CN115879646A - Reservoir water level prediction method, device, medium and equipment - Google Patents
Reservoir water level prediction method, device, medium and equipment Download PDFInfo
- Publication number
- CN115879646A CN115879646A CN202310112898.0A CN202310112898A CN115879646A CN 115879646 A CN115879646 A CN 115879646A CN 202310112898 A CN202310112898 A CN 202310112898A CN 115879646 A CN115879646 A CN 115879646A
- Authority
- CN
- China
- Prior art keywords
- water level
- information
- reservoir water
- network
- reservoir
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 100
- 238000000034 method Methods 0.000 title claims abstract description 35
- 239000013598 vector Substances 0.000 claims description 33
- 238000012549 training Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 9
- 238000006073 displacement reaction Methods 0.000 claims description 8
- 125000004122 cyclic group Chemical group 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 230000007613 environmental effect Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 10
- 238000012360 testing method Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000000295 complement effect Effects 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 241000288105 Grus Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000013505 freshwater Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 239000003621 irrigation water Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of water level prediction and artificial intelligence, and provides a method, a device, a medium and equipment for predicting the water level of a reservoir, aiming at solving the problem that the accuracy of reservoir water level prediction is reduced because the change of the water level of the reservoir is a complex result of various environmental factors and is not fused with the characteristics on the spatial dimension. The method for predicting the reservoir water level comprises the steps of obtaining rainfall historical information, rainfall average historical information and reservoir water level historical information of a plurality of stations; predicting reservoir water level information at a plurality of moments in the future based on the acquired historical information and the trained reservoir water level prediction model; the reservoir water level prediction model comprises a convolution network, a continuity GRU network and a full-connection network; according to the reservoir water level prediction method, the low-level features of input data can be extracted from the time dimension and the space dimension, the extracted features are fused, and finally accurate prediction of the long-time water level is achieved.
Description
Technical Field
The invention belongs to the technical field of water level prediction and artificial intelligence, and particularly relates to a reservoir water level prediction method, a reservoir water level prediction device, a reservoir water level prediction medium and reservoir water level prediction equipment.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
Reservoir water level fluctuations are not only important in the planning, design and operation of fresh water reservoirs, i.e. in the areas of life, industry, hydropower, irrigation water supply and flood control, shipping, water quality and quantity improvement, but also in all hydraulic structures. Water level measurement or prediction of water level through a pre-estimation model are two direct ways to obtain reservoir management decisions. Compared with water level measurement, the prediction model can obtain future reservoir prediction results and is more economical, and therefore the prediction model is more preferable for predicting the future reservoir water level.
With the rise of artificial intelligence in recent years, a deep learning network has been considered as the best tool for modeling a complex environment, wherein a GRU is a variant of an LSTM network, the GRU network has a simpler structure and a smaller amount of parameters to be trained compared with the LSTM network, and can also solve the problem of long dependence in the RNN network, and has a better prediction effect on timing prediction. In 2019, the Xuan-Hien Le predicts the water levels of 1-4 time steps of the Vietnam Roche by using a GRU network, remarkable results are obtained, and the accuracy is 94% -96% when the prediction result is evaluated by using Nash coefficients. In 2021, the Xuan-HienLe predicts the water level in the future of 1 hour, 3 hours, 6 hours and 9 hours by using the GRU network again, and the prediction accuracy is reduced along with the delay of the prediction time.
The inventor finds that the GRU network used in the prior art can only predict the water level of 4 time steps at most, tests and attempts are not made on water level prediction at more moments, historical water level data is used, prior knowledge such as rainfall is not utilized, the network can only depend on data of the previous time point, so that relevant characteristics in time are extracted, and the variation of the reservoir water level is a complex result of various environmental factors and is not fused with characteristics in spatial dimension, so that the accuracy of reservoir water level prediction is reduced.
Disclosure of Invention
In order to solve the technical problems in the background art, the invention provides a reservoir water level prediction method, a reservoir water level prediction device, a reservoir water level prediction medium and reservoir water level prediction equipment, which can extract low-level features of input data from a time dimension and a space dimension, fuse the extracted features and finally realize accurate prediction of long-time water level.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention provides a reservoir water level prediction method in a first aspect.
