CN113657557B - Hydrologic forecasting method and system based on inversion data and actual measurement data fusion - Google Patents
Hydrologic forecasting method and system based on inversion data and actual measurement data fusion Download PDFInfo
- Publication number
- CN113657557B CN113657557B CN202111136496.1A CN202111136496A CN113657557B CN 113657557 B CN113657557 B CN 113657557B CN 202111136496 A CN202111136496 A CN 202111136496A CN 113657557 B CN113657557 B CN 113657557B
- Authority
- CN
- China
- Prior art keywords
- data
- inversion
- machine learning
- flood
- hydrological
- 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.)
- Active
Links
- 230000004927 fusion Effects 0.000 title claims abstract description 35
- 238000005259 measurement Methods 0.000 title claims abstract description 13
- 238000013277 forecasting method Methods 0.000 title claims abstract description 9
- 238000010801 machine learning Methods 0.000 claims abstract description 48
- 238000000034 method Methods 0.000 claims abstract description 26
- 238000011156 evaluation Methods 0.000 claims abstract description 19
- 238000013528 artificial neural network Methods 0.000 claims description 21
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 11
- 230000008020 evaporation Effects 0.000 claims description 7
- 238000001704 evaporation Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 4
- 238000011160 research Methods 0.000 claims description 3
- 230000000630 rising effect Effects 0.000 claims description 3
- 238000012797 qualification Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/254—Fusion techniques of classification results, e.g. of results related to same input data
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/10—Devices for predicting weather conditions
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/14—Rainfall or precipitation gauges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06N3/04—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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
-
- 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
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Environmental & Geological Engineering (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Ecology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Atmospheric Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Environmental Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medical Informatics (AREA)
- Hydrology & Water Resources (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Feedback Control In General (AREA)
Abstract
The application discloses a hydrological forecasting method and a hydrological forecasting system based on inversion data and actual measurement data fusion, wherein the method comprises the following steps: collecting measured data and constructing a MIKE-SHE hydrological model according to the measured data; obtaining inversion data based on the MIKE-SHE hydrological model; fusing the measured data and the inversion data to obtain fused data; constructing a plurality of machine learning models based on the fused data; and weighting each machine learning model based on a comprehensive evaluation method, and developing real-time combined hydrologic forecast. The system comprises: the system comprises a hydrological model building module, a data inversion module, a data fusion module, a multi-machine learning module building module and a forecasting module. By using the method and the device, the hydrologic forecasting accuracy can be improved. The hydrologic forecasting method and system based on the fusion of inversion data and measured data can be widely applied to combined hydrologic forecasting precision.
Description
Technical Field
The application relates to the field of combined hydrologic forecasting, in particular to a hydrologic forecasting method and system based on inversion data and measured data fusion.
Background
The hydrologic forecasting refers to qualitative or quantitative forecasting of hydrologic conditions of a certain water body, region or hydrologic station in a certain time in the future according to the prior or current hydrologic meteorological data, and can be divided into real-time, short-term, medium-term and long-term hydrologic forecasting according to the length of forecasting time, so that important decision support is provided for the problems of watershed drought and waterlogging disaster prevention, scientific water resource distribution and the like in actual production and life. Under the dual influence of global climate change and human activities, uncertainty factors suffered by the hydrologic process are increased, so that the difficulty of developing accurate hydrologic forecast is increased sharply, and the conventional single hydrologic model is difficult to realize the related tasks of the existing hydrologic forecast.
Disclosure of Invention
In order to solve the technical problems, the application aims to provide a hydrological forecasting method and a hydrological forecasting system based on inversion data and measured data fusion, and the hydrological forecasting precision is improved.
The first technical scheme adopted by the application is as follows: a hydrological forecasting method based on inversion data and actual measurement data fusion comprises the following steps:
collecting measured data and constructing a MIKE-SHE hydrological model according to the measured data;
obtaining inversion data based on the MIKE-SHE hydrological model;
fusing the measured data and the inversion data to obtain fused data;
constructing a plurality of machine learning models based on the fused data;
and weighting each machine learning model based on a comprehensive evaluation method, and developing real-time combined hydrologic forecast.
Further, the step of collecting the measured data and constructing the MIKE-SHE hydrological model according to the measured data specifically comprises the following steps:
collecting rainfall, evaporation, flow, water level data and flood data of a research area;
dividing flood orders according to the rising points and the falling end points of flood process lines in flood data, and dividing related rainfall, evaporation, flow and water level data according to the flood orders;
dividing the divided flood orders into training data and test data according to a ratio of 7:3;
constructing a MIKE-SHE hydrological model based on the training data;
the MIKE-SHE hydrologic model was validated based on the test data.
Further, the step of obtaining inversion data based on the MIKE-SHE hydrologic model specifically further includes:
setting special working conditions of rainfall or drought conditions in different reproduction periods;
inputting hydrological data under special working conditions as calibration parameters into a MIKE-SHE hydrological model to obtain water level and flow data;
and dividing the water level and flow data according to the flood field times to obtain divided inversion data.
Further, the step of fusing the measured data and the inversion data to obtain fused data specifically includes:
classifying all flood orders of the measured data and the inversion data by adopting an SOM algorithm to obtain classified data;
and fusing the classified data by using a Deep Learning algorithm to obtain fused data.
Further, the step of constructing a plurality of machine learning models based on the fusion data specifically includes:
respectively training a multi-layer feedforward neural network machine learning model, a local regression neural network machine learning model and a neural network LSTM machine learning model based on the fusion data;
inputting measured data and obtaining corresponding hydrologic forecasting results based on the multilayer feedforward neural network machine learning model, the local regression neural network machine learning model and the neural network LSTM machine learning model.
Further, the step of weighting each machine learning model based on the comprehensive evaluation method and developing the real-time combined hydrologic forecast specifically comprises the following steps:
selecting an index to evaluate the hydrologic forecasting result to obtain an index evaluation result;
and determining the weight of each machine learning model based on the index evaluation result, and developing real-time combined hydrologic forecast.
Further, the index includes:
evaluating peak flow relative error and peak time error indexes which are accurately related to the flood peak forecast;
evaluating a total flood relative balance error index accurately related to flood forecast;
and evaluating Nash coefficient indexes of the prediction accuracy of the runoff process.
The second technical scheme adopted by the application is as follows: a hydrological forecasting system based on inversion data and measured data fusion, comprising:
the hydrological model construction module is used for collecting actual measurement data and constructing a MIKE-SHE hydrological model according to the actual measurement data;
the data inversion module is used for obtaining inversion data based on the MIKE-SHE hydrological model;
the data fusion module is used for fusing the measured data and the inversion data to obtain fusion data;
a multi-machine learning module construction module that constructs a plurality of machine learning models based on the fusion data;
and the forecasting module weights each machine learning model based on a comprehensive evaluation method and develops real-time combined hydrologic forecasting.
The method and the system have the beneficial effects that: according to the application, the measured data and the inversion data are fused, the data sample capacity is expanded, the real-time updating of the weight is realized by utilizing the high-efficiency computing capability of a machine learning algorithm, and the reasonable weight is obtained by combining multi-index comprehensive evaluation, so that the accuracy of the forecasting result is improved.
Drawings
FIG. 1 is a flow chart of the steps of a hydrological forecast based on the fusion of inversion data and measured data in accordance with the present application;
FIG. 2 is a schematic flow chart of an embodiment of the present application;
FIG. 3 is a block diagram of a hydrological forecasting system based on inversion data and measured data fusion.
Detailed Description
The application will now be described in further detail with reference to the drawings and to specific examples. The step numbers in the following embodiments are set for convenience of illustration only, and the order between the steps is not limited in any way, and the execution order of the steps in the embodiments may be adaptively adjusted according to the understanding of those skilled in the art.
Referring to fig. 1 and 2, the present application provides a hydrological forecasting method based on fusion of inversion data and measured data, the method comprising the steps of:
collecting measured data and constructing a MIKE-SHE hydrological model according to the measured data;
obtaining inversion data based on the MIKE-SHE hydrological model;
fusing the measured data and the inversion data to obtain fused data;
specifically, the problem of comprehensiveness of data is solved through data fusion.
Constructing a plurality of machine learning models based on the fused data;
specifically, constructing a plurality of machine learning models solves the problem of insufficient accuracy of a single conventional model.
And weighting each machine learning model based on a comprehensive evaluation method, and developing real-time combined hydrologic forecast.
Specifically, a plurality of evaluation indexes are introduced, a comprehensive evaluation method is adopted to evaluate the model result, and proper weights are distributed, so that the problem that weight determination is not strict enough is solved, and high-precision real-time hydrologic forecasting is provided.
Further as a preferred embodiment of the method, the step of collecting measured data and constructing the MIKE-SHE hydrological model according to the measured data specifically includes:
collecting rainfall, evaporation, flow, water level data and flood data of a research area;
dividing flood orders according to the rising points and the falling end points of flood process lines in flood data, and dividing related rainfall, evaporation, flow and water level data according to the flood orders;
dividing the divided flood orders into training data and test data according to a ratio of 7:3;
constructing a MIKE-SHE hydrological model based on the training data;
the MIKE-SHE hydrologic model was validated based on the test data.
Specifically, the training stage flood is used to rate the parameters, the testing stage flood is used to check the rate effect of the parameters, and if the rate stage does not perform well, the parameters need to be re-rate.
Further as a preferred embodiment of the method, the step of obtaining inversion data based on the MIKE-SHE hydrological model specifically further includes:
setting special working conditions of rainfall or drought conditions in different reproduction periods;
inputting hydrological data under special working conditions as calibration parameters into a MIKE-SHE hydrological model to obtain water level and flow data;
and dividing the water level and flow data according to the flood field times to obtain divided inversion data.
Specifically, the reproduction period comprises 100 years, 200 years, 500 years, 1000 years and the like, data including rainfall, evaporation and the like in special working conditions are used as input of a MIKE-SHE model, and the model with well-defined utilization rate parameters is used for carrying out special working condition water level and flow of a downstream monitoring section.
Further as a preferred embodiment of the method, the step of fusing the measured data and the inversion data to obtain fused data specifically includes:
classifying all flood orders of the measured data and the inversion data by adopting an SOM algorithm to obtain classified data;
and fusing the classified data by using a Deep Learning algorithm to obtain fused data.
Further as a preferred embodiment of the method, the step of constructing a plurality of machine learning models based on the fused data specifically includes:
respectively training a multi-layer feedforward neural network machine learning model, a local regression neural network machine learning model and a neural network LSTM machine learning model based on the fusion data;
inputting measured data and obtaining corresponding hydrologic forecasting results based on the multilayer feedforward neural network machine learning model, the local regression neural network machine learning model and the neural network LSTM machine learning model.
Specifically, a multi-layer feedforward neural network BP (BackPropagation) algorithm based on error back propagation training; the local regression neural network Elman algorithm with local memory unit and local feedback connection belongs to the improvement on BP algorithm; the neural network LSTM (Long Short Term Mermory) algorithm which can well solve the long-term dependence problem based on the global memory module belongs to improvement on the Elman algorithm; the three selected machine learning algorithms are structurally inheritable, have advantages and disadvantages, and are widely applied to the field of hydrologic forecasting.
Further as a preferred embodiment of the method, the step of weighting each machine learning model based on the comprehensive evaluation method and developing a real-time combined hydrologic forecast specifically includes:
selecting an index to evaluate the hydrologic forecasting result to obtain an index evaluation result;
and determining the weight of each machine learning model based on the index evaluation result, and developing real-time combined hydrologic forecast.
Further as a preferred embodiment of the method, the index includes:
evaluating peak flow relative error and peak time error indexes which are accurately related to the flood peak forecast;
peak-to-peak relative error qualification rate index:
wherein Q is e Represents the relative error coefficient of flood peak flow, Q er Represents the relative error qualification rate of flood peak, Q o,m Representative model forecast flood peak flow value, Q m Represents the actual measured flood peak flow value of the river basin, N q Representing flood times with qualified errors, and taking Q e Less than or equal to 20 percent of the flood field times are qualified, N sum Representing the total flood volume.
Peak time error qualification rate index:
T e =|T(Q o,m )-T(Q m )|
wherein T is e Represents peak time error, T (Q) o,m ) Representing the predicted peak flow occurrence time, T (Q) m ) Representing the appearance time of the actual measured flood peak flow of the river basin, T er Represents the percent of pass of peak time error, N t Representing flood times with qualified errors, taking Te less than or equal to 2 as qualified flood times and N sum Representing the total flood volume.
Evaluating a total flood relative balance error index accurately related to flood forecast;
total flood relative balance error index:
wherein I is vf Representing the relative error of flood balance; q (Q) t Representing a real-time observation flow value; q (Q) o,t The representative model predicts the flow value.
Evaluating Nash coefficient indexes of the prediction accuracy of the runoff process;
nash coefficient index:
wherein NSE represents Nash coefficient, Q t Representing the real-time observed flow value, Q o,t The representative model predicts the flow value,representing the mean of the measured values.
As shown in fig. 3, a hydrological forecasting system based on fusion of inversion data and measured data, comprising:
the hydrological model construction module is used for collecting actual measurement data and constructing a MIKE-SHE hydrological model according to the actual measurement data;
the data inversion module is used for obtaining inversion data based on the MIKE-SHE hydrological model;
the data fusion module is used for fusing the measured data and the inversion data to obtain fusion data;
a multi-machine learning module construction module that constructs a plurality of machine learning models based on the fusion data;
and the forecasting module weights each machine learning model based on a comprehensive evaluation method and develops real-time combined hydrologic forecasting.
The content in the method embodiment is applicable to the system embodiment, the functions specifically realized by the system embodiment are the same as those of the method embodiment, and the achieved beneficial effects are the same as those of the method embodiment.
While the preferred embodiment of the present application has been described in detail, the application is not limited to the embodiment, and various equivalent modifications and substitutions can be made by those skilled in the art without departing from the spirit of the application, and these equivalent modifications and substitutions are intended to be included in the scope of the present application as defined in the appended claims.
Claims (6)
1. A hydrological forecasting method based on inversion data and actual measurement data fusion is characterized by comprising the following steps:
collecting measured data and constructing a MIKE-SHE hydrological model according to the measured data;
obtaining inversion data based on the MIKE-SHE hydrological model;
fusing the measured data and the inversion data to obtain fused data;
constructing a plurality of machine learning models based on the fused data;
weighting each machine learning model based on a comprehensive evaluation method, and developing real-time combined hydrologic forecast;
the step of obtaining inversion data based on the MIKE-SHE hydrological model specifically further comprises the following steps:
setting special working conditions of rainfall or drought conditions in different reproduction periods;
inputting hydrological data under special working conditions as calibration parameters into a MIKE-SHE hydrological model to obtain water level and flow data;
dividing the water level and flow data according to flood orders to obtain divided inversion data;
the step of fusing the measured data and the inversion data to obtain fused data specifically comprises the following steps:
classifying all flood orders of the measured data and the inversion data by adopting an SOM algorithm to obtain classified data;
and fusing the classified data by using a Deep Learning algorithm to obtain fused data.
2. The method for hydrologic forecasting according to claim 1, wherein the method is characterized in that,
the step of collecting measured data and constructing a MIKE-SHE hydrological model according to the measured data specifically comprises the following steps:
collecting rainfall, evaporation, flow, water level data and flood data of a research area;
dividing flood orders according to the rising points and the falling end points of flood process lines in flood data, and dividing related rainfall, evaporation, flow and water level data according to the flood orders;
dividing the divided flood orders into training data and test data according to a ratio of 7:3;
constructing a MIKE-SHE hydrological model based on the training data;
the MIKE-SHE hydrologic model was validated based on the test data.
3. The method for forecasting hydrologic based on inversion data and actual measurement data fusion according to claim 2, wherein the step of constructing a plurality of machine learning models based on the fusion data specifically comprises the following steps:
respectively training a multi-layer feedforward neural network machine learning model, a local regression neural network machine learning model and a neural network LSTM machine learning model based on the fusion data;
inputting measured data and obtaining corresponding hydrologic forecasting results based on the multilayer feedforward neural network machine learning model, the local regression neural network machine learning model and the neural network LSTM machine learning model.
4. The method for forecasting hydrologic based on inversion data and actual measurement data fusion according to claim 3, wherein the step of weighting each machine learning model based on the comprehensive evaluation method and developing real-time combined hydrologic forecasting specifically comprises the following steps:
selecting an index to evaluate the hydrologic forecasting result to obtain an index evaluation result;
and determining the weight of each machine learning model based on the index evaluation result, and developing real-time combined hydrologic forecast.
5. The method for hydrologic forecasting based on inversion data and measured data fusion according to claim 4, wherein the index comprises:
evaluating peak flow relative error and peak time error indexes which are accurately related to the flood peak forecast;
evaluating a total flood relative balance error index accurately related to flood forecast;
and evaluating Nash coefficient indexes of the prediction accuracy of the runoff process.
6. The hydrological forecasting system based on the fusion of inversion data and measured data is characterized by comprising the following modules:
the hydrological model construction module is used for collecting actual measurement data and constructing a MIKE-SHE hydrological model according to the actual measurement data;
the data inversion module is used for obtaining inversion data based on the MIKE-SHE hydrological model;
the data fusion module is used for fusing the measured data and the inversion data to obtain fusion data;
a multi-machine learning module construction module that constructs a plurality of machine learning models based on the fusion data;
the forecasting module weights each machine learning model based on a comprehensive evaluation method and develops real-time combined hydrologic forecasting;
the inversion data is obtained based on the MIKE-SHE hydrological model, and the method specifically comprises the following steps: setting special working conditions of rainfall or drought conditions in different reproduction periods; inputting hydrological data under special working conditions as calibration parameters into a MIKE-SHE hydrological model to obtain water level and flow data; dividing the water level and flow data according to flood orders to obtain divided inversion data;
the fusion of the measured data and the inversion data to obtain fusion data specifically comprises the following steps: classifying all flood orders of the measured data and the inversion data by adopting an SOM algorithm to obtain classified data; and fusing the classified data by using a Deep Learning algorithm to obtain fused data.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2021106909075 | 2021-06-22 | ||
CN202110690907.5A CN113420808A (en) | 2021-06-22 | 2021-06-22 | Hydrological forecasting method and hydrological forecasting system based on fusion of inversion data and measured data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113657557A CN113657557A (en) | 2021-11-16 |
CN113657557B true CN113657557B (en) | 2023-12-15 |
Family
ID=77789796
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110690907.5A Withdrawn CN113420808A (en) | 2021-06-22 | 2021-06-22 | Hydrological forecasting method and hydrological forecasting system based on fusion of inversion data and measured data |
CN202111136496.1A Active CN113657557B (en) | 2021-06-22 | 2021-09-27 | Hydrologic forecasting method and system based on inversion data and actual measurement data fusion |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110690907.5A Withdrawn CN113420808A (en) | 2021-06-22 | 2021-06-22 | Hydrological forecasting method and hydrological forecasting system based on fusion of inversion data and measured data |
Country Status (1)
Country | Link |
---|---|
CN (2) | CN113420808A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104298841A (en) * | 2013-07-16 | 2015-01-21 | 杭州贵仁科技有限公司 | Flood forecasting method and system based on historical data |
CN106249318A (en) * | 2016-07-12 | 2016-12-21 | 清华大学 | River basin flood Real-time Forecasting Method and predictor |
CN107609335A (en) * | 2017-09-22 | 2018-01-19 | 中国水利水电科学研究院 | A kind of Flood Forecasting Method based on resultant flow and form fit |
CN111104981A (en) * | 2019-12-19 | 2020-05-05 | 华中科技大学 | Hydrological prediction precision evaluation method and system based on machine learning |
CN112861449A (en) * | 2021-02-19 | 2021-05-28 | 河海大学 | Multi-river-section combined correction model based on flood forecast error inversion |
-
2021
- 2021-06-22 CN CN202110690907.5A patent/CN113420808A/en not_active Withdrawn
- 2021-09-27 CN CN202111136496.1A patent/CN113657557B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104298841A (en) * | 2013-07-16 | 2015-01-21 | 杭州贵仁科技有限公司 | Flood forecasting method and system based on historical data |
CN106249318A (en) * | 2016-07-12 | 2016-12-21 | 清华大学 | River basin flood Real-time Forecasting Method and predictor |
CN107609335A (en) * | 2017-09-22 | 2018-01-19 | 中国水利水电科学研究院 | A kind of Flood Forecasting Method based on resultant flow and form fit |
CN111104981A (en) * | 2019-12-19 | 2020-05-05 | 华中科技大学 | Hydrological prediction precision evaluation method and system based on machine learning |
CN112861449A (en) * | 2021-02-19 | 2021-05-28 | 河海大学 | Multi-river-section combined correction model based on flood forecast error inversion |
Also Published As
Publication number | Publication date |
---|---|
CN113420808A (en) | 2021-09-21 |
CN113657557A (en) | 2021-11-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108280553B (en) | Mountain torrent disaster risk zoning and prediction method based on GIS-neural network integration | |
CN111310968B (en) | LSTM neural network circulating hydrologic forecasting method based on mutual information | |
Mba et al. | Application of artificial neural network for predicting hourly indoor air temperature and relative humidity in modern building in humid region | |
Harrigan et al. | Designation and trend analysis of the updated UK Benchmark Network of river flow stations: The UKBN2 dataset | |
Ren et al. | Improving monthly streamflow prediction in alpine regions: integrating HBV model with Bayesian neural network | |
CN109711617A (en) | A kind of medium-term and long-term Runoff Forecast method based on BLSTM deep learning | |
CN112801342A (en) | Adaptive runoff forecasting method based on rainfall runoff similarity | |
CN107665172A (en) | A kind of Software Defects Predict Methods based on complicated weighting software network | |
CN110598352B (en) | Drainage basin water supply forecasting method | |
CN112348290B (en) | River water quality prediction method, river water quality prediction device, storage medium and storage device | |
KR20140140361A (en) | Water Quality Forecasting of the River Applying Ensemble Streamflow Prediction | |
CN114970377B (en) | Method and system for field flood forecasting based on Xinanjiang and deep learning coupling model | |
CN110276477B (en) | Flood forecasting method based on hierarchical Bayesian network and incremental learning | |
CN111553394A (en) | Reservoir water level prediction method based on cyclic neural network and attention mechanism | |
CN107798431A (en) | A kind of Medium-and Long-Term Runoff Forecasting method based on Modified Elman Neural Network | |
Fallahi et al. | Leakage detection in water distribution networks using hybrid feedforward artificial neural networks | |
CN113657557B (en) | Hydrologic forecasting method and system based on inversion data and actual measurement data fusion | |
CN112905436A (en) | Quality evaluation prediction method for complex software | |
Boussabaine et al. | Modelling cost‐flow forecasting for water pipeline projects using neural networks | |
LU503105B1 (en) | Rice Productive Potential Simulation Method Based on Coupling of Land System and Climate Change | |
CN113487069B (en) | Regional flood disaster risk assessment method based on GRACE daily degradation scale and novel DWSDI index | |
CN109919362A (en) | A kind of Medium-and Long-Term Runoff Forecasting method for considering hydraulic engineering scheduling and influencing | |
Rahmati et al. | System-dynamics approach to multireservoir energy generation under climate change | |
CN109101759A (en) | A kind of parameter identification method based on forward and reverse response phase method | |
CN114240006A (en) | Water resource bearing capacity assessment method |
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 |