System and method for rapidly forecasting and correcting flood

Abstract

The invention relates to the technical field of information technology specially suitable for management or supervision, in particular to a flood rapid forecasting and correction system and method, and the system comprises a processor, and also comprises a terminal data processing module, an auxiliary processing module and a filtering output module, the end data processing module is in data connection with the auxiliary processing module, the filtering output module is in data connection with the end data processing module and is in data connection with the auxiliary processing module, and the processor is in data connection with the end data processing module, the auxiliary processing module and the filtering output module. According to the system, through the clustering model, the integration model, the filtering model and the matching degree model, rapid correction of observation data before flood comes is realized, relatively accurate observation data is obtained, and subsequent analysis and use are facilitated; meanwhile, based on the corrected observation data, the flood outbreak condition can be effectively and rapidly forecasted.

Description

Technical Field

[0001] The present application relates to the technical field of information technology specifically suitable for management or supervision purposes, and in particular to a system for rapid flood forecasting and correction, and also to a method. Background Art

[0002] At present, conceptual models are widely used in flood forecasting. The characteristics of this model are concentrated input and lumped parameters, which is inconsistent with the basin object with dispersed input and distributed parameters. That is, after the hydrological elements are averaged in space, they cause the variation of hydrological laws, and the simulated hydrological state cannot find the real correspondence in the basin, which leads to simulation errors. In addition, the observation error of the model input data also causes the model parameter identification to deviate from the true value. The existence of these factors leads to estimation errors in flood forecast results.

[0003] Therefore, it is of great significance to overcome the forecast error caused by input error, adopt relatively effective parameter identification technology and superimpose it into the forecast result. Summary of the invention

[0004] Through research, the inventors found that in the field of flood prevention, it is often necessary to carry out flood forecasting and dispatching of reservoirs and rivers, and select different forecasting models according to different conditions. Commonly used flood forecasting models include rainfall-runoff correlation diagram method, corresponding water level method, empirical unit line model, Xin'anjiang model, water tank model, etc. However, these models are all limited in the scope of application scenarios, and can only be based on the observation errors of input data.

[0005] The purpose of this application is to provide a system and method for rapid flood forecasting and correction. Through clustering models, integration models, filtering models and matching models, the technical problem that the prior art cannot provide a system and method for reasonable and rapid correction of observed data before a flood occurs is solved; at the same time, it also provides an auxiliary rapid correction and forecasting method.

[0006] According to one aspect of the present application, a system for rapid flood forecasting and correction is provided, including a processor, characterized in that it also includes: an end data processing module, an auxiliary processing module and a filtering output module, the end data processing module is data-connected to the auxiliary processing module, the filtering output module is data-connected to the end data processing module and to the auxiliary processing module, and the processor is data-connected to the end data processing module, the auxiliary processing module and the filtering output module, respectively.

[0007] In some embodiments, the end data processing module is configured with a clustering model, which classifies and processes the observation data and divides the observation data into accurate observation data, fuzzy observation errors and erroneous observation data according to preset clustering rules.

[0008] In some embodiments, the auxiliary processing module is configured with an integration model, which includes at least a primary data integration layer and a secondary data integration layer. The primary data integration layer performs data interference filtering on accurate observation data, and the secondary data integration layer performs data interference filtering on fuzzy observation errors and erroneous observation data.

[0009] In some embodiments, the data between the integration model and the clustering model is connected by an intermediate database for storing redundant data.

[0010] In some embodiments, the filtering output module is configured with a filtering model and a matching model. After the filtering model filters the observed data, the data is input into the matching model to perform matching processing.

[0011] In some embodiments, the filtering model is:

[0012]

[0013] Among them, ξ is the filter output difference; is the observed value; is the standard value.

[0014] In some embodiments, the matching model is:

[0015]

[0016] Among them, ε is the matching rate; ξ 标 The filter output value is a standard or preset value.

[0017] In some embodiments, the clustering model has a K-means clustering algorithm written into it.

[0018] In some embodiments, data fuzzy logic algorithms are written in the primary data integration layer and the secondary data integration layer.