In one or more embodiments, a reservoir level prediction method specifically includes the following steps:
acquiring rainfall historical information, rainfall average historical information and reservoir water level historical information of a plurality of stations;
predicting reservoir water level information at a plurality of moments in the future based on the acquired historical information and the trained reservoir water level prediction model;
the reservoir water level prediction model comprises a convolution network, a continuity GRU network and a full-connection network; the convolutional network is used for extracting time information and space information of the historical information; the continuity GRU network is used for predicting the states of a plurality of future time points based on the information extracted by the convolution network and combining the historical output state with the future output state for output; the full-connection network is used for fusing the historical output state and the future output state to obtain the reservoir water level information at a plurality of moments in the future.
As one implementation mode, samples for training a reservoir water level prediction model are arranged together by rainfall historical information, rainfall average historical information and reservoir water level historical information of a plurality of stations at a plurality of moments in sequence; one sample has two dimensions, one time information and the other dimension is rainfall information of a plurality of stations at the same time.
As an embodiment, the convolutional network is configured to: and finally, a pile vector is obtained by performing convolution operation, convolution displacement and the operation of replacing the first vector of the current convolution input by the last output result.
The convolution network firstly conducts padding operation on an input sample, and then convolution kernels conduct convolution on the first two moments of the sample and a vector of 0 complement at a first moment to obtain a first output vector; moving the convolution kernel one step towards the right, replacing a first input value of the position of the convolution kernel in the sample with a convolution result, and sending an output result at the previous moment and the other two vectors in the sample into the convolution kernel together to obtain a second output vector; and by analogy, replacing the first vector operation of the current convolution input by the convolution operation, the convolution displacement and the last output result to finally obtain a heap vector.
As an embodiment, the output of the continuation GRU network at the current time depends on the output at the previous time and the hidden state at the previous time.
As an embodiment, the continuation GRU network uses the Dropout method of variational reasoning, and for the same sequence, the same dropping method is used on the cyclic connection at all its times.
A second aspect of the present invention provides a reservoir level prediction apparatus.
In one or more embodiments, a reservoir level prediction apparatus specifically includes the following modules:
the historical information acquisition module is used for acquiring rainfall historical information, rainfall average historical information and reservoir water level historical information of a plurality of stations;
the reservoir water level prediction module is used for predicting reservoir water level information at a plurality of moments in the future based on the acquired historical information and the trained reservoir water level prediction model;
the reservoir water level prediction model comprises a convolution network, a continuity GRU network and a full connection network; the convolutional network is used for extracting time information and space information of the historical information; the continuity GRU network is used for predicting the states of a plurality of future time points based on the information extracted by the convolution network and combining the historical output state with the future output state for output; the full-connection network is used for fusing the historical output state and the future output state to obtain the reservoir water level information at a plurality of future moments.
As one implementation mode, samples for training a reservoir water level prediction model are arranged together by rainfall historical information, rainfall average historical information and reservoir water level historical information of a plurality of stations at a plurality of moments in sequence; one sample has two dimensions, one time information and the other dimension is rainfall information of a plurality of stations at the same time.
In one embodiment, the convolutional network is configured to: and finally, a pile vector is obtained by performing convolution operation, convolution displacement and the operation of replacing the first vector of the current convolution input by the last output result.
The convolution network firstly conducts padding operation on an input sample, and then convolution kernels conduct convolution on the first two moments of the sample and a vector of 0 complement at a first moment to obtain a first output vector; moving the convolution kernel one step towards the right, replacing a first input value of the position of the convolution kernel in the sample with a convolution result, and sending an output result at the previous moment and the other two vectors in the sample into the convolution kernel together to obtain a second output vector; and by analogy, replacing the first vector operation of the current convolution input by the convolution operation, the convolution displacement and the last output result to finally obtain a heap vector.
A third aspect of the invention provides a computer-readable storage medium.
In one or more embodiments, a computer-readable storage medium has stored thereon a computer program which, when executed by a processor, performs the steps in the reservoir level prediction method as described above.
A fourth aspect of the invention provides an electronic device.
