AU2021106423A4 - Real-time flood control using recurrent neural networks - Google Patents
Real-time flood control using recurrent neural networks Download PDFInfo
- Publication number
- AU2021106423A4 AU2021106423A4 AU2021106423A AU2021106423A AU2021106423A4 AU 2021106423 A4 AU2021106423 A4 AU 2021106423A4 AU 2021106423 A AU2021106423 A AU 2021106423A AU 2021106423 A AU2021106423 A AU 2021106423A AU 2021106423 A4 AU2021106423 A4 AU 2021106423A4
- Authority
- AU
- Australia
- Prior art keywords
- forecast
- real
- recurrent neural
- flood control
- flood
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
- 230000000306 recurrent effect Effects 0.000 title claims abstract description 16
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 15
- 238000000034 method Methods 0.000 claims abstract description 56
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 16
- 238000004458 analytical method Methods 0.000 claims abstract description 13
- 238000007418 data mining Methods 0.000 claims abstract description 10
- 238000013277 forecasting method Methods 0.000 claims abstract description 7
- 230000008569 process Effects 0.000 claims description 18
- 238000013135 deep learning Methods 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 5
- 238000010219 correlation analysis Methods 0.000 claims description 4
- 230000007123 defense Effects 0.000 abstract description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 5
- 238000006424 Flood reaction Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000001537 neural effect Effects 0.000 description 2
- 238000012876 topography Methods 0.000 description 2
- 206010013647 Drowning Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000003466 anti-cipated effect Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
- G05B13/027—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks only
Landscapes
- Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
REAL-TIME FLOOD CONTROL USING RECURRENT NEURAL NETWORKS
Aspects of the present disclosure relate to a real-time flood control using recurrent neural
networks. It is not only an important technical support for flood and drought disaster defense,
but also an important means for the reservoir's profitable operation and efficient use of
resources. The method (100) comprises steps of extracting (102) historical information of
the river basin. The that collected historical data is trained using data mining algorithm (104).
The algorithm trains a set of characteristics for the forecast. Then a traditional hydrological
forecasting model and a traditional hydrological forecasting method base are constructed
(106). Then basic information is extracted (108) by aiming at a flood that possibly occur in
the forecast period. Finally, forecast precision analysis is performed (110) for analyzing the
possibility of the flood.
(FIG. 1 will be the reference figure)
- 12 -
rage i 011
100
Extracting a historical information of the river basin
10
Using a data mining algorithm to train 104
|106
Constructing model and method base10
Extracting basic information
Carrying out forecast precision analysis of the model
____ ___ ____ ___ ___ ____ ___ ____ ___ ___110
FIG. 1 Flowchart of method for real-time flood control using recurrent neural network
1
Description
rage i 011
100 Extracting a historical information of the river basin
10
Using a data mining algorithm to train 104
|106 Constructing model and method base10
Extracting basic information
Carrying out forecast precision analysis of the model ____ ___ ____ ___ ___ ____ ___ ____ ___ ___110
FIG. 1 Flowchart of method for real-time flood control using recurrent neural network
[0001] The present disclosure relates to a real-time flood control method and in particular to a real-time flood control using recurrent neural networks.
[0002] Background description includes information that may be useful in understanding the present invention. It is not an admission that any of the information provided herein is prior art or relevant to the presently claimed invention, or that any publication specifically or implicitly referenced is prior art.
[0003] Hydrological forecasting is not only an important technical support for flood and drought disaster defense, but also an important means for the reservoir's profitable operation and efficient use of resources. There are many relevant models and methods of hydrological forecast, and most of them can reflect some basic laws of hydrology. However, due to the limited understanding of hydrological and meteorological phenomena in river basins and the intricate changes of natural laws, traditional models and methods are difficult to fully reflect objective laws, such as statistical forecasting. The method usually faces the problem of insufficient consideration of physical meaning, and the land-air coupling method often has a contradiction between the meteorological information and the spatial scale of the hydrological model.
[0004] With the release of the "New Generation Artificial Intelligence Development Plan" in China, artificial intelligence has officially become a national strategy in some countries. As the main branch of artificial intelligence, deep learning is a method that uses big data for training and continuously optimizes the results through positive feedback. With the rapid development of the Internet and the Internet of Things, human computing capabilities have continued to improve, and deep learning has shown superior performance in many fields, especially in terms of mass data information extraction and production applications.
