Flood forecasting method, device and storage medium based on historical similar floods

By screening and combining single-element and multi-element schemes of historical flood characteristics, the most similar historical floods of target floods were determined, which solved the problem of low accuracy of existing flood forecasts and achieved more accurate and efficient flood forecasts.

CN118761516BActive Publication Date: 2024-11-15BEIJING ELITEL INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411245128.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-06
Publication Date
2024-11-15
Estimated Expiration
2044-09-06

AI Technical Summary

Technical Problem

The existing flood forecasting technology has low accuracy, making it difficult to effectively use information from heavy rainstorms and floods in historically similar times for real-time flood forecasting and reservoir scheduling.

Method used

By screening the single element scheme that best reflects historical floods, a multi-element scheme is generated, and the target scheme that best reflects historical floods are determined, so as to determine the historical floods that are most similar to the target floods that are about to occur or have occurred based on the target scheme. Make flood forecasts.

Benefits of technology

It improves the accuracy and efficiency of flood forecasting, ensures the scientific basis for flood control decisions, and enhances the understanding and prediction ability of flood characteristics in specific regions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118761516B_ABST
    Figure CN118761516B_ABST
Patent Text Reader

Abstract

The present application discloses a flood forecasting method, device and storage medium based on historical similar floods. It relates to the field of flood prediction technology. The method includes: according to the first flood forecast of the first historical flood corresponding to the preset single-element scheme, the single-element scheme is screened to generate a multi-element scheme, wherein a single-element scheme is composed of one element and a multi-element scheme is composed of multiple elements; according to the second flood forecast of the first historical flood corresponding to the multi-element scheme, a target scheme is determined from the multi-element scheme; based on the target scheme, according to the comprehensive similarity between the target flood and the first historical flood, the second historical flood with the highest comprehensive similarity is determined; and according to the target flood, the second historical flood is mapped and processed to generate a third flood forecast. The technical problem of low accuracy of flood forecasting in the prior art is solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of flood prediction, and in particular to a flood forecasting method, device and storage medium based on historical similar floods. Background Art

[0002] Accurate and timely flood forecasting is the scientific basis for flood control decisions. In actual flood control decisions, in addition to the need to configure advanced water situation monitoring and reporting systems, modern communication and computer means, and compile flood forecasting plans in various ways, it is also necessary to have an in-depth study and understanding of the characteristics of rainstorm floods in the basin. The time and magnitude of floods in a specific area have the characteristics of periodic changes. Historical floods can reflect the comprehensive impact of local weather and underlying surfaces to a certain extent. Especially in various stages of flood control and dispatch, how to effectively use the occurrence, development and evolution information of similar rainstorm floods in history is particularly important for guiding real-time flood forecasting and reservoir dispatching.

[0003] However, existing technologies still have the problem of insufficient forecast accuracy. Despite continuous technological advances, the accuracy of flood forecasts still needs to be improved due to the complexity and dynamics of natural phenomena, especially the increase in extreme weather events.

[0004] The solution with the publication number CN117520852A provides a method for determining similar processes of rainstorms and floods based on multiple dimensions, including the following steps: collecting rainstorm and flood data of known basins and dividing them into events; dividing historical search samples and test samples in the data set; constructing a hydrological state similarity calculation model to obtain the hydrological state similarity of historical search samples; constructing a twin network to extract image features to carry out similarity analysis in the time dimension and space dimension, and obtain the similarity of historical search samples in the time dimension and space dimension; performing linear fitting of multi-dimensional similarity based on Lasso regression, and calculating the weight parameters of hydrological state similarity, time dimension similarity and space dimension similarity; based on the fitted weight parameters, integrating hydrological state similarity, time dimension similarity and space dimension similarity to construct a multi-dimensional similar process search model for rainfall events; and searching for historical similar rainstorm and flood events. This method takes into account the hydrological characteristics of multiple dimensions of rainstorms and floods, and effectively improves the accuracy of searching for similar historical events.

[0005] The solution with the publication number CN117454791A provides a method for predicting the evolution of flood peaks based on similarity analysis of rainfall and water level characteristics, which solves the problem that the current prediction of the evolution of flood peaks is mainly based on hydrodynamics and hydrological model calculations, which has high requirements on computing power and algorithms, and cannot well meet the needs of rapid simulation calculations in actual flood prevention and disaster reduction work. First, this method collects and processes the hydrological and meteorological data of the basin; divides the basin sections and constructs the topological relationship of the flood peak transmission in the basin; second, analyzes and calculates the historical hydrological and meteorological data characteristics of each section to form a database; third, finds historical floods similar to the current flood, and finally, based on the similarity analysis of the combination of historical rainfall and flood processes, predicts the evolution of flood peaks section by section. The present invention performs similarity analysis based on historical rainfall and flood data, and is applied to the prediction of flood peak evolution. It can simply and quickly realize the dynamic simulation of the evolution of flood peaks, which plays a great role in the actual application of flood prevention and disaster reduction work.

[0006] With respect to the technical problem of low flood forecasting accuracy existing in the above-mentioned prior art, no effective solution has been proposed yet. Summary of the invention

[0007] The embodiments of the present application provide a flood forecasting method, device and storage medium based on historical similar floods, so as to at least solve the technical problem of low flood forecasting accuracy existing in the prior art.

[0008] According to one aspect of an embodiment of the present application, a flood forecasting method based on historical similar floods is provided, including: based on a first flood forecast of a first historical flood corresponding to a preset single-element scheme, screening the single-element schemes to generate a multi-element scheme, wherein a single-element scheme is composed of one element and a multiple-element scheme is composed of multiple elements; based on a second flood forecast of the first historical flood corresponding to the multi-element scheme, determining a target scheme from the multi-element schemes; based on the target scheme, determining a second historical flood with the highest comprehensive similarity according to the comprehensive similarity between the target flood and the first historical flood; and mapping the second historical flood according to the target flood to generate a third flood forecast.

[0009] According to another aspect of an embodiment of the present application, a flood forecasting device based on historical similar floods is also provided, including: a scheme screening module, used to screen single-element schemes according to a first flood forecast of a first historical flood corresponding to a preset single-element scheme, and generate a multi-element scheme, wherein a single-element scheme is composed of one element, and a multiple-element scheme is composed of multiple elements; a scheme determination module, used to determine a target scheme from the multi-element schemes according to a second flood forecast of the first historical flood corresponding to the multi-element scheme; a flood determination module, used to determine a second historical flood with the highest comprehensive similarity based on the target scheme and according to the comprehensive similarity between the target flood and the first historical flood; and a forecast generation module, used to map the second historical flood according to the target flood, and generate a third flood forecast.

[0010] According to another aspect of an embodiment of the present application, a flood forecasting device based on historical similar floods is also provided, including: a processor; and a memory connected to the processor, for providing the processor with instructions for processing the following processing steps: based on a first flood forecast of a first historical flood corresponding to a preset single-element scheme, screening the single-element schemes to generate a multi-element scheme, wherein a single-element scheme is composed of one element and a multiple-element scheme is composed of multiple elements; based on a second flood forecast of the first historical flood corresponding to the multi-element scheme, determining a target scheme from the multi-element schemes; based on the target scheme, determining a second historical flood with the highest comprehensive similarity according to the comprehensive similarity between the target flood and the first historical flood; and mapping the second historical flood according to the target flood to generate a third flood forecast.