In one or more embodiments, an electronic device includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the program to implement the steps of the reservoir level prediction method as described above.
Compared with the prior art, the invention has the beneficial effects that:
the convolution network provided by the invention can extract low-level features of input data from time dimension and space dimension, and reduces network layers and convolution parameters, the output of a continuous GRU network can be divided into the output of a historical time period and a prediction time period, the output of the historical time period is the same as that of the traditional GRU network, the output of the historical time period depends on collected historical data, the output of the future time period depends on the output result of the network at the last moment and the output of a hidden layer thereof, and the fully-connected network carries out further spatial fusion and features on the features extracted from the continuous GRU, thereby finally realizing the prediction of water level after a longer time.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
FIG. 1 is a flow chart of a reservoir water level prediction method according to an embodiment of the present invention;
FIG. 2 is a training sample construction flow diagram of an embodiment of the present invention;
FIG. 3 is a schematic diagram of a reservoir water level prediction model according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a convolutional network of an embodiment of the present invention;
FIG. 5 is a schematic diagram of a continuation GRU network model result of an embodiment of the present invention;
FIG. 6 is a schematic diagram of a fully connected network according to an embodiment of the present invention;
FIG. 7 is a comparison of predicted results and actual water levels for an embodiment of the present invention.
Detailed Description
The invention is further described with reference to the following figures and examples.
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. 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.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an", and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
Interpretation of terms:
padding operation: for filling the area around the image so that the output feature map reaches the desired size.
Example one
Referring to fig. 1, the present embodiment provides a reservoir water level prediction method, which specifically includes the following steps:
step 1: and acquiring rainfall historical information, rainfall average historical information and reservoir water level historical information of a plurality of stations.
And 2, step: and predicting the reservoir water level information at a plurality of moments in the future based on the acquired historical information and the trained reservoir water level prediction model.
The reservoir water level prediction model comprises a convolution network, a continuity GRU network and a full-connection network; the convolution network is used for extracting time information and space information of the historical information; the continuity GRU network is used for predicting the states of a plurality of future time points based on the information extracted by the convolution network and combining the historical output state with the future output state for output; the full-connection network is used for fusing the historical output state and the future output state to obtain the reservoir water level information at a plurality of moments in the future.
In the specific implementation process, samples for training a reservoir water level prediction model are sequentially arranged together by rainfall historical information, rainfall average historical information and reservoir water level historical information of a plurality of stations at a plurality of moments; one sample comprises two pieces of information, one is time information, and the other is rainfall information of a plurality of stations at the same time.
Specifically, rainfall data, average values and reservoir water level data of a plurality of stations in 10 years of reservoir advance are collected. Further, data combination is performed, and missing data is supplemented by the average value of the correlation data at the upper and lower time points. Further, all data before 2020 is divided into a training database, and data after 2020 is divided into a testing database. Further, the data are respectively shaped, and the process is as follows: and setting the dimensionality of the data to be 10, and representing the rainfall information, the rainfall average value information and the reservoir water level information of 8 stations respectively. Further, a time window of 56 is set, and data of 56 time instants are arranged together in sequence to form a sample, so that one sample has 2 dimensions, for example, 56,10]Wherein 56 represents data of 56 continuous moments in a sample, 10 represents rainfall information of 8 stations, rainfall average value and historical reservoir level information, wherein 1-8 of 10 represents rainfall information of 8 stations, 9 represents rainfall average value, and 10 represents historical reservoir level information. The window shift step size is set to 3, and a new step size is generated for every sample point shifted by 3 time instants in all data. The whole process is shown in fig. 2, where the time window represents the time window before shifting, and sample 1 is generated, and the dotted line represents the time window after shifting, and sample 2 is generated. Further, the training database and the testing database are respectively operated according to the setting to obtain a training set and a testing set, and the training set and the testing set are used for training and testing subsequently designed models. Further, each dimension of the data set is normalized by the formula
Right side of formula->
Represents the original data, < > is selected>
Represents the minimum data->
For maximum data, left side of the formula->
Is normalized data.
