CN114091362A - Water level prediction method, system, storage medium and equipment - Google Patents
Water level prediction method, system, storage medium and equipment Download PDFInfo
- Publication number
- CN114091362A CN114091362A CN202210076811.4A CN202210076811A CN114091362A CN 114091362 A CN114091362 A CN 114091362A CN 202210076811 A CN202210076811 A CN 202210076811A CN 114091362 A CN114091362 A CN 114091362A
- Authority
- CN
- China
- Prior art keywords
- water level
- data
- time
- rainfall
- historical
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/12—Timing analysis or timing optimisation
Abstract
The invention provides a water level prediction method, a water level prediction system, a storage medium and a device, wherein the method comprises the following steps: acquiring a plurality of measuring points, historical water level data of the measuring points and a plurality of preselected areas, and acquiring historical rainfall data of the preselected areas according to the preselected areas; acquiring historical rainfall data of the associated area, correcting a time axis of rainfall time of the associated area according to the time difference, and acquiring the corrected historical rainfall data of the associated area so as to obtain a water level prediction model; and (4) combining with the water level prediction model to predict and obtain the water level data of the target measuring point. According to the water level prediction method, the water level prediction system, the storage medium and the equipment, the water level prediction model predicted water level is obtained by taking the preselected areas in the same water area system and the time difference between the water level value change time and the rainfall time of the preselected areas as model training data, so that the model prediction accuracy is improved, and the technical problem of low accuracy of the water level data obtained by the water level prediction model in the prior art is solved.
Description
Technical Field
The present invention relates to the field of water level prediction technologies, and in particular, to a water level prediction method, a water level prediction system, a storage medium, and a storage device.
Background
The water level condition of the river/reservoir has an important influence on the environment around the river/reservoir, different water level conditions can influence the occurrence conditions of meteorological disasters such as flood and drought, and in order to monitor the meteorological disasters such as flood and drought in time and prepare preventive measures, the future water level condition of the river/reservoir needs to be predicted in advance to obtain a water level prediction result.
The rainfall time point and the water level start rising time point of the area around the water level measuring point are different, the water level often starts rising after a period of rainfall, and the time interval is longer. Furthermore, the rainfall area influencing the rising of the water level measuring point is not only rainfall in the local area, but is often influenced by the rainfall of the whole water area.
In the prior art, the water level prediction model does not consider the time difference between rainfall data and water level data and the influence of rainfall in the whole water area on the prediction data, so that the accuracy of the water level data obtained by the water level prediction model is not high, and the error between the water level prediction result and the actual water level situation is large.
Disclosure of Invention
Based on this, the invention aims to provide a water level prediction method, a water level prediction system, a storage medium and a device, so as to solve the technical problem that the accuracy of water level data obtained by the prediction of a water level prediction model in the prior art is not high.
One aspect of the present invention provides a water level prediction method, including:
acquiring a plurality of measuring points, acquiring historical water level data of the measuring points according to the measuring points, acquiring a plurality of preselected areas in the same water area system with the measuring points, and acquiring historical rainfall data of the preselected areas according to the preselected areas, wherein the historical water level data of the measuring points comprises water level value change time, and the historical rainfall data of the preselected areas comprises rainfall time of the preselected areas;
respectively carrying out data processing on the historical water level data of the measuring points and the historical rainfall data of the preselected area, carrying out dynamic association calculation on the processed historical water level data of the measuring points and the processed historical rainfall data of the preselected area, determining a plurality of associated areas related to the historical water level data of the measuring points according to association degrees, and determining the time difference between the change time of the water level value and the rainfall time of the preselected area;
obtaining historical rainfall data of the associated area, wherein the historical rainfall data of the associated area comprises rainfall time of the associated area, correcting a time axis of the rainfall time of the associated area according to the time difference to obtain corrected historical rainfall data of the associated area, and performing model training according to the corrected historical rainfall data of the associated area and the measured point historical water level data to obtain a water level prediction model;
and acquiring target measuring points, initial water level data of the target measuring points and latest rainfall data of the associated regions, and predicting the water level data of the target measuring points according to the water level prediction model and by combining the initial water level data of the target measuring points and the latest rainfall data of the associated regions.
According to the water level prediction method, the multiple preselected areas in the same water area system are used as model training data, the acquisition range of the model training data is expanded, the prediction accuracy of the model is improved, the time difference between the water level value change time and the rainfall time of the preselected areas is obtained, the time axis of the rainfall time of the associated areas is corrected according to the time difference, the corrected historical rainfall data of the associated areas is obtained, the model is trained according to the corrected historical rainfall data of the associated areas and the measured point historical water level data to obtain the water level prediction model, the time difference between the rainfall time and the water level change time is considered, the prediction accuracy of the model is further improved, and the technical problem that the accuracy of the water level data obtained by the water level prediction model in the prior art is not high is solved.