[0011] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0012] In the embodiment of the present application, first, the computing device selects a single-element scheme that best reflects the flood characteristics of historical floods, then generates a multi-element scheme based on the single-element scheme, and then determines the target scheme that best reflects the flood characteristics of historical floods from the multi-element scheme, so that the computing device determines the historical flood that is most similar to the target flood that is about to occur or has occurred from the historical floods as a flood forecast based on the target scheme. Therefore, the present technical solution, based on the single-element scheme and the multi-element scheme, reflects the historical floods in many aspects, and accurately selects the target scheme that best reflects the historical floods, so that based on the target scheme, the flood forecast of the target flood is accurately determined, solving the technical problem of low accuracy of flood forecasting in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0014] Figure 1 is a hardware structure block diagram of a computing device for implementing the method according to Embodiment 1 of the present application;

[0015] Figure 2 is a flow chart of a flood forecasting method based on historical similar floods according to the first aspect of Example 1 of the present application;

[0016] Figure 3A is a schematic diagram of a process for determining a first flood forecast according to the first aspect of Embodiment 1 of the present application;

[0017] Figure 3B is a schematic diagram of a process for generating a single element qualified rate according to the first aspect of Example 1 of the present application;

[0018] Figure 3C is a schematic diagram of a process for generating a multi-element solution according to the first aspect of Example 1 of the present application;

[0019] Figure 4A is a schematic diagram of a process for determining a second flood forecast according to the first aspect of Embodiment 1 of the present application;

[0020] Figure 4B is a schematic diagram of a process for generating a multi-element qualified rate according to the first aspect of Example 1 of the present application;

[0021] Figure 4C is a schematic diagram of a process for determining a target scheme according to the first aspect of Example 1 of the present application;

[0022] Figure 5 It is a sequential flow chart of the flood forecasting method based on historical similar floods according to the first aspect of Example 1 of the present application;

[0023] Figure 6 is a schematic diagram of a flood forecasting device based on historical similar floods according to Embodiment 2 of the present application; and

[0024] Figure 7 This is a schematic diagram of a flood forecasting device based on historical similar floods according to Example 3 of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the technical solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only embodiments of a part of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. Example 1

[0027] According to this embodiment, a method embodiment of a flood forecasting method based on historical similar floods is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0028] The method embodiment provided in this embodiment can be executed in a mobile terminal, a computer terminal, a server or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computing device for implementing a flood forecasting method based on historical similar floods. Figure 1 As shown, the computing device may include one or more processors (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory for storing data, and a transmission device for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0029] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computing device. As involved in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0030] The memory can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the flood forecasting method based on historical similar floods in the embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, the flood forecasting method based on historical similar floods of the above-mentioned application program is realized. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computing device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0031] The transmission device is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computing device. In one example, the transmission device includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0032] The display may be, for example, a touch screen liquid crystal display (LCD) that may enable a user to interact with a user interface of the computing device.

[0033] It should be noted that, in some optional embodiments, the above Figure 1 The computing device shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware elements and software elements. Figure 1This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the computing devices described above.

[0034] Under the above operating environment, according to the first aspect of this embodiment, a flood forecasting method based on historical similar floods is provided. The method comprises: Figure 1 The computing device implementation shown in . Figure 2 A schematic diagram showing the process of the method is shown in FIG. Figure 2 As shown, the method includes:

[0035] S202: Screening the single-element schemes according to the first flood forecast of the first historical flood corresponding to the preset single-element schemes to generate multi-element schemes, wherein a single-element scheme is composed of one element and a multi-element scheme is composed of multiple elements;

[0036] S204: determining a target scheme from the multi-element scheme according to the second flood forecast of the first historical flood corresponding to the multi-element scheme;

[0037] S206: Based on the target scenario, according to the comprehensive similarity between the target flood and the first historical flood, determine the second historical flood with the highest comprehensive similarity; and

[0038] S208: Mapping the second historical flood event according to the target flood event to generate a third flood forecast.

[0039] Specifically, when a flood has not occurred or is occurring, the computing device will forecast future floods (i.e., target floods) based on historical floods. First, the computing device obtains data information such as the average rainfall during the period of historical floods and the previous influencing rainfall. The division of historical floods is based on the data of the flood excerpt table, and the mathematical statistics method is used to analyze the duration of each flow level in history, determine the flood rise flow, and divide the floods. The computing device distributes the flood flow according to the duration of occurrence, sets the base flow ratio and flood duration, determines the rise flow, and obtains each historical flood. At the same time, there is a certain relationship between the total rainfall and the total amount of water generated by runoff. The ratio between the two is considered to be a reasonable flood within a certain range, and the runoff coefficient of each flood is calculated. The runoff coefficient = total water volume / (previous influencing rainfall + total rainfall). After that, the computing device sets a reasonable runoff coefficient interval, eliminates unreasonable flood data, and obtains multiple historical floods.

[0040] Furthermore, the computing device obtains a preset single-element solution, wherein each single-element solution is composed of one element. Table 1 shows a single-element solution information table.

[0041] Table 1

[0042]

[0043] As shown in Table 1, single element scheme 1 to single element scheme m are all composed of one element. For example, single element scheme 1 is composed of the element "average rainfall during the period", and single element scheme 2 is composed of the element "previous impact rainfall".

[0044] Further, the computing device obtains historical floods (i.e., the first historical flood) and the corresponding flood forecast (i.e., the first flood forecast) under each single element scheme. The first flood forecast is selected from other historical floods, and the first flood forecast under the single element scheme indicates that the first flood forecast is a forecast of the historical flood corresponding to the element of the single element scheme. For example, the element of the single element scheme 1 is "average rainfall during the period", so the first flood forecast under the single element scheme 1 indicates that the first flood forecast is used to forecast the "average rainfall during the period" of the corresponding historical flood.

[0045] The computing device then calculates the similarity between the historical floods based on each single-element scheme and the corresponding first flood forecast, and determines whether each single-element scheme meets the screening requirements based on the similarity. The computing device then combines the elements of the single-element scheme that meet the screening requirements into a multi-element scheme. Table 2 shows the multi-element scheme information table.

[0046] For example, the single element schemes that meet the screening requirements include at least single element schemes 1 to 4, and the element of single element scheme 1 is "average rainfall during the period", the element of single element scheme 2 is "previous impact rainfall", the element of single element scheme 3 is "rainfall location", and the element of single element scheme 4 is "linear similarity". Thus, the computing device combines the elements of single element schemes 1 to 4 and other single element schemes to generate multiple multi-element schemes.

[0047] Table 2

[0048]

[0049] Table 2 shows the elements of multi-element scheme 1 to multi-element scheme k and the weight value of each element. For example, average rainfall during a period (0.3) means that the weight value of the element “average rainfall during a period” is 0.3.

[0050] As shown in Table 2, for example, the elements of multi-element scheme 1 include average rainfall during the period and previous rainfall, and the weight value of the element "average rainfall during the period" is 0.3, and the weight value of the element "previous rainfall" is 0.7; the elements of multi-element scheme 2 include average rainfall during the period and rainfall location, and the weight value of the element "average rainfall during the period" is 0.1, and the weight value of the element "rainfall location" is 0.9. The weight values ​​of the elements of each multi-element scheme can be set according to empirical values.

[0051] Further, the computing device obtains historical floods (i.e., first historical floods) and corresponding flood forecasts (i.e., second flood forecasts) under various multi-element schemes. The second flood forecast is selected from other historical floods, and the second flood forecast under the multi-element scheme indicates that the second flood forecast is a forecast of historical floods corresponding to the elements of the multi-element scheme. For example, the elements of multi-element scheme 1 are "average rainfall during the period" and "previous rainfall", so the second flood forecast under multi-element scheme 1 indicates that the second flood forecast is used to forecast the "average rainfall during the period" and "previous rainfall" of the corresponding historical floods.

[0052] The computing device then calculates the similarity between the historical floods and the corresponding second flood forecasts based on the elements of each multi-element scheme and the corresponding weights, and determines the target scheme from the multiple multi-element schemes based on the similarity.