Then, a network model for predicting the water level is structurally designed, and a schematic structural diagram is shown in fig. 3. The method comprises the steps that a convolution model starts from two dimensions of time and space, low-level features of input historical data are extracted, a continuity GRU network is used for taking the output of the convolution model as input, the multi-step feature extraction task of a historical time period and a future time period is completed, the output of the continuity GRU is taken as input by a full-connection network, feature information of the historical time period and the future time period is fused, feature extraction is further conducted, and finally the multi-step prediction task of a reservoir water level is completed.
Specifically, the convolution network firstly conducts padding operation on an input sample, and then a convolution kernel conducts convolution on two previous moments of the sample and a vector of 0 complement at a first moment to obtain a first output vector; moving the convolution kernel one step towards the right, replacing a first input value of the position of the convolution kernel in the sample with a convolution result, and sending an output result at the previous moment and the other two vectors in the sample into the convolution kernel together to obtain a second output vector; by analogy, the convolution operation, the convolution displacement and the last output result are used for replacing the first vector operation of the current convolution input, and finally a two-dimensional vector is obtained, wherein the length of the first dimension of the vector is the length of the moment and represents the time length to be predicted; the second dimension, which is 8 in length, represents the key features of the model extraction.
Convolution model structure as shown in fig. 4, this model is different from the conventional convolution model in that the size of the convolution kernel is set to 3, the step size is set to 1, the number of channels is set to 10, and the number is also set to 10. Firstly carrying out padding operation on an input sample, then carrying out convolution on the first two moments of the sample and a vector of a complement 0 at a moment 1 by a convolution kernel to obtain an output vector
The operation can be fusedFeature information in a spatial dimension. The convolution kernel is then shifted one step to the right and the convolution result is ≥ er>
The first input value which replaces the position of the convolution kernel in the sample->
Then the result output at the previous time is compared with ^ in the sample>
、/>
The vectors are fed into a convolution kernel together to obtain an output vector->
This operation may fuse feature information in the time dimension. And by analogy, the operation of substituting the first vector of the current convolution input by the convolution operation, the convolution displacement and the last output result is carried out, and finally a pile vector is obtained>
The length of the heap vector is 56 and the number of channels is 10. The convolution model has the advantages that the time information and the space information of the input samples are fused at the same time, and the time convolution can be realized without constructing a plurality of network layers and convolution kernels.
The continuation GRU network model results are shown in fig. 5, with the output of the convolution model being fed as input into the continuation GRU. The output at time t depends on the input at time t and the masking state at time t-1. Unlike conventional GRUs, the continuation GRU is a multi-step model that predicts states at 56 moments in the future using states at the first 56 moments, at historical data t 1 -t 56 The time, the output at the current time depends on the state of the previous time; and at t 57 -t 112 At a time, the output of the model at the current time depends on the output at the previous time and the hidden state at the previous time. Finally, the output of the model is the historical time and the future timeIs combined with the hidden state of (1). Compared with the traditional GUP, the continuity GPU can predict the states of a plurality of time points in the future, and the historical output state is combined with the future output state, so that the state data of a longer time can be seen, and the accurate prediction of the water level of a plurality of moments in the future can be facilitated. To prevent the model from over-fitting, the network uses the Dropout method of variational reasoning, which applies the same dropping method on the cyclic connections at all its times for the same sequence. Compared with the common dropout, the memory capacity of the recurrent neural network can be ensured not to decline, and important information can be ensured not to be lost.
As shown in fig. 6, the output sequence of the continuous neural network is input into a fully connected network containing 56 neurons, and the output is the water level prediction results of the reservoir at a plurality of moments 56 moments (7 days) in the future. The fully-connected neural network mainly has the function of fusing the features extracted by the continuous GRU network for the historical time period and the features extracted for the future time period, thereby completing the information extraction on the input feature time and space, and finally completing the reservoir water level prediction task at the future 56 moments.
Next, the model is trained by using a training set, and one sample in the training set contains rainfall information, average rainfall information and water level information of 8 stations of the reservoir at the past 56 times. The hyperparameter is set prior to training, the training round is set to 100, the initial training parameters are set to 0.001, and the gradient cutoff is set to 15, the loss function uses the mean square error loss function (MSE) with the formula
In the formula->
Represents the output result of the model, is asserted>
Represents the true value of the sample, is present>
Batches representing samplesSize. In the training process, an Adam optimizer is used, when the loss of the model is not reduced in 5 continuous rounds, the learning rate is set to be 0.1 time of the original learning rate, and when the loss function is not reduced in 20 continuous rounds, the network terminates the training.