In addition, according to the above water level prediction method of the present invention, the following additional technical features may be provided:
further, the step of performing dynamic correlation calculation on the processed measuring point historical water level data and the processed pre-selected area historical rainfall data comprises:
acquiring the processed rainfall time of the preselected area, gradually carrying out time backward shift adjustment on the rainfall time according to a preset time interval, and associating the adjusted rainfall time with the historical water level data of the measuring points to obtain a plurality of association results;
and acquiring the maximum correlation degree according to the plurality of correlation results, and taking the maximum correlation degree as the correlation degree of the correlation area and the measuring point historical water level data.
Further, in the step of gradually adjusting the rainfall time by time shift according to a preset time interval:
the maximum adjustment time length for the time-shift adjustment is 240 hours.
Further, the step of taking the maximum correlation degree as the correlation degree of the correlation area and the measuring point historical water level data comprises the following steps:
and acquiring a time lag adjustment duration corresponding to the maximum correlation degree according to the maximum correlation degree, and acquiring the time difference according to the time lag adjustment duration corresponding to the maximum correlation degree.
Further, the step of gradually adjusting the rainfall time by shifting the rainfall time backward according to a preset time interval comprises:
acquiring the processed weather data of the preselected area;
and selecting the time length of time backward shift adjustment according to the weather data.
Further, the step of gradually adjusting the rainfall time by shifting the rainfall time backward according to a preset time interval comprises:
judging whether the adjusted rainfall time reaches the limit or not according to the maximum adjustment time length;
if not, recording the adjusted current rainfall time and the current association degree corresponding to the adjusted current rainfall time;
and according to a preset time interval, carrying out time backward shift adjustment on the adjusted current rainfall time until the maximum adjustment time length of the time backward shift adjustment reaches the limit.
Further, the step of predicting the water level data of the target measuring point by combining the initial water level data of the target measuring point and the latest rainfall data of the associated region comprises the following steps:
and acquiring the water level data of the target measuring point, collecting the water level data of the target measuring point in the water level prediction model, and updating the water level prediction model.
In another aspect, the present invention provides a water level prediction system, including:
the acquisition module is used for acquiring a plurality of measuring points, acquiring historical water level data of the measuring points according to the measuring points, acquiring a plurality of preselected areas in the same water area system with the measuring points, and acquiring historical rainfall data of the preselected areas according to the preselected areas, wherein the historical water level data of the measuring points comprise water level value change time, and the historical rainfall data of the preselected areas comprise rainfall time of the preselected areas;
the data processing module is used for respectively carrying out data processing on the measuring point historical water level data and the pre-selection area historical rainfall data, carrying out dynamic association calculation on the processed measuring point historical water level data and the processed pre-selection area historical rainfall data, determining a plurality of association areas related to the measuring point historical water level data according to association degrees, and determining the time difference between the water level value change time and the pre-selection area rainfall time;
the model training module is used for acquiring historical rainfall data of the associated area, the historical rainfall data of the associated area comprises rainfall time of the associated area, a time axis of the rainfall time of the associated area is corrected according to the time difference to obtain corrected historical rainfall data of the associated area, and model training is carried out according to the corrected historical rainfall data of the associated area and the measured point historical water level data to obtain a water level prediction model;
and the prediction module is used for acquiring target measuring points, initial water level data of the target measuring points and latest rainfall data of the associated region, and predicting the water level data of the target measuring points according to the water level prediction model and by combining the initial water level data of the target measuring points and the latest rainfall data of the associated region.
Another aspect of the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the water level prediction method as described above.
Another aspect of the present invention also provides a data processing apparatus comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the water level prediction method as described above when executing the program.
Drawings
FIG. 1 is a flow chart illustrating a water level prediction method according to a first embodiment of the present invention;
FIG. 2 is a flow chart of a water level prediction method according to a second embodiment of the present invention;
FIG. 3 is a diagram illustrating the detailed steps of step S202 according to the second embodiment of the present invention;
fig. 4 is a system block diagram of a water level prediction system according to a third embodiment of the present invention.
The following detailed description will further illustrate the invention in conjunction with the above-described figures.
Detailed Description
To facilitate an understanding of the invention, the invention will now be described more fully with reference to the accompanying drawings. Several embodiments of the invention are presented in the drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
In the invention, the relevance between the rainfall data of the preselected area and the water level data of the measuring points is determined through a dynamic relevance algorithm, and the time difference between the rainfall data of the preselected area and the water level data of the measuring points is determined. According to the relevance, a partial area with high relevance can be selected from rainfall data of a preselected area as model input data, and the time axis of the data can be corrected before the model is input according to the time difference, so that the accuracy of the model is improved.
