CN111753965A - Deep learning-based river flow automatic editing method and system - Google Patents
Deep learning-based river flow automatic editing method and system Download PDFInfo
- Publication number
- CN111753965A CN111753965A CN202010619756.XA CN202010619756A CN111753965A CN 111753965 A CN111753965 A CN 111753965A CN 202010619756 A CN202010619756 A CN 202010619756A CN 111753965 A CN111753965 A CN 111753965A
- Authority
- CN
- China
- Prior art keywords
- flow
- sample
- model
- deep learning
- time
- 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.)
- Pending
Links
Images
Classifications
-
- 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
- G06N3/045—Combinations of 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- 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
Abstract
The invention discloses a river flow automatic reorganizing method and system based on deep learning, which comprises the following steps: selecting an input factor-flow sample with a preset time period from a historical hydrological big data sample library; dividing the selected input factor-flow sample into a training sample, a verification sample and a test sample; constructing a deep learning compilation model through training samples, verifying the hyper-parameters of a sample adjusting model, and finally evaluating the model precision of a test sample; and inputting the input factors into the model based on the trained deep learning compilation model, and calculating in real time to obtain the flow. According to the method, on the basis of fully utilizing hydrological duration time-sequence big data samples with good consistency, reliability and continuity and developing physical cause analysis of hydrological station flow, a deep learning method is utilized to establish a flow real-time calculation model of the station, and automatic flow sorting is realized; the method does not need to invest any facility equipment, and has the advantages of high automation degree, strong timeliness, higher precision and the like.
Description
Technical Field
The invention relates to the technical field of data reorganization, in particular to a river flow automatic reorganization method and system based on deep learning.
Background
River flow is one of the most important hydrological factors, and in general, the flow can be indirectly converted by contrasting the water level flow relation with the water level; therefore, the stable water level-flow relationship as shown in fig. 1 is an important factor for rapidly and accurately acquiring the flow data. Influenced by complex water flow conditions (such as flood fluctuation, downstream jacking and the like) and human activities (such as building various wading buildings in a test river reach), the water level and flow relationship becomes very complex and unstable, as shown in fig. 2. In order to control the flow change process and the marshalling line, hydrologic testers need to carry out a large amount of field test work, which not only greatly increases the investment of manpower and material resources, but also improves the complexity of the internal marshalling line, and the timeliness of the hydrologic real-time marshalling is difficult to guarantee.
In order to solve the problems, a large number of hydrological mechanisms utilize various online flow measuring methods and adopt a continuous flow measuring process line method to realize online flow monitoring, so that a good application effect is obtained to a certain extent. But the online flow measurement also has the defects of large early investment, long specific rate fixed period, large operation and maintenance workload and the like; for some cross sections, the cross sections are comprehensively influenced by instrument precision, instrument installation representativeness and the like, even if an online flow measurement method is adopted, the precision cannot be put into operation because the precision cannot meet the precision requirement, and large measurement times still need to be manually arranged to carry out line arrangement. The hydrology industry has a strict regulation system, the test result has high continuity and reliability, and the test result also has excellent consistency when the test river reach is not influenced by human activities. In the face of hydrologic duration big data samples, how to fully mine the value of the hydrologic duration big data samples is necessary to establish a hydrologic deep learning model based on big data on the basis of physical cause analysis and solve the problem of automatic flow reorganization under the condition of complex water flow by applying the model.
The current flow reorganization method can be classified into three types: the first type is a traditional whole editing method, and plug flow is carried out by adopting a water level flow relation curve determined manually; the second type is an online whole editing method, which carries out plug flow by utilizing a continuous actual measurement flow process line method for the real-time flow monitored online; the third type is a formula editing method, wherein a flow calculation formula is preset in a software system, and the flow is calculated in real time by using the formula.
The three methods have certain defects or limitations: the traditional whole editing method is a reference method of other methods, but the method has low timeliness, large field work load and low automation degree; the online whole editing method depends on an online flow measuring method, and has the risks of large investment, incapability of putting into production due to the influence of multiple factors on the precision and the like; the formula method integer compilation method needs to preset various plug flow formulas, and has a short board with large application limitation.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a river flow automatic editing method and system based on deep learning.