[0053] Furthermore, the computing device obtains the characteristic values ​​of the corresponding flood characteristics of the target flood and the characteristic values ​​of the corresponding flood characteristics of the first historical flood according to the elements of the target scheme. Then, the computing device calculates the comprehensive similarity between the historical floods of the target flood (i.e., the first historical flood) according to the characteristic values ​​of the flood characteristics corresponding to the elements of the target scheme and the corresponding weights, and determines the historical flood with the highest comprehensive similarity to the target flood (i.e., the second historical flood) from the historical floods.

[0054] For example, the target scheme is multi-element scheme 1, where the elements of multi-element scheme 1 are "average rainfall during the period" and "previous impact rainfall", so that the computing device obtains the average rainfall during the period corresponding to the target flood and the elements of multi-element scheme 1, the previous impact water volume (i.e., the characteristic value of the flood characteristics) and the corresponding weights, and then performs a weighted summation operation based on the average rainfall during the period, the previous impact water volume and the corresponding weights to obtain the first calculation result corresponding to the target flood. And the computing device obtains the average rainfall during the period corresponding to the first historical flood and the elements of multi-element scheme 1, the previous impact water volume (i.e., the characteristic value of the flood characteristics) and the corresponding weights, and then performs a weighted summation operation based on the average rainfall during the period, the previous impact water volume and the corresponding weights to obtain the second calculation result corresponding to the first historical flood.

[0055] Furthermore, the computing device calculates the similarity (i.e., comprehensive similarity) between the first operation result and each second operation result corresponding to the first flood. The computing device then compares the calculated multiple comprehensive similarities to determine the historical flood with the highest comprehensive similarity to the target flood (i.e., the second historical flood).

[0056] Further, the computing device maps the second historical flood event as a flood forecast for the target flood event (ie, a third flood forecast).

[0057] As described in the background technology, accurate and timely flood forecasting is the scientific basis for flood control decision-making. In actual flood control decision-making, in addition to the need to configure advanced water situation monitoring and reporting systems, modern communication and computer means, and compile flood forecasting plans in various ways, it is also necessary to have an in-depth study and understanding of the characteristics of rainstorms and floods in this basin. The time and magnitude of floods in a specific area have the characteristics of periodic changes. Historical floods can reflect the comprehensive influence of local weather and underlying surfaces to a certain extent. Especially in various stages of flood control scheduling, how to effectively use the occurrence, development and evolution information of similar rainstorms and floods in history is particularly important for guiding real-time flood forecasting and reservoir scheduling. However, there is still a problem of insufficient forecast accuracy for existing technologies. Although technology continues to advance, due to the complexity and dynamics of natural phenomena, especially the increase in extreme weather events, the accuracy of flood forecasting still needs to be improved.

[0058] In view of the technical problems described above, through the technical solutions of the embodiments of the present application, first, the computing device screens the single-element solution that best reflects the flood characteristics of historical floods, then generates a multi-element solution based on the single-element solution, and then determines the target solution that best reflects the flood characteristics of historical floods from the multi-element solution, so that the computing device determines the historical floods that are most similar to the target floods that are about to occur or have occurred from the historical floods as a flood forecast based on the target solution. Therefore, the present technical solution, based on the single-element solution and the multi-element solution, reflects the historical floods in many aspects, and accurately selects the target solution that best reflects the historical floods, so as to accurately determine the flood forecast of the target flood based on the target solution, thereby solving the technical problem of low accuracy of flood forecasts in the prior art.

[0059] Optionally, the single-element scheme is screened according to the first flood forecast of the first historical flood corresponding to the preset single-element scheme to generate an operation of a multi-element scheme, including: calculating a first similarity between the first historical floods based on the single-element scheme, and determining the first flood forecast for the first historical flood; calculating a second similarity between the first historical flood and the first flood forecast, and determining a first qualified number of the first historical flood corresponding to the single-element scheme; determining the single-element qualified rate according to the first qualified number and the number of the first historical flood by using a qualified rate calculation formula; and screening the single-element scheme according to the single-element qualified rate to generate a multi-element scheme.

[0060] Specifically, for example, there are n floods in the first historical period, including: H1~H n .

[0061] First, the computing device sequentially designates each historical flood (i.e., the first historical flood) as the designated flood, and then calculates the similarity between the designated flood and the other remaining historical floods (i.e., the first similarity) based on the single element scheme i, and then uses the historical flood with the highest similarity to the designated flood as the flood forecast MY of the designated flood. i,j (ie, the first flood forecast). i,j Represents the first historical flood H based on single element scheme i j The first flood forecast of . Where i=1~m, j=1~n.

[0062] refer to Figure 3A As shown, taking single element scheme 1 as an example, the computing device determines the element of single element scheme 1, that is, the average rainfall in the period. Then the computing device first specifies H1 as the specified flood, and then the computing device obtains H1~H n The eigenvalues ​​corresponding to the elements of the single-element scheme 1 are the average rainfall over the period.

[0063] The computing device then uses the preset time period average rainfall similarity calculation formula to calculate the average rainfall in the time period of H1 and the other historical floods, i.e. H2~H n The average rainfall during the period of H1 and H2~H is calculated respectively. n The average rainfall similarity MS 1,j (ie, the first similarity). Among them, MS 1,j Indicates H1 and H j The first similarity. For example, MS 1,2 Indicates the first similarity between H1 and H2; MS 1,3 Indicates the first similarity between H1 and H3; ...; MS 1,n Indicates H1 and H n The first similarity of the average rainfall in a period is calculated as follows:

[0064]

[0065] Furthermore, the computing device compares the calculated average rainfall similarities of each period, thereby determining the historical flood with the greatest similarity to the average rainfall of H1, and uses the historical flood as the flood forecast MY of H1 under the single element scheme 1. 1,1 (i.e., the First Flood Forecast).

[0066] Furthermore, the computing device designates H2 as the designated flood, and then determines the corresponding flood forecast under single element scheme 1 (i.e., the first flood forecast) for H2 in accordance with the above method of determining the flood forecast for H1. And so on, the computing device sequentially designates the remaining historical floods as designated floods, and determines their flood forecasts under single element scheme 1 (i.e., the first flood forecast).

[0067] Therefore, the computing device calculates the first similarity between the first historical floods based on the single element scheme 1 in accordance with the above scheme, and determines the first flood forecast for each first historical flood.

[0068] Further, the computing device determines the first flood forecast of each first historical flood in accordance with the first similarity between the first historical floods calculated based on the single element scheme 1, and determines the first flood forecast of each first historical flood under other single element schemes. The calculation formula for calculating the first similarity corresponding to each single element scheme is as follows:

[0069]

[0070] Calculation of rainfall location similarity: Calculate the similarity based on the overlap of rainfall locations (upstream, midstream, downstream, and the entire river basin).

[0071] Calculation of flow process similarity and rainfall process similarity:

[0072] Similarity distance is an indicator to measure whether two processes are similar, but the calculated similarity distance does not have relative meaning. Therefore, when calculating the similarity between a flood and another flood, normalization is required. The similarity distance between this flood and all floods is calculated, and the maximum-minimum value is used as the maximum difference in similarity distance. The offset of the similarity distance of each group of floods compared to the maximum difference is calculated.

[0073] The maximum difference in similarity distance = the maximum value - minimum value of the similarity distance between this flood and all floods.

[0074] .

[0075] .

[0076] .

[0077] .

[0078] .

[0079] .

[0080] Furthermore, the computing device sequentially determines the first historical flood H1~H n The peak flow of the first historical flood and the corresponding peak flow of the first flood forecast are taken as the measured peak flow, and the peak flow of the first flood forecast is taken as the predicted peak flow.