Furthermore, the invention uses the 'expanded alternative area rainfall data' + 'dynamic association algorithm', in the existing water level prediction method, the rainfall data of the area near the water level measuring point is generally only used as model input data, and the influence of the rainfall of the water area system or larger area on the water level measuring point data is often ignored. On one hand, on the invention, a plurality of preselected areas in the same water area system are used as selection areas for model training, the selection range of historical rainfall data of the preselected areas is expanded, then areas with standard correlation degree are screened through a dynamic correlation algorithm, and the calculated time difference is stored as a subsequent data processing basis, so that the prediction accuracy is further improved.
Example one
Referring to fig. 1, a water level prediction method according to a first embodiment of the present invention is shown, the method includes steps S101 to S104:
s101, obtaining a plurality of measuring points, obtaining historical water level data of the measuring points according to the measuring points, obtaining a plurality of preselected areas in the same water area system with the measuring points, and obtaining historical rainfall data of the preselected areas according to the preselected areas, wherein the historical water level data of the measuring points comprise water level value change time, and the historical rainfall data of the preselected areas comprise rainfall time of the preselected areas.
The existing prediction method only selects municipal rainfall data which are the same as water level measuring points as input data, but the regions of the municipal districts are huge, the rainfall amount of each district is different greatly, and the regions of the whole system of rivers, lakes and reservoirs are huge, so that rainfall areas influencing water level fluctuation of the measuring points are not in the city, more rainfall areas influence the water level fluctuation of the measuring points in the upstream municipal districts, and the selection of the influence areas is enlarged, the influence areas are refined, and the data input by the model are more comprehensive.
S102, respectively carrying out data processing on the measuring point historical water level data and the pre-selection area historical rainfall data, carrying out dynamic correlation calculation on the processed measuring point historical water level data and the processed pre-selection area historical rainfall data, determining a plurality of correlation areas related to the measuring point historical water level data according to the correlation degree, and determining the time difference between the water level value change time and the pre-selection area rainfall time.
In the application, a dynamic correlation diagram and a dynamic correlation analysis method are established, and the existing prediction method usually ignores the time difference between rainfall and water level fluctuation, so that the correlation degree between a plurality of rainfall areas which greatly influence the water level rising and the water level fluctuation of a measuring point is not high under the condition of not adjusting the time. According to the method, the time difference is adjusted once every hour, the highest correlation degree during the time difference adjustment period is found out to be used as the selection basis of the region, the time difference factor can be solved in the subsequent model training process, the region with the larger correlation degree can be extracted to be used as the main influence factor, and the purpose of improving the accuracy rate is finally achieved.
S103, obtaining historical rainfall data of the associated area, wherein the historical rainfall data of the associated area comprises rainfall time of the associated area, correcting a time axis of the rainfall time of the associated area according to the time difference to obtain corrected historical rainfall data of the associated area, and performing model training according to the corrected historical rainfall data of the associated area and the measured point historical water level data to obtain a water level prediction model.
Specifically, the accuracy of water level prediction is improved by establishing an accurate correlation diagram of weather data and water level data. The premise of establishing an accurate association graph is to acquire weather data of an accurate region, find out the association relation of each water level measuring point and the weather condition of each region on the time difference through a dynamic linkage analysis method, and predict the corresponding measuring point water level by using the region with higher association degree. And finally, the future water level situation can be predicted more accurately on the premise of lower cost.
S104, acquiring target measuring points, initial water level data of the target measuring points and latest rainfall data of the associated regions, and predicting the water level data of the target measuring points according to the water level prediction model and the combination of the initial water level data of the target measuring points and the latest rainfall data of the associated regions.
In summary, in the water level prediction method in the above embodiment of the present invention, the multiple preselected areas in the same water area system are used as model training data, so as to expand the collection range of the model training data and improve the prediction accuracy of the model, further, the time difference between the water level value change time and the rainfall time of the preselected area is obtained, the time axis of the rainfall time of the associated area is corrected according to the time difference, so as to obtain the corrected historical rainfall data of the associated area, the model training is performed according to the corrected historical rainfall data of the associated area and the measured point historical water level data, so as to obtain the water level prediction model, the time difference between the rainfall time and the water level change time is considered, so as to further improve the prediction accuracy of the model, and solve the technical problem in the prior art that the accuracy of the water level data obtained by the water level prediction model in prediction is not high.