And then, testing the trained model by using the test set, evaluating the test result, sending the test set and the training set into the model when the evaluation result meets the preset condition, and finely adjusting the model parameters again to finally obtain the model required in actual use. And if the evaluation result does not meet the expectation, the model is trained, tested and evaluated again until the evaluation result meets the expectation.
And finally, deploying the model into a server, transmitting the data in the database into the deployed model by the server, and returning the result to the design front-end interface after the result is calculated by the model. The model is tested by using data after 2020, and the prediction result is compared with the real water level, and the comparison result is shown in fig. 7.
Example two
The embodiment provides a reservoir water level prediction device, which specifically comprises the following modules:
the historical information acquisition module is used for acquiring rainfall historical information, rainfall average historical information and reservoir water level historical information of a plurality of stations;
the reservoir water level prediction module is used for predicting reservoir water level information at a plurality of moments in the future based on the acquired historical information and the trained reservoir water level prediction model;
the reservoir water level prediction model comprises a convolution network, a continuity GRU network and a full-connection network; the convolutional network is used for extracting time information and space information of the historical information; the continuity GRU network is used for predicting the states of a plurality of future time points based on the information extracted by the convolution network and combining the historical output state with the future output state for output; the full-connection network is used for fusing the historical output state and the future output state to obtain the reservoir water level information at a plurality of moments in the future.
It should be noted that, each module in the present embodiment corresponds to each step in the first embodiment one to one, and the specific implementation process is the same, which is not described herein again.
EXAMPLE III
The present embodiment provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps in the reservoir level prediction method as described above.
Example four
The present embodiment provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the program, the steps in the reservoir level prediction method as described above are implemented.
The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A reservoir water level prediction method is characterized by comprising the following steps:
acquiring rainfall historical information, rainfall average historical information and reservoir water level historical information of a plurality of stations;
predicting reservoir water level information at a plurality of moments in the future based on the acquired historical information and the trained reservoir water level prediction model;
the reservoir water level prediction model comprises a convolution network, a continuity GRU network and a full connection network; the convolutional network is used for extracting time information and space information of the historical information; the continuity GRU network is used for predicting the states of a plurality of future time points based on the information extracted by the convolution network and combining the historical output state with the future output state for output; the full-connection network is used for fusing the historical output state and the future output state to obtain the reservoir water level information at a plurality of moments in the future.
2. The reservoir water level prediction method according to claim 1, wherein samples for training the reservoir water level prediction model are arranged in order of rainfall history information, rainfall average history information, and reservoir water level history information of a plurality of sites at a plurality of times; one sample has two dimensions, one time information and the other dimension is rainfall information of a plurality of stations at the same time.
3. The reservoir water level prediction method of claim 1, wherein the convolutional network is configured to: and finally, a pile vector is obtained by performing convolution operation, convolution displacement and the operation of replacing the first vector of the current convolution input by the last output result.
4. The reservoir level prediction method of claim 1, wherein the output of the continuation GRU network at the current time depends on the output at the previous time and the hidden state at the previous time.
5. The reservoir water level prediction method of claim 1, wherein the continuation GRU network uses a Dropout method of variational reasoning, employing the same dropping method on cyclic connections at all its times for the same sequence.
6. A reservoir water level predicting apparatus, comprising:
the historical information acquisition module is used for acquiring rainfall historical information, rainfall average historical information and reservoir water level historical information of a plurality of stations;
the reservoir water level prediction module is used for predicting reservoir water level information at a plurality of moments in the future based on the acquired historical information and the trained reservoir water level prediction model;
the reservoir water level prediction model comprises a convolution network, a continuity GRU network and a full-connection network; the convolution network is used for extracting time information and space information of the historical information; the continuity GRU network is used for predicting states of a plurality of time points in the future based on information extracted by the convolution network and outputting a historical output state and a future output state in a combined manner; the full-connection network is used for fusing the historical output state and the future output state to obtain the reservoir water level information at a plurality of moments in the future.