[0005] Flooding is a big problem in underdeveloped, emerging as well as in the developed countries. It is also a problem in the low lying rural, suburban as well as in the urban area. Every year people die by drowning due to sudden floods in their area. Even after the event that triggered the flooding ends, unforeseeable dangers can still be present in the areas where stagnant or slow draining water remains. Such circumstances can present a greater hazard specifically because the flood cause has ended, since people will be more inclined to discount the danger.
[0006] In some cases, it can be seen that mainly death is due to the lack of their awareness of situations that did not exist prior to the flood prior to the flood. for example, channels cut by the original moving water, sinkholes or depressions, displaced manhole covers, etc., rendering the water in some places deeper than it might appear from the surface or would be presumed based upon a person's knowledge of the pre-flood topography. In these types of cases, people who are familiar with the topography of the area also may be misled into thinking that it is safe to cross the remaining water. But this can be dangerous as they don't know the situation of the water that is present.
[00071 In some embodiments, the numbers expressing quantities or dimensions of items, and so forth, used to describe and claim certain embodiments of the invention are to be understood as being modified in some instances by the term "about." Accordingly, in some embodiments, the numerical parameters set forth in the written description and attached claims are approximations that can vary depending upon the desired properties sought to be obtained by a particular embodiment. In some embodiments, the numerical parameters should be construed in light of the number of reported significant digits and by applying ordinary rounding techniques. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of some embodiments of the invention are approximations, the numerical values set forth in the specific examples are reported as precisely as practicable. The numerical values presented in some embodiments of the invention may contain certain errors necessarily resulting from the standard deviation found in their respective testing measurements.
[0008] The recitation of ranges of values herein is merely intended to serve as a shorthand method of referring individually to each separate value falling within the range. Unless otherwise indicated herein, each individual value is incorporated into the specification as if it were individually recited herein. All methods described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The use of any and all examples, or exemplary language (e.g. "such as") provided with respect to certain embodiments herein is intended merely to better illuminate the invention and does not pose a limitation on the scope of the invention otherwise claimed. No language in the specification should be construed as indicating any non-claimed element essential to the practice of the invention.
[0009] It is an object of the present disclosure to predict flood in real-time.
[0010] The present concept of the present invention is directed towards a method for real-time flood control using recurrent neural network.
[0011] In an aspect, A method for real-time flood control using recurrent neural, wherein said method comprises steps of: extracting a historical information of the river basin, wherein the historical information comprises a set of characteristic factors for a forecast; using a data mining algorithm to train the set of characteristic factors for forecast; constructing a traditional hydrological forecasting model base and a traditional hydrological forecasting method base, wherein the traditional hydrological forecasting model base and a traditional hydrological forecasting method base are developed using the deep learning algorithm; extracting basic information, obtained by aiming at a flood process which possibly occurs in a forecast period; carrying out forecast precision analysis of the model using the extracted information.
[0012] In an aspect, the set of characteristic factors for the forecast are obtained by performing physical cause analysis, correlation analysis and significance test on the historical information. Using data mining algorithm multiple set of flood process sets with similar magnitude are obtained. If a required accuracy is not achieved while performing the forecast precision analysis then the basic information is again extracted.
[0013] One should appreciate that although the present disclosure has been explained with respect to a defined set of functional modules, any other module or set of modules can be added/deleted/modified/combined, and any such changes in architecture/construction of the proposed system are completely within the scope of the present disclosure. Each module can also be fragmented into one or more functional sub-modules, all of which also completely within the scope of the present disclosure.
[0014] Various objects, features, aspects and advantages of the inventive subject matter will become more apparent from the following detailed description of preferred embodiments, along with the accompanying drawing figures in which like numerals represent like components.
[0015] The accompanying drawings are included to provide a further understanding of the present disclosure and are incorporated in and constitute a part of this specification. The drawings illustrate exemplary embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.
[0016] FIG. 1 illustrates a flowchart of method for real-time flood control using recurrent neural.