[0081] Then, the computing device calculates the peak flow deviation (i.e., the second similarity) between the measured peak flow of the first historical flood and the predicted peak flow of the first flood forecast according to the peak flow deviation calculation formula. The peak flow deviation calculation formula is:

[0082] Peak flow deviation = (forecast peak flow - measured peak flow) / measured peak flow 100%.

[0083] Further, the computing device compares the peak flow deviation with a preset threshold value to determine whether the peak flow deviation is within the preset threshold range, and if the peak flow deviation is within the preset threshold range, the first historical flood corresponding to the peak flow deviation and the corresponding first flood forecast are determined to be qualified. For example, the preset thresholds are -20% and 20%, respectively, so that if the peak flow deviation is greater than or equal to -20% and less than or equal to 20%, the first historical flood corresponding to the peak flow deviation and the corresponding first flood forecast are determined to be qualified.

[0084] Further, refer to Figure 3B As shown, the computing device counts the qualified first historical flood H corresponding to each single element solution i. j And the corresponding first flood forecast MY i,j The qualified number corresponding to the first historical flood and the corresponding first flood forecast is recorded as 1.

[0085] Furthermore, the computing device calculates the single element qualified rate i corresponding to each single element scheme i using a preset qualified rate calculation formula according to the first qualified number and the number of the first historical flood. The qualified rate calculation formula is:

[0086] Single element pass rate = the first pass number / the total number of floods in the first historical period 100%.

[0087] Furthermore, the computing device screens from a plurality of single-element solutions according to the single-element qualification rate to generate a multi-element solution.

[0088] Therefore, this technical solution calculates the similarity values ​​between various historical floods based on the single-element solution, thereby screening out the single-element solution that best reflects the historical floods from the historical floods, and combining the elements of the single-element solution to generate a single-element solution, which can reflect the historical floods in multiple dimensions and aspects, thereby improving the comprehensiveness of the historical floods.

[0089] Optionally, the operation of screening single-element schemes according to the single-element pass rate to generate a multi-element scheme includes: grading the single-element schemes according to the single-element pass rate to determine the level of the single-element schemes; screening the single-element schemes according to the level of the single-element schemes to determine a high-level single-element scheme; and generating a multi-element scheme according to the flood characteristics of the high-level single-element schemes.

[0090] Specifically, refer to Figure 3CAs shown, the computing device compares the single element qualified rate i corresponding to each single element scheme with the preset grade table, so as to grade each single element scheme and determine the grade of each single element scheme. The grade table is determined in accordance with the flood forecast accuracy assessment specification of "SL250-2000 Hydrological Information Forecast Specification", and the grade table has three grades, namely Grade A, Grade B and Grade C. The grade table is shown in Table 3.

[0091] Table 3

[0092]

[0093] Furthermore, the computing device determines the single element solutions that meet the level requirements as high-level single element solutions according to the preset level requirements. For example, the level requirements are level A and level B, so the computing device selects the single element solutions with levels A and level B from the single element solutions, and then selects the single element solutions with levels A and level B as high-level single element solutions.

[0094] Further, the computing device combines the elements of the high-level single-element solution, and regards each group of elements as a multi-element solution. The elements are combined in pairs, groups of ...

[0095] This technical solution screens and processes single-element solutions by setting levels to generate multi-element solutions 1~k, thereby improving the accuracy of reflecting historical floods.

[0096] Optionally, the operation of determining a target scheme from the multi-element scheme based on the second flood forecast of the first historical flood corresponding to the multi-element scheme includes: calculating the third similarity between the first historical flood based on the multi-element scheme, and determining the second flood forecast of the first historical flood; calculating the fourth similarity between the first historical flood and the second flood forecast, and determining the second qualified number of the first historical flood corresponding to the multi-element scheme; determining the multi-element qualified rate based on the second qualified number and the number of the first historical flood by using a qualified rate calculation formula; grading the multi-element scheme based on the multi-element qualified rate to determine the grade of the multi-element scheme; and determining the multi-element scheme that meets the flood forecast requirements as the target scheme based on the grade of the multi-element scheme.

[0097] Specifically, first, the computing device sequentially designates each historical flood (i.e., the first historical flood) as the designated flood, and then calculates the similarity between the designated flood and the other remaining historical floods (i.e., the third similarity) based on the multi-element scheme L, and then uses the historical flood with the highest similarity to the designated flood as the flood forecast KY of the designated flood.L,j (ie, the second flood forecast). L,j Represents the first historical flood H based on the multi-element scheme L j The second flood forecast. Where L=1~k, j=1~n.

[0098] Taking multi-element solution 1 as an example, refer to Figure 4A As shown, the computing device determines the elements of multi-element scheme 1, namely, the average rainfall in the period and the previous influencing rainfall. Then, the computing device first specifies H1 as the designated flood, and then obtains H1~H n The eigenvalues ​​corresponding to the elements of multi-element scheme 1, namely the values ​​of the average rainfall in the period and the previous influencing rainfall.

[0099] The computing device then uses the preset time period average rainfall similarity calculation formula to calculate the average rainfall in the time period of H1 and the other historical floods, i.e. H2~H n The average rainfall during the period of H1 and H2~H is calculated respectively. n The calculation formula for the average rainfall similarity of a period is:

[0100]

[0101] The computing device then uses the preset previous rainfall similarity calculation formula to calculate the previous rainfall of H1 and the other historical floods, i.e. H2~H n The previous rainfall amount is calculated by H1 and H2~H n The calculation formula of the similarity of the previous rainfall impact is:

[0102]

[0103] Further, the computing device determines H1~H according to the similarity of each element of the multi-element scheme 1 and the weight value of each element. n The third similarity KS 1,j . KS 1,j Indicates H1 and H j The third similarity. For example, KS 1,2 Indicates the third similarity between H1 and H2; KS 1,3 Indicates the third similarity between H1 and H3; ...; KS 1,n Indicates H1 and H n The third similarity.

[0104] The weight value of the element "average rainfall during the period" of multi-element scheme 1 is 0.3, and the weight value of the element "previous impact rainfall" is 0.7. Therefore, the calculation formula for the third similarity of multi-element scheme 1 is:

[0105] The third similarity of multi-element scheme 1 = the average rainfall similarity of the period 0.3+Previous impact rainfall similarity 0.7.

[0106] Further, the computing device compares the calculated third similarities corresponding to H1 based on multi-element scheme 1, thereby determining the historical flood with the greatest third similarity to H1 corresponding to multi-element scheme 1, and uses the historical flood as the flood forecast KY of H1 under multi-element scheme 1. 1,1 (i.e., the Second Flood Forecast).

[0107] Furthermore, the computing device designates H2 as the designated flood, and then determines the corresponding flood forecast under multi-element scheme 1 (i.e., the second flood forecast) for H2 in accordance with the above method of determining the flood forecast for H1. And so on, the computing device sequentially designates the remaining historical floods as designated floods, and determines their flood forecasts under multi-element scheme 1 (i.e., the second flood forecast).

[0108] Therefore, the computing device calculates the third similarity between the first historical floods based on the multi-element scheme 1 in accordance with the above scheme, and determines the second flood forecast for each first historical flood.

[0109] Furthermore, the computing device calculates the third similarity between the first historical floods based on multi-element scheme 1, determines the second flood forecast for each first historical flood, and determines the second flood forecast for each first historical flood under other multi-element schemes.

[0110] Furthermore, the computing device determines in sequence the peak flow of the first historical flood and the corresponding peak flow of the second flood forecast, and uses the peak flow of the first historical flood as the measured peak flow, and the peak flow of the second flood forecast as the predicted peak flow.