7. The reservoir level prediction apparatus according to claim 6, wherein samples for training a reservoir level prediction model are arranged in order of rainfall history information, rainfall average history information, and reservoir level history information of a plurality of sites at a plurality of times; one sample has two dimensions, namely time information and rainfall information of a plurality of stations at the same time.
8. The reservoir water level prediction device of claim 6, wherein the convolutional network is configured to: and finally, a pile vector is obtained by performing convolution operation, convolution displacement and the operation of replacing the first vector of the current convolution input by the last output result.
9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the reservoir water level prediction method according to any one of claims 1 to 5.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the reservoir level prediction method according to any one of claims 1 to 5 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310112898.0A CN115879646B (en) | 2023-02-15 | 2023-02-15 | Reservoir water level prediction method, device, medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310112898.0A CN115879646B (en) | 2023-02-15 | 2023-02-15 | Reservoir water level prediction method, device, medium and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115879646A true CN115879646A (en) | 2023-03-31 |
| CN115879646B CN115879646B (en) | 2023-11-07 |
Family
ID=85761113
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310112898.0A Active CN115879646B (en) | 2023-02-15 | 2023-02-15 | Reservoir water level prediction method, device, medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115879646B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN110991776A (en) * | 2020-03-04 | 2020-04-10 | 浙江鹏信信息科技股份有限公司 | Method and system for realizing water level prediction based on GRU network |
| CN111242344A (en) * | 2019-12-11 | 2020-06-05 | 大连海事大学 | Intelligent water level prediction method based on cyclic neural network and convolutional neural network |
| CN112561191A (en) * | 2020-12-22 | 2021-03-26 | 北京百度网讯科技有限公司 | Prediction model training method, prediction method, device, apparatus, program, and medium |
| CN113947259A (en) * | 2021-11-09 | 2022-01-18 | 吉林大学 | Method for predicting vehicle speeds of drivers in different styles based on GRU neural network |
| CN115034497A (en) * | 2022-06-27 | 2022-09-09 | 武汉理工大学 | Multi-site daily water level prediction method and device, electronic equipment and computer medium |
| CN115186857A (en) * | 2022-03-24 | 2022-10-14 | 国家能源集团西藏尼洋河流域水电开发有限公司 | Neural network reservoir water level prediction method based on ensemble learning |
| CN115238855A (en) * | 2022-05-23 | 2022-10-25 | 北京邮电大学 | Completion method of time sequence knowledge graph based on graph neural network and related equipment |
| CN115310536A (en) * | 2022-08-06 | 2022-11-08 | 福建中锐网络股份有限公司 | Reservoir water level prediction early warning method based on neural network and GCN deep learning model |
| CN115310532A (en) * | 2022-08-04 | 2022-11-08 | 福建中锐网络股份有限公司 | Basin multipoint prediction early warning method based on space-time association mixed deep learning model |
-
2023
- 2023-02-15 CN CN202310112898.0A patent/CN115879646B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN111242344A (en) * | 2019-12-11 | 2020-06-05 | 大连海事大学 | Intelligent water level prediction method based on cyclic neural network and convolutional neural network |
| CN110991776A (en) * | 2020-03-04 | 2020-04-10 | 浙江鹏信信息科技股份有限公司 | Method and system for realizing water level prediction based on GRU network |
| CN112561191A (en) * | 2020-12-22 | 2021-03-26 | 北京百度网讯科技有限公司 | Prediction model training method, prediction method, device, apparatus, program, and medium |
| CN113947259A (en) * | 2021-11-09 | 2022-01-18 | 吉林大学 | Method for predicting vehicle speeds of drivers in different styles based on GRU neural network |
| CN115186857A (en) * | 2022-03-24 | 2022-10-14 | 国家能源集团西藏尼洋河流域水电开发有限公司 | Neural network reservoir water level prediction method based on ensemble learning |