[00171 The accompanying drawings are included to provide a further understanding of the present disclosure, and are incorporated in and constitute a part of this specification. The drawings illustrate exemplary embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.
[0018] Other objects, advantages and novel features of the invention will become apparent from the following detailed description of the present embodiment when taken in conjunction with the accompanying drawings.
[0021] In the following description, numerous specific details are set forth in order to provide a thorough understanding of embodiments of the present invention. It will be apparent to one skilled in the art that embodiments of the present invention may be practiced without some of these specific details.
[0022] Embodiments of the present invention include various steps, which will be described below. The steps may be performed by hardware components or may be embodied in machine-executable instructions, which may be used to cause a general-purpose or special-purpose processor programmed with the instructions to perform the steps. Alternatively, steps may be performed by a combination of hardware, software, and firmware and/or by human operators.
[0023] If the specification states a component or feature "may", "can", "could", or "might" be included or have a characteristic, that particular component or feature is not required to be included or have the characteristic.
[0024] Although the present invention has been described with respect to monitoring and surveillance for defense purposes, it should be appreciated that the same has been done merely to illustrate the invention in an exemplary manner and any other purpose or function for which the explained structure or configuration can be used, is covered within the scope of the present disclosure.
[0025] Exemplary embodiments will now be described more fully hereinafter with reference to the accompanying drawings, in which exemplary embodiments are shown. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. These embodiments are provided so that this disclosure will be thorough and complete and will fully convey the scope of the invention to those of ordinary skill in the art. Moreover, all statements herein reciting embodiments of the invention, as well as specific examples thereof, are intended to encompass both structural and functional equivalents thereof. Additionally, it is intended that such equivalents include both currently known equivalents as well as equivalents developed in the future (i.e., any elements developed that perform the same function, regardless of structure).
[00261 The following is a detailed description of embodiments of the disclosure depicted in the accompanying drawings. The embodiments are in such detail as to clearly communicate the disclosure. However, the amount of detail offered is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the present disclosure as defined by the appended claims.
[00271 Each of the appended claims defines a separate invention, which for infringement purposes is recognized as including equivalents to the various elements or limitations specified in the claims. Depending on the context, all references below to the "invention" may in some cases refer to certain specific embodiments only. In other cases, it will be recognized that references to the "invention" will refer to subject matter recited in one or more, but not necessarily all, of the claims.
[00281 Various terms as used herein are shown below. To the extent a term used in a claim is not defined below, it should be given the broadest definition persons in the pertinent art have given that term as reflected in printed publications and issued patents at the time of filing.
[0029] In an embodiment of the present disclosure, FIG. 1 is a illustrates a flowchart of method (100) for real-time flood control using recurrent neural network. The method (100) comprises steps of extracting (102) a historical information of the river basin, wherein the historical information comprises a set of characteristic factors for a forecast; using a data mining algorithm (104) to train the set of characteristic factors for forecast; constructing (106) a traditional hydrological forecasting model base and a traditional hydrological forecasting method base, wherein the traditional hydrological forecasting model base and a traditional hydrological forecasting method base are developed using the deep learning algorithm; extracting (108) basic information, obtained by aiming at a flood process which possibly occurs in a forecast period; carrying (110) out forecast precision analysis of the model using the extracted information.
[0029] In an aspect of the present invention, extract the historical information of the river basin, and obtain the set of characteristic factors for the hydrological forecast of the river basin by performing physical cause analysis, correlation analysis, and significance test on all historical information.
[0030] In an aspect of the present invention, use the data mining algorithm (104) to train the set of characteristic factors for hydrological forecasting to obtain multiple sets of flood process sets with similar magnitudes and process shapes under the action of different factors.
[0031] In another aspect of the present invention, construct (106) a traditional hydrological forecast model library and method library. Based on the characteristic factors and field floods described in previous step, use deep learning algorithms to carry out parameter calibration of models and methods, and obtain a set of multiple sets of parameter solutions corresponding to different models and methods, And form a model library and method library supporting models, methods and parameter schemes.