[0111] Then, the computing device calculates the peak flow deviation (i.e., the fourth similarity) between the measured peak flow of the first historical flood and the predicted peak flow of the corresponding second flood forecast according to the peak flow deviation calculation formula. The peak flow deviation calculation formula is:

[0112]

[0113] Further, the computing device compares the peak flow deviation with a preset threshold value to determine whether the peak flow deviation is within the preset threshold range, and when the peak flow deviation is within the preset threshold range, the first historical flood corresponding to the peak flow deviation and the corresponding second flood forecast are determined to be qualified. For example, the preset thresholds are -20% and 20%, respectively, so that when the peak flow deviation is greater than or equal to -20% and less than or equal to 20%, the first historical flood corresponding to the peak flow deviation and the corresponding second flood forecast are determined to be qualified.

[0114] Further, refer to Figure 4B As shown, the computing device counts the qualified first historical flood H corresponding to each multi-element solution L j And the corresponding second flood forecast KY L,j The qualified number of the first historical flood and the corresponding second flood forecast is recorded as 1.

[0115] Furthermore, the computing device calculates the multi-element qualified rate L corresponding to each multi-element scheme L according to the second qualified number and the number of the first historical flood using a preset qualified rate calculation formula. The qualified rate calculation formula is:

[0116]

[0117] Furthermore, the computing device compares the multi-element qualification rate L corresponding to each multi-element scheme with a preset grade table (ie, Table 3), thereby grading each multi-element scheme and determining the grade of each multi-element scheme.

[0118] Further, refer to Figure 4C As shown, the computing device determines the target solution from the multi-element solutions that meet the level requirements according to the pre-set level requirements. For example, the level requirements are Class A and Class B, so the computing device determines the target solution from the multi-element solutions of Class A and Class B according to the statistical needs at that time. For example, the flood forecast requirement is to focus on the average rainfall in the period and the previous impact rainfall, and the multi-element solution 1 whose elements are the average rainfall in the period and the previous impact rainfall is Class B, so the multi-element solution 1 that meets the level requirements is used as the target solution.

[0119] Therefore, in the present technical solution, the computing device calculates the similarity between each historical flood based on a multi-element solution, and then uses a simple method of calculating similarity to screen out the target solution that best reflects the historical floods from the historical floods, thereby improving the computing efficiency and further increasing the screening speed for the target solution.

[0120] Optionally, the method also includes: when the target flood has not yet occurred, constructing a single element scheme according to preset flood characteristics, wherein the flood characteristics include total rainfall, rainfall location, previous impact rainfall, maximum rainfall in 1 hour, maximum rainfall in 6 hours, maximum rainfall in 12 hours, hourly average of maximum rainfall in 6 hours, hourly average of maximum rainfall in 12 hours, average rainfall in time period and linear similarity.

[0121] Specifically, when the target flood has not occurred, the computing device determines the flood characteristics of the flood. The flood characteristics include at least: total rainfall, rainfall location, previous rainfall, maximum rainfall in 1 hour, maximum rainfall in 6 hours, maximum rainfall in 12 hours, hourly average of maximum rainfall in 6 hours, hourly average of maximum rainfall in 12 hours, average rainfall in the time period, and linear similarity. The linear similarity is to use the time series similarity metric (DTW) algorithm to determine the linear similarity distance of two flood process lines. The smaller the similarity distance, the closer the linear shape.

[0122] For the linear similarity index, the time series similarity measure (DTW) algorithm is used to determine the linear similarity distance of the two flood process lines. The smaller the similarity distance, the closer the linear shape.

[0123] Dynamic Time Warping (DTW) is essentially similar to calculating the distance of a sequence through dynamic programming. It does not require the samples to have the same length and range, as long as the starting boundary of the samples is given and they are guaranteed to be continuous and unidirectional (which can be understood as progressing over time).

[0124] Core algorithm: Based on dynamic programming, the distance matrix dp[v][u] of sequence a (i.e., the time series of flood a) and sequence b (i.e., the time series of flood b) is constructed, where dp[v][u] represents the square of the similarity distance between sequences a[0:v] and b[0:u]. v is any point in sequence a, and u is any point in sequence b. dp[len(a)-1][len(b)-1] is the square of the similarity distance, and the square root is the similarity distance of the two time series. The smaller the corresponding value, the higher the similarity. The calculation formula is as follows:

[0125]

[0126] Furthermore, the computing device constructs a single-element solution according to the flood feature. For example, the computing device may construct a single-element solution by taking one flood feature as an element, or may process multiple flood features as one element as a single-element solution.

[0127] Therefore, this technical solution selects appropriate flood characteristics to construct a single-element solution for target floods that have not yet occurred, thereby improving the adaptability of the constructed single-element solution to historical floods.

[0128] Optionally, the method also includes: when the target flood has occurred, constructing a single element scheme according to preset flood characteristics, wherein the flood characteristics include total rainfall, rainfall location, previous influencing rainfall, peak flow, flood duration, cumulative rainfall in 15 days before the rise, pre-peak rain, post-peak rain, time from the rise to the peak of the flood, maximum rainfall in 1 hour, maximum rainfall in 6 hours, maximum rainfall in 12 hours, hourly average of maximum rainfall in 6 hours, hourly average of maximum rainfall in 12 hours, average rainfall in time period and linear similarity.

[0129] Specifically, when the target flood has occurred, the computing device determines the flood characteristics of the flood. The flood characteristics include at least: total rainfall, rainfall location, previous impact rainfall, flood peak flow, flood duration, cumulative rainfall 15 days before the rise, pre-peak rain, post-peak rain, duration from the rise to the peak, maximum rainfall in 1 hour, maximum rainfall in 6 hours, maximum rainfall in 12 hours, 6h maximum rainfall hourly average, 12h maximum rainfall hourly average, time period average rainfall, and linear similarity. The linear similarity is to use the time series similarity metric (DTW) algorithm to determine the linear similarity distance of two flood process lines. The smaller the similarity distance, the closer the linear shape.

[0130] Then the computing device constructs a single element solution according to the flood characteristics. For example, the computing device can construct a single element solution by taking one flood characteristic as an element, or can process multiple flood characteristics as one element as a single element solution.

[0131] Therefore, this technical solution selects appropriate flood characteristics to construct a single-element solution for target floods that have already occurred, thereby improving the adaptability of the constructed single-element solution to historical floods.

[0132] Optionally, the operation of mapping the second historical flood according to the target flood to generate a third flood forecast includes: comparing the sum of the previous impact rainfall of the target flood and the maximum rainfall in 6 hours, and the sum of the previous impact rainfall of the second historical flood and the maximum rainfall in 6 hours to generate a mapping value; and mapping the second historical flood according to the mapping value to generate a third flood forecast corresponding to the target flood.

[0133] Specifically, the computing device obtains the previous impact rainfall and the maximum rainfall in 6 hours of the target flood, and calculates the sum of the previous impact rainfall and the maximum rainfall in 6 hours to generate the first data. The computing device then obtains the previous impact rainfall and the sum of the maximum rainfall in 6 hours of the second historical flood to generate the second data. The computing device then calculates the ratio between the first data and the second data (i.e., the mapping value). The computing device then amplifies or reduces the flow process of the second historical flood in equal proportions according to the ratio (i.e., the mapping value) as the subsequent flow of the target flood. The computing device then determines the peak flow of the target flood that needs to be forecasted (i.e., the third forecast) based on the subsequent flow of the target flood.

[0134] Therefore, the technical solution performs mapping processing on the second historical flood, adjusts the flow process of the historical flood according to the calculated ratio, and improves the accuracy of flood forecasting.