Example two
Referring to fig. 2, a water level prediction method according to a second embodiment of the present invention is shown, the method includes steps S201 to S205:
s201, obtaining a plurality of measuring points, obtaining historical water level data of the measuring points according to the measuring points, obtaining a plurality of preselected areas in the same water area system with the measuring points, and obtaining historical rainfall data of the preselected areas according to the preselected areas, wherein the historical water level data of the measuring points comprise water level value change time, and the historical rainfall data of the preselected areas comprise rainfall time of the preselected areas.
In the above steps, when selecting the data source, for single point prediction and multipoint prediction, if the data source is single point prediction, selecting historical water level information of the point for one year, and then selecting rainfall information of a region as large as possible around the point accurately to a county according to the geographical position of the point, wherein the granularity of all the information needs to be within one hour. If the prediction is multipoint prediction, each point is subjected to model building.
Acquiring historical water level data of the measuring points, wherein the historical water level data of the measuring points comprise initial water levels of the measuring points at specific time and final water levels after preset time; and acquiring the average water level change value of the measuring point according to the initial water level and the termination water level in combination with preset time.
S202, data processing is respectively carried out on the measuring point historical water level data and the pre-selection area historical rainfall data, dynamic association calculation is carried out on the processed measuring point historical water level data and the processed pre-selection area historical rainfall data, a plurality of association areas related to the measuring point historical water level data are determined according to association degrees, and the time difference between the water level value change time and the pre-selection area rainfall time is determined.
In some optional embodiments, referring to fig. 3, the step S202 may specifically include steps S2021 to S2023:
s2021, acquiring the processed rainfall time of the preselected area, gradually carrying out time backward adjustment on the rainfall time according to a preset time interval, and associating the adjusted rainfall time with the measuring point historical water level data to obtain a plurality of association results.
Acquiring the processed weather data of a preselected area before the step of gradually carrying out time backward adjustment on the rainfall time according to a preset time interval; and selecting the time length of the time backward adjustment according to the weather data.
Further, the step of gradually adjusting the rainfall time by a time shift according to the preset time interval comprises the following steps:
judging whether the adjusted rainfall time reaches the limit or not according to the maximum adjustment time length; if the current rainfall time does not reach the limit, recording the adjusted current rainfall time and the current association degree corresponding to the adjusted current rainfall time; and according to a preset time interval, carrying out time backward shift adjustment on the adjusted current rainfall time until the maximum adjustment time length of the time backward shift adjustment reaches the limit.
S2022, obtaining the maximum correlation degree according to the plurality of correlation results, and taking the maximum correlation degree as the correlation degree of the correlation area and the measuring point historical water level data.
S2023, obtaining the time backward shift adjustment duration corresponding to the maximum correlation degree according to the maximum correlation degree, and obtaining the time difference according to the time backward shift adjustment duration corresponding to the maximum correlation degree.
Regarding the dynamic correlation analysis method, considering that rain in a certain area and water level rise of a measuring point generally occur simultaneously, if the calculation of the correlation degree is carried out according to the same time line, the calculation is inaccurate. Taking a region and a measuring point as an example, gradually adjusting the rainfall time of the region in hours, associating the rainfall time with the water level data of the measuring point once each adjustment is performed, setting the maximum adjustment time length to be 240 hours, taking the maximum association degree during the adjustment as the association degree of the region and the water level data of the measuring point, and recording the adjustment hours at the time. And calculating rainfall data and measured point water level data of each area and recording the maximum correlation degree and the corresponding adjustment time of each area.
S203, obtaining the historical rainfall data of the associated area, wherein the historical rainfall data of the associated area comprises the rainfall time of the associated area, correcting the time axis of the rainfall time of the associated area according to the time difference to obtain the corrected historical rainfall data of the associated area, and performing model training according to the corrected historical rainfall data of the associated area and the measured point historical water level data to obtain a water level prediction model.
Further, acquiring historical rainfall data of the associated area;
judging whether the historical rainfall data of the associated region has data loss or not according to the data integrity;
and if so, completing the historical rainfall data of the associated area with data loss according to a preset mode.
As a specific example, when cleaning the original data, the missing data is first filled up, the rainfall data needs to use 0 instead of the missing data, and the water level data needs to use an average filling method. And eliminating abnormal data or changing the abnormal data into a normal range, wherein operation needs to be performed on data characteristics.
When data preparation is carried out, all the selected area rainfall data are taken, the area rainfall data are adjusted according to the recorded maximum correlation degree adjustment duration, all the adjusted rainfall data and all the adjusted water level data are integrated into a data set, the rainfall data and the water level data in the previous period are taken as input data, and the water level data in the later period are taken as tags.
Further, a dynamic association graph is established, and dynamic association analysis is carried out on the water level measuring point data and rainfall data of all regions. Then, a plurality of areas with the maximum relevance are selected (selected according to the water area condition), and the time difference of the areas and the measured point water level relevance is recorded and used as the basis for preparing training data later.