[0019] According to another aspect of the present application, a method for rapid flood forecasting and correction is provided, the method being executed by a processor and comprising:

[0020] Obtain target observation data before flooding occurs in the target area;

[0021] Perform clustering processing on the target observation data to obtain accurate observation data, fuzzy observation errors and erroneous observation data;

[0022] Perform data noise filtering on accurate observation data;

[0023] Perform data interference filtering on fuzzy observation errors and erroneous observation data;

[0024] The accurate observation data after interference filtering, the fuzzy observation errors and the erroneous observation data are filtered based on the filtering model to obtain the filtered data set;

[0025] Execute the input matching model on the filtered data set and perform matching processing;

[0026] Perform flood occurrence forecast based on datasets that meet the requirements.

[0027] Compared with the prior art, the present application system realizes rapid correction of observation data before the arrival of floods through clustering models, integration models, filtering models and matching models, and obtains more accurate observation data, which is convenient for subsequent analysis and use; at the same time, based on the corrected observation data, it can effectively realize rapid forecast of flood outbreak conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0029] Figure 1 is a structural diagram of the system of the present application;

[0030] Figure 2 It is a flow chart of the method of this application. DETAILED DESCRIPTION

[0031] The following will be combined with the attached examples of the present application Figure 1-2 The technical solutions in the embodiments of the present application are clearly and completely described together. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments.

[0032] In order to better understand this application, some terms are explained below:

[0033] K-means clustering algorithm: cluster a set of data into k groups. The algorithm process is as follows: randomly select k center points in the data set; calculate the distance from each data point to the k center points respectively, and classify the data points according to the distance; calculate the midpoint of the same type of data points as the position of the center point of the class to be updated; update the center point, repeatedly calculate the distance from each data point to the k center points, and classify the data points according to the distance. If the sum of the distances between each data point and the center point of its class does not change, the algorithm ends.

[0034] Data fuzzy logic algorithm: a method for dealing with fuzziness and uncertainty, suitable for scenarios that need to deal with fuzzy concepts.

[0035] Application Overview

[0036] Flood prevention operations often require flood forecasting and dispatching of reservoirs and rivers. Different forecasting models are selected according to different conditions. Commonly used flood forecasting models include rainfall-runoff correlation diagram method, corresponding water level method, empirical unit line model, Xin'anjiang model, water tank model, etc. However, these models have certain limitations on the scope of application scenarios, and can only be based on the observation errors of input data, which leads to errors in subsequent forecasts and ultimately causes forecast deviations. Based on this, the present application provides a system for rapid flood forecasting and correction, which realizes reasonable and rapid correction of observation data before the flood occurs, and ultimately ensures that the subsequent procedures of the forecast are carried out accurately.

[0037] This embodiment provides a system for rapid flood forecasting and correction, including a processor. It can be understood that the processor controls the modules in the system to perform corresponding operations.

[0038] In detail,

[0039] The system also includes: an end data processing module, an auxiliary processing module and a filtering output module. The end data processing module is data-connected to the auxiliary processing module, and the filtering output module is data-connected to the end data processing module and data-connected to the auxiliary processing module. It should be noted that the data connection is a wireless connection or a communication connection.

[0040] The processor is respectively connected to the data processing module, the auxiliary processing module and the filter output module. It can be understood that the processor can control the data processing module, the auxiliary processing module or the filter output module alone.

[0041] In some embodiments, the end data processing module is configured with a clustering model, and the K-means clustering algorithm is written in the clustering model. Based on this, the clustering model classifies and processes the observation data, and divides the observation data into accurate observation data, fuzzy observation errors and erroneous observation data according to preset clustering rules; the auxiliary processing module is configured with an integration model, and the integration model includes at least a primary data integration layer and a secondary data integration layer, and the primary data integration layer and the secondary data integration layer have data fuzzy logic algorithms written in them, based on which the primary data integration layer performs data interference filtering on accurate observation data, and the secondary data integration layer performs data interference filtering on fuzzy observation errors and erroneous observation data. The data between the integration model and the clustering model is connected with an intermediate database for redundant data storage.

[0042] In some implementations, a filtering model and a matching model are configured in the filtering output module. After the filtering model filters the observed data, the data is input into the matching model to perform matching processing.