| CN115238855A (en) * | 2022-05-23 | 2022-10-25 | 北京邮电大学 | Completion method of time sequence knowledge graph based on graph neural network and related equipment |
| CN115034497A (en) * | 2022-06-27 | 2022-09-09 | 武汉理工大学 | Multi-site daily water level prediction method and device, electronic equipment and computer medium |
| CN115310532A (en) * | 2022-08-04 | 2022-11-08 | 福建中锐网络股份有限公司 | Basin multipoint prediction early warning method based on space-time association mixed deep learning model |
| CN115310536A (en) * | 2022-08-06 | 2022-11-08 | 福建中锐网络股份有限公司 | Reservoir water level prediction early warning method based on neural network and GCN deep learning model |
Non-Patent Citations (6)
| Title |
|---|
| ZIQIAN KONG，BAOPING TANG，，，YAN HAN: "Condition monitoring of wind turbines based on spatio-temporal fusion of SCADA data by convolutional neural networks and gated recurrent units", 《RENEWABLE ENERGY》, vol. 146, pages 760 - 768, XP085904508, DOI: 10.1016/j.renene.2019.07.033 * |
| 刘惟飞，陈兵，余周: "基于GRU-BP组合模型的湖泊水位预测方法探索", 《中国农村水利水电》, no. 11 * |
| 刘惟飞，陈兵，余周: "基于门控循环单元—支持向量回归组合模型的湖泊水位预测方法探索", 《科学技术与工程》, vol. 22, no. 33 * |
| 许国艳;周星熠;司存友;胡文斌;刘凡;: "基于GRU和LightGBM特征选择的水位时间序列预测模型", 计算机应用与软件, no. 02 * |
| 郭燕;赖锡军;: "基于长短时记忆神经网络的鄱阳湖水位预测", 湖泊科学, no. 03 * |
| 黄玲;郭亨聪;张荣辉;吴建平;: "人机混驾环境下基于LSTM的无人驾驶车辆换道行为模型", 《中国公路学报》, no. 07 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115879646B (en) | 2023-11-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110852420B (en) | Garbage classification method based on artificial intelligence | |
| Jain et al. | Application of ANN for reservoir inflow prediction and operation | |
| CN114492211B (en) | Residual oil distribution prediction method based on autoregressive network model | |
| US20220108185A1 (en) | Inverse and forward modeling machine learning-based generative design | |
| Qian et al. | Physics informed data driven model for flood prediction: Application of deep learning in prediction of urban flood development | |
| CN112733997A (en) | Hydrological time series prediction optimization method based on WOA-LSTM-MC | |
| CN114330101A (en) | Slope earthquake slip prediction method and system based on artificial neural network | |
| CN115935834A (en) | History fitting method based on deep autoregressive network and continuous learning strategy | |
| CN110895729A (en) | Prediction method for construction period of power transmission line engineering | |
| CN115545334B (en) | Land utilization type prediction method and device, electronic equipment and storage medium | |
| CN116681945A (en) | Small sample class increment recognition method based on reinforcement learning | |
| CN110969249A (en) | Production well yield prediction model establishing method, production well yield prediction method and related device | |
| CN115879646A (en) | Reservoir water level prediction method, device, medium and equipment | |
| CN116910534A (en) | Space-time intelligent prediction method and device for ocean environmental elements in different sea areas | |
| CN117172355A (en) | Sea surface temperature prediction method integrating space-time granularity context neural network | |
| CN115860272A (en) | Reservoir multi-time point intelligent water level prediction method and system based on deep learning | |
| CN115459982A (en) | Power network false data injection attack detection method | |
| CN115204463A (en) | Residual service life uncertainty prediction method based on multi-attention machine mechanism | |
| CN113821974B (en) | Engine residual life prediction method based on multiple fault modes | |
| CN112800670B (en) | Multi-target structure optimization method and device for driving cognitive model | |
| Cornelio et al. | Transfer learning with multiple aggregated source models in unconventional reservoirs | |
| Lanjekar et al. | Application of deep machine learning techniques in oil production forecasting | |
| CN117172113A (en) | Method, system, equipment and medium for predicting rotary steerable drilling well track | |
| CN115952876A (en) | Machine learning model reliability assessment method facing engineering application | |
| KR20210064794A (en) | Method and apparatus for determining performance degradation using prediction uncertainty |
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 |