In the model training, Z-score normalization is adopted, the model is a double-layer LSTM plus one full-connection layer, wherein the first-layer LSTM activation function is tan h, the intermediate output and the final output are transmitted into the second-layer LSTM, the second-layer LSTM activation function is tan h, then the second-layer LSTM activation function is transmitted into one full-connection layer, the output value of the full-connection layer is the output result, and the dimensionality of the output result is the hours needing to be predicted later. Adam is selected as the optimization function and mse is selected as the loss function. The number of training times and the number of batches are determined according to specific data.
S204, acquiring the target measuring point, the initial water level data of the target measuring point and the latest rainfall data of the associated region, and predicting according to the water level prediction model and combining the initial water level data of the target measuring point and the latest rainfall data of the associated region to obtain the water level data of the target measuring point.
In the data preparation link, rainfall data of a period of time before prediction is taken, whether the data are selected or not is judged, the selected data are adjusted according to the optimal time recorded by the dynamic association diagram, and then the data and water level data of a period of time before prediction are integrated into input data.
And in model prediction, putting the sorted data into a model to predict future water level data.
S205, acquiring water level data of the target measuring point, collecting the water level data of the target measuring point in the water level prediction model, and updating the water level prediction model.
As a specific example, in order to improve the accuracy of model prediction, after the water level prediction value of the target measuring point is obtained, the water level prediction value is collected in the water level prediction model, and the water level prediction model is updated so as to improve the model prediction accuracy.
In the present application, the model is trained as a subsequent prediction model according to the above method. In specific implementation, the model is generally updated once a year, so that the model is more accurate.
It should be noted that, the method provided by the second embodiment of the present invention, which implements the same principle and produces some technical effects as the first embodiment, can refer to the corresponding contents in the first embodiment for the sake of brief description, where this embodiment is not mentioned.
In summary, in the water level prediction method in the above embodiment of the present invention, the multiple preselected areas in the same water area system are used as model training data, so as to expand the collection range of the model training data and improve the prediction accuracy of the model, further, the time difference between the water level value change time and the rainfall time of the preselected area is obtained, the time axis of the rainfall time of the associated area is corrected according to the time difference, so as to obtain the corrected historical rainfall data of the associated area, the model training is performed according to the corrected historical rainfall data of the associated area and the measured point historical water level data, so as to obtain the water level prediction model, the time difference between the rainfall time and the water level change time is considered, so as to further improve the prediction accuracy of the model, and solve the technical problem in the prior art that the accuracy of the water level data obtained by the water level prediction model in prediction is not high.
EXAMPLE III
Referring to fig. 4, a water level prediction system according to a third embodiment of the present invention is shown, the system including:
the acquisition module is used for acquiring a plurality of measuring points, acquiring historical water level data of the measuring points according to the measuring points, acquiring a plurality of preselected areas in the same water area system with the measuring points, and acquiring historical rainfall data of the preselected areas according to the preselected areas, wherein the historical water level data of the measuring points comprise water level value change time, and the historical rainfall data of the preselected areas comprise rainfall time of the preselected areas;
the data processing module is used for respectively carrying out data processing on the measuring point historical water level data and the pre-selection area historical rainfall data, carrying out dynamic association calculation on the processed measuring point historical water level data and the processed pre-selection area historical rainfall data, determining a plurality of association areas related to the measuring point historical water level data according to association degrees, and determining the time difference between the water level value change time and the pre-selection area rainfall time;
the model training module is used for acquiring historical rainfall data of the associated area, the historical rainfall data of the associated area comprises rainfall time of the associated area, a time axis of the rainfall time of the associated area is corrected according to the time difference to obtain corrected historical rainfall data of the associated area, and model training is carried out according to the corrected historical rainfall data of the associated area and the measured point historical water level data to obtain a water level prediction model;
and the prediction module is used for acquiring target measuring points, initial water level data of the target measuring points and latest rainfall data of the associated region, and predicting the water level data of the target measuring points according to the water level prediction model and by combining the initial water level data of the target measuring points and the latest rainfall data of the associated region.
In some optional embodiments, the data processing module comprises:
the time backward shifting adjusting unit is used for acquiring the processed rainfall time of the preselected area, gradually performing time backward shifting adjustment on the rainfall time according to a preset time interval, and associating the adjusted rainfall time with the measuring point historical water level data to obtain a plurality of association results;
and the maximum correlation degree acquisition unit is used for acquiring the maximum correlation degree according to a plurality of correlation results and taking the maximum correlation degree as the correlation degree of the correlation area and the measuring point historical water level data.