[0135] In addition, (1) River basin selection: select river basins with continuous and complete data, which are relatively closed, less affected by upstream water conservancy projects and human activities, and with relatively small changes in hydrological conditions: for example, river sections, water levels and hydrological characteristics change less.

[0136] (2) Data processing: Initialize the data of the basin outlet section and upstream hydrological stations, including flood excerpt data and rainfall excerpt data. Perform equal time period (1h) processing through interpolation to facilitate subsequent use. When processing flood excerpt data, for non-integer peaks, perform peak shifting to ensure that the peak is not lost.

[0137] In summary, reference Figure 5 As shown in Figure 1, the sequential steps for generating a flood forecast for a target flood are as follows:

[0138] S501: The computing device calculates the first similarity between each first historical flood based on each single element scheme, and determines a first flood forecast for each first historical flood based on each single element scheme;

[0139] S502: The computing device calculates the peak flow deviation between the first historical flood and the corresponding first flood forecast based on each single element scheme, and determines whether the corresponding first historical flood and its first flood forecast are qualified according to the peak flow deviation;

[0140] S503: The computing device counts the qualified number (first qualified number), and determines the single element solution qualified rate of each single element solution according to the qualified number;

[0141] S504: The computing device determines a high-level single-element solution according to the single-element solution qualification rate of each single-element solution, and combines the high-level single-element solutions to generate a plurality of multi-element solutions;

[0142] S505: The computing device calculates the third similarity between each first historical flood based on each multi-element scheme, and determines a second flood forecast for each first historical flood based on each multi-element scheme;

[0143] S506: The computing device calculates the peak flow deviation between the first historical flood and the corresponding second flood forecast based on each multi-element scheme, and determines whether the corresponding first historical flood and its second flood forecast are qualified according to the peak flow deviation;

[0144] S507: The computing device counts the qualified number (second qualified number), and determines the multi-element solution qualified rate of each multi-element solution according to the qualified number;

[0145] S508: The computing device determines the level of each multi-element solution according to the multi-element solution qualification rate of each multi-element solution, and determines the target solution according to the level of each multi-element solution;

[0146] S509: The computing device calculates the comprehensive similarity between the target flood and each first historical flood based on the target solution, and determines the second historical flood with the highest comprehensive similarity;

[0147] S510: The computing device maps the second historical flood according to the target flood to generate a flood forecast of the target flood (ie, a third flood forecast).

[0148] In addition, according to the second aspect of the embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0149] Therefore, according to this embodiment, first, the computing device selects the single-element scheme that best reflects the flood characteristics of historical floods, then generates a multi-element scheme based on the single-element scheme, and then determines the target scheme that best reflects the flood characteristics of historical floods from the multi-element scheme, so that the computing device determines the historical floods that are most similar to the target floods that are about to occur or have occurred from the historical floods as flood forecasts based on the target scheme. Therefore, this technical solution, based on the single-element scheme and the multi-element scheme, reflects the historical floods in many aspects, and accurately selects the target scheme that best reflects the historical floods, so that based on the target scheme, the flood forecast of the target flood is accurately determined, solving the technical problem of low accuracy of flood forecasts in the prior art.

[0150] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0151] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention. Example 2

[0152] Figure 6 The flood forecasting device 600 based on historical similar floods according to this embodiment is shown, and the device 600 corresponds to the method according to the first aspect of embodiment 1. Figure 6 As shown, the device 600 includes: a scheme screening module 610, which is used to screen single-element schemes according to a first flood forecast of a first historical flood corresponding to a preset single-element scheme, and generate a multi-element scheme, wherein a single-element scheme is composed of one element, and a multiple-element scheme is composed of multiple elements; a scheme determination module 620, which is used to determine a target scheme from the multi-element schemes according to a second flood forecast of the first historical flood corresponding to the multi-element scheme; a flood determination module 630, which is used to determine a second historical flood with the highest comprehensive similarity based on the target scheme and according to the comprehensive similarity between the target flood and the first historical flood; and a forecast generation module 640, which is used to map the second historical flood according to the target flood to generate a third flood forecast.

[0153] Optionally, the scheme screening module 610 includes: a first determination submodule, used to calculate the first similarity between the first historical floods based on the single-element scheme, and determine the first flood forecast of the first historical flood; a second determination submodule, used to calculate the second similarity between the first historical flood and the first flood forecast, and determine the first qualified number of the first historical floods corresponding to the single-element scheme; a third determination submodule, used to determine the single-element qualified rate according to the first qualified number and the number of the first historical floods by using the qualified rate calculation formula; and a first generation submodule, used to screen the single-element schemes according to the single-element qualified rate to generate a multi-element scheme.

[0154] Optionally, the first generating submodule includes: a first determining unit, used to grade the single-element schemes according to the single-element qualification rate to determine the level of the single-element schemes; a second determining unit, used to screen the single-element schemes according to the level of the single-element schemes to determine the high-level single-element schemes; and the first generating unit is used to generate a multi-element scheme according to the flood characteristics of the high-level single-element schemes.

[0155] Optionally, the scheme determination module 620 includes: a fourth determination submodule, which is used to calculate the third similarity between the first historical flood based on the multi-element scheme, and determine the second flood forecast of the first historical flood; a fifth determination submodule, which is used to calculate the fourth similarity between the first historical flood and the second flood forecast, and determine the second qualified number of the first historical flood corresponding to the multi-element scheme; a sixth determination submodule, which is used to determine the multi-element qualified rate according to the second qualified number and the number of the first historical flood by using the qualified rate calculation formula; a seventh determination submodule, which is used to grade the multi-element scheme according to the multi-element qualified rate and determine the level of the multi-element scheme; and a ninth determination submodule, which is used to determine the multi-element scheme that meets the flood forecast requirements as the target scheme according to the level of the multi-element scheme.

[0156] Optionally, the method also includes: a first construction module, used to construct a single-element scheme according to preset flood characteristics when the target flood has not yet occurred, wherein the flood characteristics include total rainfall, rainfall location, previous impact rainfall, maximum rainfall in 1 hour, maximum rainfall in 6 hours, maximum rainfall in 12 hours, 6h maximum rainfall hourly average, 12h maximum rainfall hourly average, time period average rainfall and linear similarity.

[0157] Optionally, the method also includes: a second construction module, which, when the target flood has occurred, constructs a single-element scheme according to preset flood characteristics, wherein the flood characteristics include total rainfall, rainfall location, previous influencing rainfall, peak flow, flood duration, cumulative rainfall in 15 days before the rise, pre-peak rain, post-peak rain, time from the rise to the peak of the flood, maximum rainfall in 1 hour, maximum rainfall in 6 hours, maximum rainfall in 12 hours, 6h maximum rainfall hourly average, 12h maximum rainfall hourly average, time period average rainfall and linear similarity.

[0158] Optionally, the forecast generation module 640 includes: a second generation submodule, used to compare the sum of the previous impact rainfall of the target flood and the maximum rainfall in 6 hours, and the sum of the previous impact rainfall of the second historical flood and the maximum rainfall in 6 hours, to generate a mapping value; and a third generation submodule, used to map the second historical flood according to the mapping value, and generate a third flood forecast corresponding to the target flood.

