current rainfall process and the nearest historical flood process, is determined, the influence of the flood monitoring indicators is determined based on the rainfall amount, and when the number of the flood monitoring targets for which the influence model construction process is not performed and whose variation does not meet the requirement is greater than the preset target number threshold under the rainfall amount, the risk weight coefficients of the flood monitoring targets are determined by using the influence model, the risk weight coefficients of the stable monitoring targets without the influence model are determined by using the preset method, the monitoring data of different flood monitoring targets are normalized to obtain normalized monitoring data, the prediction analysis result of the flood risk is determined according to the sum of the risk weight coefficients of the normalized monitoring data.

[0107] Further, when the variation of the flood monitoring target under the rainfall does not meet the requirement and the number of flood monitoring targets that do not perform the construction process of the influence model is not greater than the preset target number threshold, the risk weight coefficient of the flood monitoring target is determined by using the influence model, and the risk weight coefficient of the stable monitoring target without the influence model is determined by using the second preset method. The prediction analysis result of the flood risk is determined by using the sum of the risk weight coefficients of the normalized monitoring data of different flood monitoring targets.

[0108] It should be noted that the preset method is to determine the risk weight coefficient of the flood monitoring target based on the variation of the weight coefficient of the flood monitoring target under the rainfall, combine the maximum value of the weight coefficient of the flood monitoring index in different combinations, and determine the risk weight coefficient of the flood monitoring target based on the sum of the variation and the maximum value of the weight coefficient. The second preset method is to determine the risk weight coefficient of the flood monitoring target based on the variation of the weight coefficient of the flood monitoring target under the rainfall, combine the weight coefficient of the flood monitoring index in the combination corresponding to the recent historical flood process, and determine the risk weight coefficient of the flood monitoring target based on the sum of the variation and the weight coefficient of the monitoring data.

[0109] Further, the variation of the weight coefficient of the flood monitoring target under the rainfall is determined according to the variation of the weight coefficient of the flood monitoring target between the combinations with the minimum absolute value of the deviation of the rainfall, wherein if the absolute value of the deviation of the rainfall in the interval date between two adjacent combinations is the minimum, the difference of the weight coefficient of the flood monitoring target between the previous combination is determined as the variation of the weight coefficient of the flood monitoring target under the rainfall.

[0110] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the difference from other embodiments. Especially, the device, equipment, and non-volatile computer storage medium embodiments are basically similar to the method embodiments, so the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment.

[0111] The above describes specific embodiments of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different than the order in the embodiments and still achieve the desired result. In addition, the processes depicted in the figures do not necessarily require the particular order shown or sequential order to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous or possible.

[0112] The above merely provides one or more embodiments of the present specification and is not intended to limit the present specification. One of ordinary skill in the art can make various modifications and changes to one or more embodiments of the present specification. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of the present specification should be included in the scope of claims of the present specification.

Claims

1. A flood risk forecasting method considering the uncertainty of indicators and weights, characterized in that, Specifically, it includes: Based on historical flood data of a specific region, the changes in flood monitoring indicators between historical flood events are determined. When the changes do not meet the requirements, the historical flood events are divided into multiple combinations according to the changes in the flood monitoring indicators. Based on the flood monitoring indicators of the historical flood events in different combinations, the weight coefficients of the flood monitoring indicators corresponding to different combinations are determined. Stable monitoring indicators are determined based on the analysis results of the weight coefficients. Based on the stable monitoring index data, and based on the changes in the weight coefficients of flood monitoring indicators among different combinations, the strategy for constructing the impact model of flood monitoring indicators is determined. Based on the aforementioned impact model and rainfall data from previous rainfall events, a method for predicting and analyzing flood risk is determined. The determination that the aforementioned changes do not meet the requirements specifically includes: Based on the changes in flood monitoring indicators between the aforementioned historical flood events, the monitoring data of the flood monitoring targets at the time of the floods during the historical flood events are determined; Based on the monitoring data, determine the amount of change in the monitoring data of the historical flood event compared to the previous historical flood event; Based on the amount of change, determine whether the change meets the requirements; The historical flood events are divided into multiple combinations, specifically including: If the rate of change between the monitoring data of the flood monitoring target during the flood in the historical flood process and the monitoring data of the flood monitoring target during the previous historical flood process meets the requirements, then the historical flood process and the previous historical flood process are classified into the same group. The weighting coefficients of the flood monitoring indicators are determined based on the monitoring data of historical flood processes in the combination, using correlation analysis methods to determine the weighting coefficients of different flood monitoring indicators. The method for determining the stability monitoring indicators is as follows: Based on the analysis results of the weighting coefficients, the weighting coefficients of flood monitoring indicators in different combinations are determined; Based on the similarity of the weighting coefficients of flood monitoring indicators in different combinations, it is determined whether the flood monitoring indicator is a stable monitoring indicator. The method for determining the construction strategy of the impact model of the flood monitoring indicators is as follows: Based on the stability monitoring index data, the composition of the stability monitoring index in the flood monitoring index is determined; Based on the variation of the weight coefficients of flood monitoring indicators among different combinations, the distribution data of the weight coefficients of the flood monitoring indicators in different ranges are obtained. Based on the distribution data of the weight coefficients of the flood monitoring indicators in different ranges and the composition of stable monitoring indicators in the flood monitoring indicators, the construction strategy of the impact model of the flood monitoring indicators is determined.

2. The flood risk forecasting method considering the uncertainty of indicators and weights as described in claim 1, characterized in that, The historical flood data refers to the historical flood events in the specific region and the times of different historical flood events.

3. The flood risk forecasting method considering the uncertainty of indicators and weights as described in claim 1, characterized in that, The flood monitoring indicators include short-term heavy rainfall indicators, continuous cumulative rainfall indicators, high-sediment flow, water level critical value, flow matching degree, dam seepage flow, and soil moisture content.

4. The flood risk forecasting method considering the uncertainty of indicators and weights as described in claim 1, characterized in that, The changes in flood monitoring indicators between historical flood events are determined based on the amount of change in flood monitoring indicators between different historical flood events.

5. The flood risk forecasting method considering the uncertainty of indicators and weights as described in claim 1, characterized in that, Based on the amount of change, determining whether the change meets the requirements specifically includes: Based on the aforementioned amount of change, the average rate of change of the monitoring data of the flood monitoring target in different historical flood processes and the previous historical flood process is determined, and this average rate of change is used as the indicator rate of change. Based on the rate of change of flood monitoring indicators, determine whether the changes meet the requirements.

6. The flood risk forecasting method considering the uncertainty of indicators and weights as described in claim 1, characterized in that, The method for determining the flood risk prediction and analysis method is as follows: Based on the aforementioned impact model, flood monitoring indicators for constructing the impact model are determined; Based on the rainfall data, determine the rainfall data prior to the current rainfall event, and based on the rainfall data prior to the current rainfall event, determine the rainfall amount of the rainfall event prior to the current rainfall event; Based on the flood monitoring indicators processed by the aforementioned impact model construction and the rainfall amount of the previous rainfall process, a predictive analysis method for determining the flood risk is used.

7. A computer system, comprising: A memory and processor connected by communication, and a computer program stored in the memory and capable of running on the processor, characterized in that, when the processor runs the computer program, it executes a flood risk forecasting method considering the uncertainty of indicators and weights as described in any one of claims 1-6.

Images