In some optional embodiments, the time-lag adjusting unit further comprises:
the weather data acquisition subunit is used for acquiring the processed weather data of the preselected area;
and the time length acquisition subunit is used for selecting the time length of time backward shift adjustment according to the weather data.
In some optional embodiments, the time-lag adjusting unit further comprises:
the judgment subunit is used for judging whether the adjusted rainfall time reaches the limit or not according to the maximum adjustment time length;
the first execution subunit is used for recording the adjusted current rainfall time and the current association degree corresponding to the adjusted current rainfall time when the adjusted rainfall time does not reach the limit;
and the time backward shifting adjustment subunit is used for performing time backward shifting adjustment on the adjusted current rainfall time according to a preset time interval until the maximum adjustment time length of the time backward shifting adjustment reaches the limit.
In summary, in the water level prediction system in the above embodiment of the present invention, the multiple preselected areas in the same water area system are used as the model training data, so as to expand the collection range of the model training data and improve the prediction accuracy of the model, further, the time difference between the water level value change time and the rainfall time of the preselected area is obtained, the time axis of the rainfall time of the associated area is corrected according to the time difference, so as to obtain the corrected historical rainfall data of the associated area, the model training is performed according to the corrected historical rainfall data of the associated area and the measured point historical water level data, so as to obtain the water level prediction model, the time difference between the rainfall time and the water level change time is considered, so as to further improve the prediction accuracy of the model, and solve the technical problem in the prior art that the accuracy of the water level data obtained by the water level prediction model is not high.
Furthermore, an embodiment of the present invention also proposes a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps of the method in the above-described embodiment.
Furthermore, an embodiment of the present invention also provides a data processing apparatus, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the steps of the method in the above-mentioned embodiment.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
Claims (10)
1. A water level prediction method, the method comprising:
acquiring a plurality of measuring points, acquiring historical water level data of the measuring points according to the measuring points, acquiring a plurality of preselected areas in the same water area system with the measuring points, and acquiring historical rainfall data of the preselected areas according to the preselected areas, wherein the historical water level data of the measuring points comprises water level value change time, and the historical rainfall data of the preselected areas comprises rainfall time of the preselected areas;
respectively carrying out data processing on the historical water level data of the measuring points and the historical rainfall data of the preselected area, carrying out dynamic association calculation on the processed historical water level data of the measuring points and the processed historical rainfall data of the preselected area, determining a plurality of associated areas related to the historical water level data of the measuring points according to association degrees, and determining the time difference between the change time of the water level value and the rainfall time of the preselected area;
obtaining historical rainfall data of the associated area, wherein the historical rainfall data of the associated area comprises rainfall time of the associated area, correcting a time axis of the rainfall time of the associated area according to the time difference to obtain corrected historical rainfall data of the associated area, and performing model training according to the corrected historical rainfall data of the associated area and the measured point historical water level data to obtain a water level prediction model;
and acquiring target measuring points, initial water level data of the target measuring points and latest rainfall data of the associated regions, and predicting the water level data of the target measuring points according to the water level prediction model and by combining the initial water level data of the target measuring points and the latest rainfall data of the associated regions.
2. The water level prediction method according to claim 1, wherein the step of performing dynamic correlation calculation on the processed measuring point historical water level data and the processed preselected area historical rainfall data comprises the following steps:
acquiring the processed rainfall time of the preselected area, gradually carrying out time backward shift adjustment on the rainfall time according to a preset time interval, and associating the adjusted rainfall time with the historical water level data of the measuring points to obtain a plurality of association results;
and acquiring the maximum correlation degree according to the plurality of correlation results, and taking the maximum correlation degree as the correlation degree of the correlation area and the measuring point historical water level data.
3. The water level prediction method according to claim 2, wherein in the step of gradually time-shifting the rainfall time according to a preset time interval:
the maximum adjustment time length for the time-shift adjustment is 240 hours.
4. The water level prediction method according to claim 2, wherein the step of taking the maximum correlation degree as the correlation degree of the correlation area and the station historical water level data is followed by the steps of:
and acquiring a time lag adjustment duration corresponding to the maximum correlation degree according to the maximum correlation degree, and acquiring the time difference according to the time lag adjustment duration corresponding to the maximum correlation degree.
5. The method for forecasting water level according to claim 2, wherein the step of gradually adjusting the rainfall time with a time shift according to a preset time interval is preceded by:
acquiring the processed weather data of the preselected area;
and selecting the time length of time backward shift adjustment according to the weather data.