[0159] Therefore, according to this embodiment, first, the computing device selects the single-element scheme that best reflects the flood characteristics of historical floods, then generates a multi-element scheme based on the single-element scheme, and then determines the target scheme that best reflects the flood characteristics of historical floods from the multi-element scheme, so that the computing device determines the historical floods that are most similar to the target floods that are about to occur or have occurred from the historical floods as flood forecasts based on the target scheme. Therefore, this technical solution, based on the single-element scheme and the multi-element scheme, reflects the historical floods in many aspects, and accurately selects the target scheme that best reflects the historical floods, so that based on the target scheme, the flood forecast of the target flood is accurately determined, solving the technical problem of low accuracy of flood forecasts in the prior art. Example 3

[0160] Figure 7 The flood forecasting device 700 based on historical similar floods according to the first aspect of this embodiment is shown, and the device 700 corresponds to the method according to the first aspect of embodiment 1. Figure 7As shown, the device 700 includes: a processor 710; and a memory 720, which is connected to the processor 710 and is used to provide the processor 710 with instructions for processing the following processing steps: according to a first flood forecast of a first historical flood corresponding to a preset single-element scheme, the single-element scheme is screened to generate a multi-element scheme, wherein a single-element scheme is composed of one element and a multiple-element scheme is composed of multiple elements; according to a second flood forecast of the first historical flood corresponding to the multi-element scheme, a target scheme is determined from the multi-element scheme; based on the target scheme, according to the comprehensive similarity between the target flood and the first historical flood, a second historical flood with the highest comprehensive similarity is determined; and according to the target flood, the second historical flood is mapped to generate a third flood forecast.

[0161] Optionally, the single-element scheme is screened according to the first flood forecast of the first historical flood corresponding to the preset single-element scheme to generate an operation of a multi-element scheme, including: calculating a first similarity between the first historical floods based on the single-element scheme, and determining the first flood forecast for the first historical flood; calculating a second similarity between the first historical flood and the first flood forecast, and determining a first qualified number of the first historical flood corresponding to the single-element scheme; determining the single-element qualified rate according to the first qualified number and the number of the first historical flood by using a qualified rate calculation formula; and screening the single-element scheme according to the single-element qualified rate to generate a multi-element scheme.

[0162] Optionally, the operation of screening single-element schemes according to the single-element pass rate to generate a multi-element scheme includes: grading the single-element schemes according to the single-element pass rate to determine the level of the single-element schemes; screening the single-element schemes according to the level of the single-element schemes to determine a high-level single-element scheme; and generating a multi-element scheme according to the flood characteristics of the high-level single-element schemes.

[0163] Optionally, the operation of determining a target scheme from the multi-element scheme based on the second flood forecast of the first historical flood corresponding to the multi-element scheme includes: calculating the third similarity between the first historical flood based on the multi-element scheme, and determining the second flood forecast of the first historical flood; calculating the fourth similarity between the first historical flood and the second flood forecast, and determining the second qualified number of the first historical flood corresponding to the multi-element scheme; determining the multi-element qualified rate based on the second qualified number and the number of the first historical flood by using a qualified rate calculation formula; grading the multi-element scheme based on the multi-element qualified rate to determine the grade of the multi-element scheme; and determining the multi-element scheme that meets the flood forecast requirements as the target scheme based on the grade of the multi-element scheme.

[0164] Optionally, the memory 720 is also used to provide the processor 710 with instructions for processing the following processing steps: when the target flood has not yet occurred, construct a single element scheme according to preset flood characteristics, wherein the flood characteristics include total rainfall, rainfall location, previous impact rainfall, maximum rainfall in 1 hour, maximum rainfall in 6 hours, maximum rainfall in 12 hours, hourly average of maximum rainfall in 6 hours, hourly average of maximum rainfall in 12 hours, average rainfall in time period, and linear similarity.

[0165] Optionally, the memory 720 is also used to provide the processor 710 with instructions for processing the following processing steps: when the target flood has occurred, a single-element scheme is constructed according to preset flood characteristics, wherein the flood characteristics include total rainfall, rainfall location, previous influencing rainfall, peak flow, flood duration, cumulative rainfall in the 15 days before the rise, pre-peak rain, post-peak rain, time from the rise to the peak of the flood, maximum rainfall in 1 hour, maximum rainfall in 6 hours, maximum rainfall in 12 hours, hourly average of maximum rainfall in 6 hours, hourly average of maximum rainfall in 12 hours, average rainfall in time period, and linear similarity.

[0166] Optionally, the operation of mapping the second historical flood according to the target flood to generate a third flood forecast includes: comparing the sum of the previous impact rainfall of the target flood and the maximum rainfall in 6 hours, and the sum of the previous impact rainfall of the second historical flood and the maximum rainfall in 6 hours to generate a mapping value; and mapping the second historical flood according to the mapping value to generate a third flood forecast corresponding to the target flood.

[0167] Therefore, according to this embodiment, first, the computing device selects the single-element scheme that best reflects the flood characteristics of historical floods, then generates a multi-element scheme based on the single-element scheme, and then determines the target scheme that best reflects the flood characteristics of historical floods from the multi-element scheme, so that the computing device determines the historical floods that are most similar to the target floods that are about to occur or have occurred from the historical floods as flood forecasts based on the target scheme. Therefore, this technical solution, based on the single-element scheme and the multi-element scheme, reflects the historical floods in many aspects, and accurately selects the target scheme that best reflects the historical floods, so that based on the target scheme, the flood forecast of the target flood is accurately determined, solving the technical problem of low accuracy of flood forecasts in the prior art.

[0168] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0169] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0170] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0171] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0172] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0173] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.

[0174] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A flood forecasting method based on historical similar floods, It is characterized in that include: According to a first flood forecast of a first historical flood corresponding to a preset single-element scheme, the single-element scheme is screened to generate a multi-element scheme, wherein a single-element scheme is composed of one element and a multi-element scheme is composed of multiple elements; Determining a target solution from the multi-element solution according to a second flood forecast of the first historical flood corresponding to the multi-element solution; Based on the target scenario, determining a second historical flood with the highest comprehensive similarity according to the comprehensive similarity between the target flood and the first historical flood; and The second historical flood is mapped according to the target flood to generate a third flood forecast, wherein The operation of screening the single-element scheme according to the first flood forecast of the first historical flood corresponding to the preset single-element scheme to generate the multi-element scheme includes: calculating the first similarity between the first historical floods based on the single-element scheme to determine the first flood forecast of the first historical flood; calculating the second similarity between the first historical flood and the first flood forecast to determine the first qualified number of the first historical flood corresponding to the single-element scheme; determining the single-element qualified rate according to the first qualified number and the number of the first historical flood by using the qualified rate calculation formula; and screening the single-element scheme according to the single-element qualified rate to generate the multi-element scheme, wherein The operation of determining a target scheme from the multi-element scheme according to the second flood forecast of the first historical flood corresponding to the multi-element scheme includes: calculating the third similarity between the first historical floods based on the multi-element scheme to determine the second flood forecast of the first historical flood; calculating the fourth similarity between the first historical flood and the second flood forecast to determine the second qualified number of the first historical flood corresponding to the multi-element scheme; determining the multi-element qualified rate according to the second qualified number and the number of the first historical flood by using a qualified rate calculation formula; grading the multi-element scheme according to the multi-element qualified rate to determine the grade of the multi-element scheme; and determining the multi-element scheme that meets the flood forecast requirements as the target scheme according to the grade of the multi-element scheme, and The method also includes: constructing the single element scheme according to preset flood characteristics when the target flood has not occurred, wherein the flood characteristics include total rainfall, rainfall location, previous impact rainfall, maximum rainfall in 1 hour, maximum rainfall in 6 hours, maximum rainfall in 12 hours, hourly average of maximum rainfall in 6 hours, hourly average of maximum rainfall in 12 hours, average rainfall in time period and linear similarity, and The method also includes: when the target flood has occurred, constructing the single element scheme according to preset flood characteristics, wherein the flood characteristics include total rainfall, rainfall location, previous impact rainfall, flood peak flow, flood duration, cumulative rainfall 15 days before the flood, pre-peak rain, post-peak rain, duration from the flood to the flood peak, maximum rainfall in 1 hour, maximum rainfall in 6 hours, maximum rainfall in 12 hours, hourly average of maximum rainfall in 6 hours, hourly average of maximum rainfall in 12 hours, average rainfall in time period and linear similarity, wherein The operation of mapping the second historical flood according to the target flood to generate a third flood forecast includes: comparing the sum of the preceding impact rainfall of the target flood and the maximum rainfall in 6 hours, and the sum of the preceding impact rainfall of the second historical flood and the maximum rainfall in 6 hours to generate a mapping value; and mapping the second historical flood according to the mapping value to generate a third flood forecast corresponding to the target flood.