The invention discloses a river flow automatic reorganizing method based on deep learning, which comprises the following steps:
selecting an input factor-flow sample with a preset time period from a historical hydrological big data sample library; wherein the input factors comprise the water level of the station, the water level of an upstream station, the water level of a downstream station, rainfall, evaporation and the like;
dividing the selected input factor-flow sample into a training sample, a verification sample and a test sample;
constructing a deep learning compilation model through the training samples, verifying the hyper-parameters of the sample adjusting model, and testing the sample to finally evaluate the model precision;
and inputting the input factors into the model based on the trained deep learning compilation model, and calculating in real time to obtain the flow.
As a further improvement of the invention, the step of the period of the input factor-flow sample is selected from the historical hydrologic big data sample library and is at least 30 min.
As a further improvement of the invention, after the deep learning compilation model is trained, parametrized and evaluated, if the error is lower than a preset value, the training is finished.
As a further improvement of the invention, the deep learning compilation model is an LSTM deep learning compilation model.
As a further improvement of the present invention, the calculating the flow rate in real time includes:
NET deploys the researched model to the production environment, and develops deep learning compilation software; and calculating the flow in real time by using the real-time input factor and the input factor of the previous n time periods, and using the flow for online flow monitoring, real-time flood forecasting and automatic editing.
The invention also discloses a deep learning-based river flow automatic reorganization system, which comprises:
the selection module is used for selecting an input factor-flow sample with a preset time period from the historical hydrologic big data sample library; wherein the input factors comprise the water level of the station, the water level of an upstream station, the water level of a downstream station, rainfall, evaporation and the like;
the classification module is used for dividing the selected input factor-flow sample into a training sample, a verification sample and a test sample;
the training module is used for constructing a deep learning compilation model through the training samples, verifying the hyper-parameters of the sample adjusting model and testing the sample to finally evaluate the model precision;
and the calculation module is used for inputting the input factors into the model based on the trained deep learning compilation model and calculating in real time to obtain the flow.
As a further improvement of the invention, in the selection module, the step of the period of the input factor-flow sample selected from the historical hydrologic big data sample library is at least 30 min.
As a further improvement of the present invention, in the training module, after the deep learning compilation model is trained, parametered and evaluated, if the error is lower than a preset value, it indicates that the training is completed.
As a further improvement of the invention, the deep learning compilation model is an LSTM deep learning compilation model.
As a further improvement of the present invention, the computing module is specifically configured to:
NET deploys the researched model to the production environment, and develops deep learning compilation software; and calculating the flow in real time by using the real-time input factor and the input factor of the previous n time periods, and using the flow for online flow monitoring, real-time flood forecasting and automatic editing.
Compared with the prior art, the invention has the beneficial effects that:
according to the method, on the basis of fully utilizing hydrological duration time-sequence big data samples with good consistency, reliability and continuity and developing physical cause analysis of hydrological station flow, a deep learning method is utilized to establish a flow real-time calculation model of the station, and automatic flow sorting is realized; the method does not need to invest any facility equipment, and has the advantages of high automation degree, strong timeliness, higher precision and the like.
Drawings
FIG. 1 is a water level flow rate diagram;
FIG. 2 is a water level flow rate relationship diagram affected by hydraulics;
FIG. 3 is a flow chart of a deep learning-based river discharge automatic editing method according to an embodiment of the present invention;
FIG. 4 is a model structure diagram of a deep learning compilation model according to an embodiment of the present invention;
fig. 5 is a frame diagram of an automatic river discharge compilation system based on deep learning according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
The invention is described in further detail below with reference to the attached drawing figures:
the invention provides a river flow automatic integer editing method based on an LSTM (long-short memory recurrent neural network) deep learning integer editing model, which is used for flow online monitoring, real-time flood reporting and automatic integer editing. The basic principle is as follows:
the hydrology industry has strict quality assurance measures, and the test result has good reliability, continuity and consistency. Through the collection of long-term basic data, a large amount of historical data is accumulated, and a hydrologic big data sample library is formed. The flow of the hydrological station is influenced by various factors, the flow change of the hydrological station can be influenced by various factors such as the water level of the hydrological station, the water level of an upstream station, the water level of a downstream station, rainfall, evaporation and the like, and the factors are collectively called as input factors; since the flow rate is a continuously variable physical quantity, the flow rate at time t is not only related to the input factor at time t, but also related to each input factor at the previous n times. The selection of the input factors and the length of n time need to be obtained by adopting an optimization method based on big data sample data.