[0032] In another aspect of the present invention, for the flood process that may occur during the foreseeable period, extract the basic information that can be obtained, and use cluster analysis to match the basic information with the feature factor set, and then obtain the magnitude and risk of possible floods. Describe the process shape, and then select the corresponding model, method and supporting parameters in the model library and method library to complete the hydrological forecast calculation to obtain forecast information.
[0033] In another aspect of the present invention, perform a forecasting effect test to determine whether the forecasting accuracy (108) meets the requirements, and if so, terminate the forecasting; if not, repeat step S4 and replace the model, method, and supporting parameters to re-forecast until the forecasting accuracy meets the requirements.
[0034] In another aspect of the present invention, the first step of extracting (102) includes the steps of Extract the historical information of the river basin: classify according to the information coverage level and physical causes, and divide it into underlying surface conditions and previous meteorological conditions, where the underlying surface conditions include previous rainfall, runoff, previous impact rainfall, soil humidity, and temperature; The previous meteorological conditions include 140 circulation indexes, which include 90 atmospheric circulation indexes, 30 sea surface temperature indexes, and 20 other indexes.
[0035] Also includes, calculation formula is as follows by performing physical cause analysis and correlation analysis on all historical information. Among them: In the formula: rxy represents the correlation coefficient between different kinds of historical information x and y; Sxy represents the covariance between different kinds of historical information x and y; Sx represents the standard deviation of historical information x; Sy represents the standard deviation of historical information y Xi and yi are the i-th individual of historical information x and y; is the average of historical information x and y; n is the number of individuals of different types of historical information.
[00361 In another aspect of the present invention, he data mining algorithm (104) in step second step includes a multi-dimensional Euclidean distance clustering method and a step function and a bulldozer distance clustering method. The multi-dimensional Euclidean distance clustering method calculates Euclidean distances of different forecast factors for different historical flood processes to determine historical flood processes with similar magnitudes in different classifications. The calculation formula is as follows: In the formula:
D (X, Y) is the Euclidean distance of a certain type of forecasting factors in the historical flood process of different times; X, Y respectively represent the historical flooding process of two different times; xi, yi are a certain type of corresponding historical flooding process The i-th value of the forecast factor; The bulldozer distance clustering method calculates field floods with similar process shapes in different historical flood processes, and marks them as a type.
[00371 In another aspect of the present invention, in step third, the parameter estimation of the traditional hydrological forecasting model using a deep learning algorithm including a recursive neural network is repeated. For each type of traditional hydrological forecasting model, the calibration process is repeated and the calibration results of each model are described Unified storage and storage to form a model library and method library.
[0038] In another aspect of the present invention, in final steps, extracting (108) basic information, obtained by aiming at a flood process which possibly occurs in a forecast period; carrying (110) out forecast precision analysis of the model using the extracted information.
[0039] While the foregoing describes, various embodiments of the present invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof. The scope of the invention is determined by the claims that follow. The invention is not limited to the described embodiments, versions or examples, which are included to enable a person having ordinary skill in the art to make and use the invention when combined with information and knowledge available to the person having ordinary skill in the art.
[0045] The present invention is not limited to the above-described specific embodiments, and various modifications and variations are possible. Any modifications, equivalents, improvements and the like made to the above embodiments in accordance with the technical spirit of the present invention should be included in the scope of the present invention.
[00461 Thus, the scope of the present disclosure is defined by the appended claims and includes both combinations and sub-combinations of the various features described hereinabove as well as variations and modifications thereof, which would occur to persons skilled in the art upon reading the foregoing description.
Claims (4)
1. A method (100) for real-time flood control using recurrent neural network, wherein said method (100) comprises steps of:
extracting (102) a historical information of the river basin, wherein the historical information comprises a set of characteristic factors for a forecast;
using a data mining algorithm (104) to train the set of characteristic factors for forecast;
constructing (106) a traditional hydrological forecasting model base and a traditional hydrological forecasting method base, wherein the traditional hydrological forecasting model base and a traditional hydrological forecasting method base are developed using the deep learning algorithm;
extracting (108) basic information, obtained by aiming at a flood process which possibly occurs in a forecast period;
carrying (110) out forecast precision analysis of the model using the extracted information.