[0043] In detail, the filtering model is:

[0044]

[0045] Among them, ξ is the filter output difference; is the observed value; is the standard value;

[0046] For example, when rainfall is the observation object, the observed The rainfall is 140 mm in 12 hours or 250 mm in 24 hours. For a standard precipitation of 100 mm in 12 hours or 200 mm in 24 hours, the ξ is 40 mm or 50 mm.

[0047] The matching model is:

[0048]

[0049] Among them, ε is the matching rate; ξ 标 The filter output value is a standard or preset value.

[0050] Based on the above, for example, when ξ is 40mm, ξ 标 When ξ is 20 mm, ε is 100%, which means the matching rate is qualified, that is, the data application of the subsequent program of the forecast program can be carried out; when ξ is 50 mm, ξ 标 When it is 40 mm, ε is 25%, which means that the matching degree is unsatisfactory, that is, the data application of the subsequent procedures of the forecasting program is not carried out.

[0051] In order to better understand the present application, the present application provides an exemplary method: a method for rapid flood forecasting and correction, which is executed by a processor. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0052] Specifically include:

[0053] Obtain the target observation data before the flood occurs in the target area; perform clustering processing on the target observation data to obtain accurate observation data, fuzzy observation errors and erroneous observation data; perform data interference filtering on the accurate observation data; perform data interference filtering on the fuzzy observation errors and erroneous observation data; perform filtering processing on the accurate observation data, fuzzy observation errors and erroneous observation data after interference filtering based on the filtering model to obtain a filtered data set; execute the input matching model on the filtered data set and perform matching processing; perform flood occurrence forecasting based on the data set that meets the requirements.

[0054] The above shows and describes the basic principles and main features of the present application and the advantages of the present application. For those skilled in the art, it is obvious that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or basic features of the present application. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present application is defined by the attached claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present application. Any figure mark in the claims should not be regarded as limiting the claims involved.

[0055] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A system for rapid flood forecasting and correction, comprising a processor, characterized in that: Also includes: An end data processing module, an auxiliary processing module and a filtering output module, the end data processing module is data-connected to the auxiliary processing module, the filtering output module is data-connected to the end data processing module and to the auxiliary processing module, and the processor is data-connected to the end data processing module, the auxiliary processing module and the filtering output module respectively.

2. The system according to claim 1, characterized in that The terminal data processing module is configured with a clustering model, which classifies and processes the observation data and divides the observation data into accurate observation data, fuzzy observation errors and erroneous observation data according to preset clustering rules.

3. The system according to claim 2, characterized in that The auxiliary processing module is configured with an integration model, which includes at least a primary data integration layer and a secondary data integration layer. The primary data integration layer performs data interference filtering on accurate observation data, and the secondary data integration layer performs data interference filtering on fuzzy observation errors and erroneous observation data.

4. The system according to claim 3, characterized in that The data between the integration model and the clustering model is connected with an intermediate database for storing redundant data.

5. The system according to claim 1, characterized in that The filtering output module is configured with a filtering model and a matching degree model. After the filtering model filters the observed data, the data is input into the matching degree model to perform matching degree processing.

6. The system according to claim 5, characterized in that The filtering model is: Among them, ξ is the filter output difference; is the observed value; is the standard value.

7. The system according to claim 5, characterized in that The matching degree model is: Among them, ε is the matching rate; ξ 标 The filter output value is a standard or preset value.

8. The system according to claim 2, characterized in that The clustering model includes a K-means clustering algorithm.

9. The system according to claim 3, characterized in that The primary data integration layer and the secondary data integration layer have data fuzzy logic algorithms written in them.

10. A method for rapid flood forecasting and correction, the method being executed by a processor, characterized in that: include: Obtain target observation data before flooding occurs in the target area; Perform clustering processing on the target observation data to obtain accurate observation data, fuzzy observation errors and erroneous observation data; Perform data noise filtering on accurate observation data; Perform data interference filtering on fuzzy observation errors and erroneous observation data; The accurate observation data after interference filtering, the fuzzy observation errors and the erroneous observation data are filtered based on the filtering model to obtain the filtered data set; Execute the input matching model on the filtered data set and perform matching processing; Perform flood occurrence forecast based on datasets that meet the requirements.

Images