As shown in fig. 3 and 4, the invention provides a river flow automatic editing method based on deep learning, which comprises the following steps:
the input factors comprise the water level of the station, the water level of the upstream station, the water level of the downstream station, rainfall and evaporation; the delta t can be set as required and can be set to be 30min, 60min and the like; the larger the number of samples is, the better the representativeness is, the higher the model precision is;
the proportion of the training samples, the verification samples and the test samples can be selected according to actual requirements, for example, the proportion of the training samples, the verification samples and the test samples is 6:2:2 or other suitable proportions. The training sample, the verification sample and the test sample respectively comprise a plurality of groups of input factors at the time t, input factors at n time (30min) before the time t and flow at the time t, the input factors are used as input of subsequent model training, and the flow at the time t is used as output of the subsequent model training, so that the training, the verification and the test of the model are realized.
Step 3, selecting an LSTM deep learning compilation model, constructing the deep learning compilation model through training samples, verifying the hyper-parameters of the sample adjustment model, and finally evaluating the model precision of the test samples; wherein the content of the first and second substances,
after the deep learning and editing model is trained, parametered and evaluated, if the error is lower than a preset value (such as 0.05%), the training is finished.
Step 4, inputting input factors into the model based on the trained deep learning compilation model, and calculating in real time to obtain flow; wherein, specifically include:
NET deploys the researched model to the production environment, and develops deep learning compilation software; and calculating the flow in real time by using the real-time input factor and the input factor of the previous n time periods, and using the flow for online flow monitoring, real-time flood forecasting and automatic editing.
Furthermore, the flow calculated at the current moment is stored in a historical hydrological big data sample library and can be further used for optimizing a deep learning compilation model.
Example (b):
as shown in figure 4 of the drawings,
selecting a time period n which is 30min, and monitoring once every 5 min;
inputting input factors of t-5min (the current station water level, the current upstream station water level, the current downstream station water level, the current rainfall and the current evaporation), the t-30min (the current station water level, the current upstream station water level, the current downstream station water level, the rainfall and the evaporation at the time of 5 min), and the t-30min into the trained deep learning integer model to obtain the flow at the current time t, wherein the input factors are used for online flow monitoring, real-time flood reporting and automatic integer compiling.
As shown in fig. 5, the present invention provides an automatic river flow editing system based on deep learning, which comprises:
the selection module is used for realizing the step 1 of automatically arranging and compiling the river flow;
the classification module is used for realizing the step 2 of automatically arranging and editing the river flow;
the training module is used for realizing the step 3 of automatically arranging and weaving the river flow;
and the calculation module is used for realizing the step 4 of automatically arranging and compiling the river flow.
Furthermore, the flow calculated at the current moment is stored in a historical hydrological big data sample library and can be further used for optimizing a deep learning compilation model.
Example (b):
as shown in figure 4 of the drawings,
selecting a time period n which is 30min, and monitoring once every 5 min;
inputting input factors of t-5min (the current station water level, the current upstream station water level, the current downstream station water level, the current rainfall and the current evaporation), the t-30min (the current station water level, the current upstream station water level, the current downstream station water level, the rainfall and the evaporation at the time of 5 min), and the t-30min into the trained deep learning integer model to obtain the flow at the current time t, wherein the input factors are used for online flow monitoring, real-time flood reporting and automatic integer compiling.
The invention has the advantages that:
according to the method, on the basis of fully utilizing hydrological duration time-sequence big data samples with good consistency, reliability and continuity and developing physical cause analysis of hydrological station flow, a deep learning method is utilized to establish a flow real-time calculation model of the station, and automatic flow sorting is realized; the method does not need to invest any facility equipment, and has the advantages of high automation degree, strong timeliness, higher precision and the like.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes will occur to 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 river flow automatic editing method based on deep learning is characterized by comprising the following steps:
selecting an input factor-flow sample with a preset time period from a historical hydrological big data sample library; wherein the input factors comprise the water level of the station, the water level of the upstream station, the water level of the downstream station, rainfall and evaporation;
dividing the selected input factor-flow sample into a training sample, a verification sample and a test sample;
constructing a deep learning compilation model through the training samples, verifying the hyper-parameters of the sample adjusting model, and testing the sample to finally evaluate the model precision;
and inputting the input factors into the model based on the trained deep learning compilation model, and calculating in real time to obtain the flow.