2. The method (100) for real-time flood control using recurrent neural network as claimed in claim 1, wherein the set of characteristic factors for the forecast are obtained (102) by performing physical cause analysis, correlation analysis and significance test on the historical information.
3. The method (100) for real-time flood control using recurrent neural network as claimed in claim 1, wherein using data mining algorithm (104) multiple set of flood process sets with similar magnitude are obtained.
4. The method (100) for real-time flood control using recurrent neural network as claimed in claim 1, wherein if a required accuracy is not achieved while performing the forecast precision analysis (110) then the basic information is again extracted.
1 1
Application no.: Total no. of sheets: 1 22 Aug 2021 2021106423 Page 1 of 1
FIG. 1 Flowchart of method for real-time flood control using recurrent neural network
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2021106423A AU2021106423A4 (en) | 2021-08-22 | 2021-08-22 | Real-time flood control using recurrent neural networks |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2021106423A AU2021106423A4 (en) | 2021-08-22 | 2021-08-22 | Real-time flood control using recurrent neural networks |
Publications (1)
Publication Number | Publication Date |
---|---|
AU2021106423A4 true AU2021106423A4 (en) | 2021-11-25 |
Family
ID=78610559
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
AU2021106423A Ceased AU2021106423A4 (en) | 2021-08-22 | 2021-08-22 | Real-time flood control using recurrent neural networks |
Country Status (1)
Country | Link |
---|---|
AU (1) | AU2021106423A4 (en) |
-
2021
- 2021-08-22 AU AU2021106423A patent/AU2021106423A4/en not_active Ceased
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110852577B (en) | Urban flood assessment method based on urban toughness and urban watershed hydrologic model | |
CN108304668B (en) | Flood prediction method combining hydrologic process data and historical prior data | |
Ghosh et al. | Urban expansion induced vulnerability assessment of East Kolkata Wetland using Fuzzy MCDM method | |
CN112785043B (en) | Flood forecasting method based on time sequence attention mechanism | |
CN106875060B (en) | Flood real-time correction method based on global automatic optimization algorithm | |
CN110619432A (en) | Feature extraction hydrological forecasting method based on deep learning | |
CN112016831A (en) | AI intelligent forecast-based urban waterlogging landing area identification method | |
Lin et al. | Development of a real-time regional-inundation forecasting model for the inundation warning system | |
CN117010726B (en) | Intelligent early warning method and system for urban flood control | |
CN111507375A (en) | Urban waterlogging risk rapid assessment method and system | |
Goyal et al. | Climate change impact on precipitation extremes over Indian cities: non-stationary analysis | |
CN113807545A (en) | River and lake ecological flow forecasting and early warning method based on deep learning and physical model | |
Núñez et al. | Resolving regional frequency analysis of precipitation at large and complex scales using a bottom-up approach: The Latin America and the Caribbean Drought Atlas | |
CN108615098A (en) | Water supply network pipeline burst Risk Forecast Method based on Bayesian survival analysis | |
Straumann et al. | Delineation of valleys and valley floors | |
AU2021106423A4 (en) | Real-time flood control using recurrent neural networks | |
Liu et al. | Mapping detention basins and deriving their spatial attributes from airborne LiDAR data for hydrological applications | |
Rohaimi et al. | 3 Hours ahead of time flood water level prediction using NNARX structure: Case study pahang | |
CN113626929A (en) | Multi-stage multi-topology ship traffic complexity measuring method and system | |
Maze et al. | Profile classification models | |
CN107608938A (en) | The factor screening method towards two-value classification of tree algorithm is returned based on enhancing | |
Priyanka et al. | Forecasting and meta-features estimation of wastewater and climate change impacts in coastal region using manifold learning | |
Goshem et al. | Analyzing and predicting land use and land cover changes with an integrated CA-Markov Model: A Spatiotemporal perspective in case of Chuko Town and Surroundings, Sidama Region, Ethiopia | |
CN108985493A (en) | A kind of ground class variation prediction method based on self-adapting changeable filter | |
Scotto et al. | Model-based clustering of Baltic sea-level |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
FGI | Letters patent sealed or granted (innovation patent) | ||
MK22 | Patent ceased section 143a(d), or expired - non payment of renewal fee or expiry |