6. The method for forecasting water level according to claim 2, wherein the step of gradually adjusting the rainfall time with a time shift according to a preset time interval is followed by:
judging whether the adjusted rainfall time reaches the limit or not according to the maximum adjustment time length;
if not, recording the adjusted current rainfall time and the current association degree corresponding to the adjusted current rainfall time;
and according to a preset time interval, carrying out time backward shift adjustment on the adjusted current rainfall time until the maximum adjustment time length of the time backward shift adjustment reaches the limit.
7. The water level prediction method of claim 1, wherein the step of predicting the water level data of the target measuring point by combining the initial water level data of the target measuring point and the latest rainfall data of the associated region comprises the following steps:
and acquiring the water level data of the target measuring point, collecting the water level data of the target measuring point in the water level prediction model, and updating the water level prediction model.
8. A water level prediction system, characterized in that the system comprises
The acquisition module is used for acquiring a plurality of measuring points, acquiring historical water level data of the measuring points according to the measuring points, acquiring a plurality of preselected areas in the same water area system with the measuring points, and acquiring historical rainfall data of the preselected areas according to the preselected areas, wherein the historical water level data of the measuring points comprise water level value change time, and the historical rainfall data of the preselected areas comprise rainfall time of the preselected areas;
the data processing module is used for respectively carrying out data processing on the measuring point historical water level data and the pre-selection area historical rainfall data, carrying out dynamic association calculation on the processed measuring point historical water level data and the processed pre-selection area historical rainfall data, determining a plurality of association areas related to the measuring point historical water level data according to association degrees, and determining the time difference between the water level value change time and the pre-selection area rainfall time;
the model training module is used for acquiring historical rainfall data of the associated area, the historical rainfall data of the associated area comprises rainfall time of the associated area, a time axis of the rainfall time of the associated area is corrected according to the time difference to obtain corrected historical rainfall data of the associated area, and model training is carried out according to the corrected historical rainfall data of the associated area and the measured point historical water level data to obtain a water level prediction model;
and the prediction module is used for acquiring target measuring points, initial water level data of the target measuring points and latest rainfall data of the associated region, and predicting the water level data of the target measuring points according to the water level prediction model and by combining the initial water level data of the target measuring points and the latest rainfall data of the associated region.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the water level prediction method according to any one of claims 1-7.
10. A data processing apparatus comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements a water level prediction method as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210076811.4A CN114091362B (en) | 2022-01-24 | 2022-01-24 | Water level prediction method, system, storage medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210076811.4A CN114091362B (en) | 2022-01-24 | 2022-01-24 | Water level prediction method, system, storage medium and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114091362A true CN114091362A (en) | 2022-02-25 |
| CN114091362B CN114091362B (en) | 2022-06-10 |
Family
ID=80309285
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210076811.4A Active CN114091362B (en) | 2022-01-24 | 2022-01-24 | Water level prediction method, system, storage medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114091362B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115240394A (en) * | 2022-09-22 | 2022-10-25 | 国网湖北省电力有限公司经济技术研究院 | Method and system for monitoring and early warning water level of accident oil pool of transformer substation |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007063849A (en) * | 2005-08-31 | 2007-03-15 | Toshiba Corp | Method of creating river water level prediction model, device for predicting river water level, and program for creating river water level prediction model |
| JP2019094640A (en) * | 2017-11-20 | 2019-06-20 | 日本無線株式会社 | Water level prediction method, water level prediction program and water level prediction device |
| CN109991685A (en) * | 2019-04-03 | 2019-07-09 | 北京市天元网络技术股份有限公司 | A kind of precipitation prediction technique and device based on more LSTM Model Fusions |
| CN111027193A (en) * | 2019-12-02 | 2020-04-17 | 浙江工业大学 | Short-term water level prediction method based on regression model |
| CN112990598A (en) * | 2021-03-31 | 2021-06-18 | 浙江禹贡信息科技有限公司 | Reservoir water level time sequence prediction method and system |