2. The method of claim 1, wherein the step of selecting the input factor-flow sample period from the historical hydrographic big data sample library is at least 30 min.
3. The method as claimed in claim 1, wherein the deep learning compilation model is trained, parametered and evaluated, and if the error is lower than a predetermined value, the training is completed.
4. The method of claim 1, wherein the deep learning compilation model is an LSTM deep learning compilation model.
5. The method for automatically organizing river discharge according to claim 1, wherein the calculating the discharge in real time comprises:
NET deploys the researched model to the production environment, and develops deep learning compilation software; and calculating the flow in real time by using the real-time input factor and the input factor of the previous n time periods, and using the flow for online flow monitoring, real-time flood forecasting and automatic editing.
6. The utility model provides an automatic reorganization system of river flow based on deep study which characterized in that includes:
the selection module is used for selecting an input factor-flow sample with a preset time period from the historical hydrologic big data sample library; wherein the input factors comprise the water level of the station, the water level of the upstream station, the water level of the downstream station, rainfall and evaporation;
the classification module is used for dividing the selected input factor-flow sample into a training sample, a verification sample and a test sample;
the training module is used for constructing a deep learning compilation model through the training samples, verifying the hyper-parameters of the sample adjusting model and testing the sample to finally evaluate the model precision;
and the calculation module is used for inputting the input factors into the model based on the trained deep learning compilation model and calculating in real time to obtain the flow.
7. The system of claim 6, wherein the period step of selecting the input factor-flow sample from the historical hydrographic big data sample library in the selection module is at least 30 min.
8. The system of claim 6, wherein the training module is configured to train, adjust parameters and evaluate the deep learning compilation model, and if the error is lower than a predetermined value, the training is complete.
9. The system of claim 6, wherein the deep learning compilation model is an LSTM deep learning compilation model.
10. The system of claim 6, wherein the computing module is specifically configured to:
NET deploys the researched model to the production environment, and develops deep learning compilation software; and calculating the flow in real time by using the real-time input factor and the input factor of the previous n time periods, and using the flow for online flow monitoring, real-time flood forecasting and automatic editing.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010619756.XA CN111753965A (en) | 2020-06-30 | 2020-06-30 | Deep learning-based river flow automatic editing method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010619756.XA CN111753965A (en) | 2020-06-30 | 2020-06-30 | Deep learning-based river flow automatic editing method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111753965A true CN111753965A (en) | 2020-10-09 |
Family
ID=72678631
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010619756.XA Pending CN111753965A (en) | 2020-06-30 | 2020-06-30 | Deep learning-based river flow automatic editing method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111753965A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113641733A (en) * | 2021-10-18 | 2021-11-12 | 长江水利委员会水文局 | Real-time intelligent estimation method for river cross section flow |
CN113673759A (en) * | 2021-08-19 | 2021-11-19 | 四创科技有限公司 | Real-time marshalling method and terminal for hydrological data |
CN113934777A (en) * | 2021-12-16 | 2022-01-14 | 长江水利委员会水文局 | Method and system for quantifying influence of backwater jacking on water level change |
CN117408173A (en) * | 2023-12-16 | 2024-01-16 | 长江水利委员会水文局长江中游水文水资源勘测局 | Hydrologic flow recompilation intelligent model construction method based on machine learning |
Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106777775A (en) * | 2017-01-10 | 2017-05-31 | 清华大学 | A kind of neural net method based on many section water level forecast river discharges |
CN108647807A (en) * | 2018-04-10 | 2018-10-12 | 武汉理工大学 | The prediction technique of river discharge |
CN109543912A (en) * | 2018-11-29 | 2019-03-29 | 中国水利水电科学研究院 | Reservoir optimal scheduling decision model generation method based on deep learning |
CN109583565A (en) * | 2018-11-07 | 2019-04-05 | 河海大学 | Forecasting Flood method based on the long memory network in short-term of attention model |
CN109615011A (en) * | 2018-12-14 | 2019-04-12 | 河海大学 | A kind of middle and small river short time flood forecast method based on LSTM |
CN109754025A (en) * | 2019-02-02 | 2019-05-14 | 中国水利水电科学研究院 | A kind of small reservoir parameter identification method of the non-avaible of combination hydrological simulation and continuous remote sensing image |
CN110110921A (en) * | 2019-04-30 | 2019-08-09 | 武汉理工大学 | A kind of river level prediction technique considering time-lag effect |
CN110163419A (en) * | 2019-04-28 | 2019-08-23 | 河海大学 | A kind of method of middle and small river river basin flood forecast |
CN110288157A (en) * | 2019-06-27 | 2019-09-27 | 电子科技大学 | A kind of Runoff Forecast method based on attention mechanism and LSTM |
CN110459036A (en) * | 2019-09-09 | 2019-11-15 | 四川省水利科学研究院 | A kind of mountain torrents method for early warning based on deep learning |
CN110969282A (en) * | 2019-10-17 | 2020-04-07 | 天津大学 | Runoff stability prediction method based on LSTM composite network |
CN111079998A (en) * | 2019-12-03 | 2020-04-28 | 华东师范大学 | Flow prediction method based on long and short time sequence correlation attention mechanism model |
CN111159149A (en) * | 2019-12-13 | 2020-05-15 | 国网浙江省电力有限公司紧水滩水力发电厂 | River flow prediction method based on three-dimensional convolutional neural network |
CN111222698A (en) * | 2020-01-06 | 2020-06-02 | 重庆邮电大学 | Long-and-short-term memory network-based ponding water level prediction method for Internet of things |
CN111275253A (en) * | 2020-01-15 | 2020-06-12 | 中国地质大学(武汉) | Runoff probabilistic prediction method and system integrating deep learning and error correction |
-
2020
- 2020-06-30 CN CN202010619756.XA patent/CN111753965A/en active Pending
Patent Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106777775A (en) * | 2017-01-10 | 2017-05-31 | 清华大学 | A kind of neural net method based on many section water level forecast river discharges |
CN108647807A (en) * | 2018-04-10 | 2018-10-12 | 武汉理工大学 | The prediction technique of river discharge |
CN109583565A (en) * | 2018-11-07 | 2019-04-05 | 河海大学 | Forecasting Flood method based on the long memory network in short-term of attention model |
CN109543912A (en) * | 2018-11-29 | 2019-03-29 | 中国水利水电科学研究院 | Reservoir optimal scheduling decision model generation method based on deep learning |
CN109615011A (en) * | 2018-12-14 | 2019-04-12 | 河海大学 | A kind of middle and small river short time flood forecast method based on LSTM |
CN109754025A (en) * | 2019-02-02 | 2019-05-14 | 中国水利水电科学研究院 | A kind of small reservoir parameter identification method of the non-avaible of combination hydrological simulation and continuous remote sensing image |
CN110163419A (en) * | 2019-04-28 | 2019-08-23 | 河海大学 | A kind of method of middle and small river river basin flood forecast |
CN110110921A (en) * | 2019-04-30 | 2019-08-09 | 武汉理工大学 | A kind of river level prediction technique considering time-lag effect |
CN110288157A (en) * | 2019-06-27 | 2019-09-27 | 电子科技大学 | A kind of Runoff Forecast method based on attention mechanism and LSTM |
CN110459036A (en) * | 2019-09-09 | 2019-11-15 | 四川省水利科学研究院 | A kind of mountain torrents method for early warning based on deep learning |
CN110969282A (en) * | 2019-10-17 | 2020-04-07 | 天津大学 | Runoff stability prediction method based on LSTM composite network |
CN111079998A (en) * | 2019-12-03 | 2020-04-28 | 华东师范大学 | Flow prediction method based on long and short time sequence correlation attention mechanism model |
CN111159149A (en) * | 2019-12-13 | 2020-05-15 | 国网浙江省电力有限公司紧水滩水力发电厂 | River flow prediction method based on three-dimensional convolutional neural network |
CN111222698A (en) * | 2020-01-06 | 2020-06-02 | 重庆邮电大学 | Long-and-short-term memory network-based ponding water level prediction method for Internet of things |
CN111275253A (en) * | 2020-01-15 | 2020-06-12 | 中国地质大学(武汉) | Runoff probabilistic prediction method and system integrating deep learning and error correction |
Non-Patent Citations (5)
Title |
---|
吕世新 等: "高新技术在水文勘测中的实用性研究", 《河南科技》 * |
江竹 等: "机器学习在河流流量参数估计中的应用", 《西华大学学报(自然科学版)》 * |
燕艳 等: "探讨水文水情信息大数据处理现状及策略", 《价值工程》 * |
郑茹楠 等: "深度学习在水文工作中的应用探讨", 《河南水利与南水北调》 * |
陈健健 等: "基于神经网络模型计算感潮河段断面平均流速", 《水利信息化》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113673759A (en) * | 2021-08-19 | 2021-11-19 | 四创科技有限公司 | Real-time marshalling method and terminal for hydrological data |
CN113641733A (en) * | 2021-10-18 | 2021-11-12 | 长江水利委员会水文局 | Real-time intelligent estimation method for river cross section flow |
CN113934777A (en) * | 2021-12-16 | 2022-01-14 | 长江水利委员会水文局 | Method and system for quantifying influence of backwater jacking on water level change |
CN113934777B (en) * | 2021-12-16 | 2022-03-04 | 长江水利委员会水文局 | Method and system for quantifying influence of backwater jacking on water level change |
CN117408173A (en) * | 2023-12-16 | 2024-01-16 | 长江水利委员会水文局长江中游水文水资源勘测局 | Hydrologic flow recompilation intelligent model construction method based on machine learning |
CN117408173B (en) * | 2023-12-16 | 2024-03-01 | 长江水利委员会水文局长江中游水文水资源勘测局 | Hydrologic flow recompilation intelligent model construction method based on machine learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111753965A (en) | Deep learning-based river flow automatic editing method and system | |
CN111310968B (en) | LSTM neural network circulating hydrologic forecasting method based on mutual information | |
CN102183621B (en) | Aquaculture dissolved oxygen concentration online forecasting method and system | |
CN116630122B (en) | Lake ecological hydraulic regulation and control method and system based on hydrologic-ecological response relation | |
CN113298297B (en) | Wind power output power prediction method based on isolated forest and WGAN network | |
CN114168906B (en) | Mapping geographic information data acquisition system based on cloud computing | |
CN112330065A (en) | Runoff forecasting method based on basic flow segmentation and artificial neural network model | |
CN113205203A (en) | CNN-LSTM-based building energy consumption prediction method and system | |
CN109783934A (en) | A kind of mean velocity in section fitting rating method based on H-ADCP | |
CN103577647A (en) | Evaluation analysis method and device of steam turbine and steam turbine speed adjusting system model | |
CN116643331A (en) | Hydrologic forecasting method based on hydrologic information big data of regional river basin | |
CN103279030B (en) | Dynamic soft measuring modeling method and device based on Bayesian frame | |
CN114692981A (en) | Medium-and-long-term runoff forecasting method and system based on Seq2Seq model | |
CN114357737A (en) | Agent optimization calibration method for time-varying parameters of large-scale hydrological model | |
CN113033845B (en) | Construction method and device for power transmission resource co-construction and sharing | |
CN114154686A (en) | Dam deformation prediction method based on ensemble learning | |
CN113868223A (en) | Water quality monitoring method, device and system and readable storage medium | |
CN113537770A (en) | Decision tree configuration life prediction method and system based on cloud computing | |
CN105260789A (en) | Wind power data time scale optimization method for short-term forecast of wind power | |
CN115422840A (en) | Ridge-scale runoff estimation method based on physical model mixed deep learning model | |
CN113094876B (en) | Reservoir flood control risk calculation method and system based on ARIMA model under future situation | |
CN117113157B (en) | Platform district power consumption fault detection system based on artificial intelligence | |
CN113256018B (en) | Wind power ultra-short term probability prediction method based on conditional quantile regression model | |
CN111291490B (en) | Nonlinear mapping intelligent modeling method for structure multi-scale heterogeneous response | |
CN109948108B (en) | The verification method of the selection of fugitive dust discharge capacity account model, discharge capacity account and displacement data |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201009 |