2. The method according to claim 1, It is characterized in that The operation of screening the single-element scheme according to the single-element qualified rate to generate the multi-element scheme includes: According to the single element qualified rate, the single element scheme is graded to determine the grade of the single element scheme; Screening the single-element solutions according to their levels to determine a high-level single-element solution; and The multi-element scheme is generated according to flood characteristics of the high-level single-element scheme.

3. A flood forecasting device based on historical similar floods, It is characterized in that include: A scheme screening module, for screening the single-element schemes according to the first flood forecast of the first historical flood corresponding to the preset single-element schemes, and generating multi-element schemes, wherein a single-element scheme is composed of one element, and a multi-element scheme is composed of multiple elements; A scheme determination module, configured to determine a target scheme from the multi-element scheme according to a second flood forecast of the first historical flood corresponding to the multi-element scheme; a flood determination module, configured to determine, based on the target scenario and according to the comprehensive similarity between the target flood and the first historical flood, a second historical flood with the highest comprehensive similarity; and A forecast generation module is used to map the second historical flood according to the target flood to generate a third flood forecast, wherein The scheme screening module includes: a first determination submodule, used to calculate the first similarity between the first historical floods based on the single-element scheme, and determine the first flood forecast of the first historical flood; a second determination submodule, used to calculate the second similarity between the first historical flood and the first flood forecast, and determine the first qualified number of the first historical floods corresponding to the single-element scheme; a third determination submodule, used to determine the single-element qualified rate according to the first qualified number and the number of the first historical floods by using a qualified rate calculation formula; and a first generation submodule, used to screen the single-element scheme according to the single-element qualified rate, and generate the multi-element scheme, wherein The scheme determination module includes: a fourth determination submodule, which is used to calculate the third similarity between the first historical floods based on the multi-element scheme, and determine the second flood forecast of the first historical flood; a fifth determination submodule, which is used to calculate the fourth similarity between the first historical flood and the second flood forecast, and determine the second qualified number of the first historical flood corresponding to the multi-element scheme; a sixth determination submodule, which is used to determine the multi-element qualified rate according to the second qualified number and the number of the first historical flood by using the qualified rate calculation formula; a seventh determination submodule, which is used to grade the multi-element scheme according to the multi-element qualified rate and determine the level of the multi-element scheme; and a ninth determination submodule, which is used to determine the multi-element scheme that meets the flood forecast requirements as the target scheme according to the level of the multi-element scheme, and The device also includes: a first construction module, which is used to construct the single element scheme according to preset flood characteristics when the target flood has not occurred, wherein the flood characteristics include total rainfall, rainfall location, previous impact rainfall, maximum rainfall in 1 hour, maximum rainfall in 6 hours, maximum rainfall in 12 hours, hourly average of maximum rainfall in 6 hours, hourly average of maximum rainfall in 12 hours, average rainfall in time period and linear similarity, and The device also includes: a second construction module, which is used to construct the single element scheme according to the preset flood characteristics when the target flood has occurred, wherein the flood characteristics include total rainfall, rainfall location, previous impact rainfall, flood peak flow, flood duration, cumulative rainfall 15 days before the flood, pre-peak rain, post-peak rain, duration from the flood to the flood peak, maximum rainfall in 1 hour, maximum rainfall in 6 hours, maximum rainfall in 12 hours, hourly average of maximum rainfall in 6 hours, hourly average of maximum rainfall in 12 hours, average rainfall in time period and linear similarity, wherein The forecast generation module includes: a second generation submodule, used to compare the sum of the previous impact rainfall of the target flood and the maximum rainfall in 6 hours, and the sum of the previous impact rainfall of the second historical flood and the maximum rainfall in 6 hours, to generate a mapping value; and a third generation submodule, used to map the second historical flood according to the mapping value to generate a third flood forecast corresponding to the target flood.

4. A flood forecasting device based on historical similar floods, It is characterized in that include: processor; as well as A memory, connected to the processor, configured to provide the processor with instructions for processing the following processing steps: According to a first flood forecast of a first historical flood corresponding to a preset single-element scheme, the single-element scheme is screened to generate a multi-element scheme, wherein a single-element scheme is composed of one element and a multi-element scheme is composed of multiple elements; Determining a target solution from the multi-element solution according to a second flood forecast of the first historical flood corresponding to the multi-element solution; Based on the target scenario, determining a second historical flood with the highest comprehensive similarity according to the comprehensive similarity between the target flood and the first historical flood; and The second historical flood is mapped according to the target flood to generate a third flood forecast, wherein The operation of screening the single-element scheme according to the first flood forecast of the first historical flood corresponding to the preset single-element scheme to generate the multi-element scheme includes: calculating the first similarity between the first historical floods based on the single-element scheme to determine the first flood forecast of the first historical flood; calculating the second similarity between the first historical flood and the first flood forecast to determine the first qualified number of the first historical flood corresponding to the single-element scheme; determining the single-element qualified rate according to the first qualified number and the number of the first historical flood by using the qualified rate calculation formula; and screening the single-element scheme according to the single-element qualified rate to generate the multi-element scheme, wherein The operation of determining a target scheme from the multi-element scheme according to the second flood forecast of the first historical flood corresponding to the multi-element scheme includes: calculating the third similarity between the first historical floods based on the multi-element scheme to determine the second flood forecast of the first historical flood; calculating the fourth similarity between the first historical flood and the second flood forecast to determine the second qualified number of the first historical flood corresponding to the multi-element scheme; determining the multi-element qualified rate according to the second qualified number and the number of the first historical flood by using a qualified rate calculation formula; grading the multi-element scheme according to the multi-element qualified rate to determine the grade of the multi-element scheme; and determining the multi-element scheme that meets the flood forecast requirements as the target scheme according to the grade of the multi-element scheme, and The device also includes: when the target flood has not occurred, constructing the single element scheme according to preset flood characteristics, wherein the flood characteristics include total rainfall, rainfall location, previous impact rainfall, maximum rainfall in 1 hour, maximum rainfall in 6 hours, maximum rainfall in 12 hours, hourly average of maximum rainfall in 6 hours, hourly average of maximum rainfall in 12 hours, average rainfall in time period and linear similarity, and The device also includes: when the target flood has occurred, constructing the single element scheme according to the preset flood characteristics, wherein the flood characteristics include total rainfall, rainfall location, previous impact rainfall, flood peak flow, flood duration, cumulative rainfall 15 days before the flood, pre-peak rain, post-peak rain, duration from the flood to the flood peak, maximum rainfall in 1 hour, maximum rainfall in 6 hours, maximum rainfall in 12 hours, hourly average of maximum rainfall in 6 hours, hourly average of maximum rainfall in 12 hours, average rainfall in time period and linear similarity, wherein The operation of mapping the second historical flood according to the target flood to generate a third flood forecast includes: comparing the sum of the preceding impact rainfall of the target flood and the maximum rainfall in 6 hours, and the sum of the preceding impact rainfall of the second historical flood and the maximum rainfall in 6 hours to generate a mapping value; and mapping the second historical flood according to the mapping value to generate a third flood forecast corresponding to the target flood.

5. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to claim 1 are implemented.