| CN113139700A (en) * | 2020-11-30 | 2021-07-20 | 中科三清科技有限公司 | River flow prediction method, device, equipment and storage medium |
| CN113379098A (en) * | 2021-04-16 | 2021-09-10 | 水利部珠江水利委员会技术咨询(广州)有限公司 | River interval dynamic flood peak analysis early warning method, system, equipment and medium |
| CN113780668A (en) * | 2021-09-15 | 2021-12-10 | 泰华智慧产业集团股份有限公司 | Urban ponding waterlogging prediction method and system based on historical data |
| CN113916318A (en) * | 2021-08-31 | 2022-01-11 | 福建枋洋水利投资发展有限公司 | Dam safety monitoring method based on water regime monitoring |
-
2022
- 2022-01-24 CN CN202210076811.4A patent/CN114091362B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007063849A (en) * | 2005-08-31 | 2007-03-15 | Toshiba Corp | Method of creating river water level prediction model, device for predicting river water level, and program for creating river water level prediction model |
| JP2019094640A (en) * | 2017-11-20 | 2019-06-20 | 日本無線株式会社 | Water level prediction method, water level prediction program and water level prediction device |
| CN109991685A (en) * | 2019-04-03 | 2019-07-09 | 北京市天元网络技术股份有限公司 | A kind of precipitation prediction technique and device based on more LSTM Model Fusions |
| CN111027193A (en) * | 2019-12-02 | 2020-04-17 | 浙江工业大学 | Short-term water level prediction method based on regression model |
| CN113139700A (en) * | 2020-11-30 | 2021-07-20 | 中科三清科技有限公司 | River flow prediction method, device, equipment and storage medium |
| CN112990598A (en) * | 2021-03-31 | 2021-06-18 | 浙江禹贡信息科技有限公司 | Reservoir water level time sequence prediction method and system |
| CN113379098A (en) * | 2021-04-16 | 2021-09-10 | 水利部珠江水利委员会技术咨询(广州)有限公司 | River interval dynamic flood peak analysis early warning method, system, equipment and medium |
| CN113916318A (en) * | 2021-08-31 | 2022-01-11 | 福建枋洋水利投资发展有限公司 | Dam safety monitoring method based on water regime monitoring |
| CN113780668A (en) * | 2021-09-15 | 2021-12-10 | 泰华智慧产业集团股份有限公司 | Urban ponding waterlogging prediction method and system based on historical data |
Non-Patent Citations (2)
| Title |
|---|
| KHOSROMOROVATI等: "A Machine learning framework to predict reverse flow and water level: A case study of Tonle Sap Lake", 《JOURNAL OF HYDROLOGY》 * |
| 万中英等: "鄱阳湖水位动态预测模型", 《江西师范大学学报(自然科学版)》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115240394A (en) * | 2022-09-22 | 2022-10-25 | 国网湖北省电力有限公司经济技术研究院 | Method and system for monitoring and early warning water level of accident oil pool of transformer substation |
| CN115240394B (en) * | 2022-09-22 | 2022-12-20 | 国网湖北省电力有限公司经济技术研究院 | Method and system for monitoring and early warning water level of accident oil pool of transformer substation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114091362B (en) | 2022-06-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Turner et al. | Complex relationship between seasonal streamflow forecast skill and value in reservoir operations | |
| Ribeiro et al. | Review and discussion of homogenisation methods for climate data | |
| CN113139700B (en) | River flow prediction method, device, equipment and storage medium | |
| Kjeldsen | The revitalised FSR/FEH rainfall-runoff method | |
| CN111665575B (en) | Medium-and-long-term rainfall grading coupling forecasting method and system based on statistical power | |
| JP2007205001A (en) | Discharge forecasting apparatus | |
| CN112686426B (en) | Incoming water quantity early warning method and system based on hydropower station basin key points | |
| CN114091362B (en) | Water level prediction method, system, storage medium and equipment | |
| CN110597873A (en) | Precipitation data estimation method, precipitation data estimation device, precipitation data estimation equipment and storage medium | |
| CN114611778B (en) | Reservoir water level early warning method and system based on warehousing flow | |
| CN110276477A (en) | A kind of Flood Forecasting Method based on layering Bayesian network and incremental learning | |
| CN110619433B (en) | Rapid selection method and system for power grid heavy rain numerical mode parameterization scheme | |
| Herath et al. | Evaluation of HEC-HMS model for water resources management in Maha Oya Basin in Sri Lanka | |
| Smith et al. | The hourly wind-bias adjusted precipitation data set from the Environment and Climate Change Canada automated surface observation network (2001–2019) | |
| CN113281827A (en) | Quality control method and device for precipitation meteorological elements, storage medium and equipment | |
| EP4318278A1 (en) | Method and apparatus for processing runoff abnormal abrupt-change data | |
| CN116186493A (en) | Meteorological forecasting method, device, equipment and medium based on numerical mode correction | |
| Chiew et al. | El Nino/Southern Oscillation and Australian rainfall and streamflow | |
| CN113961623A (en) | Rainfall characteristic index statistical method based on short-duration data | |
| CN113947007A (en) | Energy load prediction method, device and equipment | |
| CN114545529B (en) | Rainfall detection method, system, medium and equipment based on high-frequency lattice point | |
| CN114370611B (en) | Pipe network inflow and infiltration monitoring method and terminal | |
| CN117849908B (en) | Plum-entering and plum-exiting date prediction method and device in plum rainy season based on mode circular flow field | |
| CN113177702B (en) | Meteorological input data matching method and system | |
| CN117408391A (en) | Agricultural water prediction method, agricultural water prediction device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |