CN114792168A - Hydrological prediction method and system based on space-time big data - Google Patents
Hydrological prediction method and system based on space-time big data Download PDFInfo
- Publication number
- CN114792168A CN114792168A CN202210502777.2A CN202210502777A CN114792168A CN 114792168 A CN114792168 A CN 114792168A CN 202210502777 A CN202210502777 A CN 202210502777A CN 114792168 A CN114792168 A CN 114792168A
- Authority
- CN
- China
- Prior art keywords
- flood
- scene
- hydrological
- information
- space
- 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
- 238000000034 method Methods 0.000 title claims abstract description 72
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 31
- 238000012216 screening Methods 0.000 claims abstract description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 239000002689 soil Substances 0.000 claims description 6
- 238000006424 Flood reaction Methods 0.000 claims description 4
- 238000003066 decision tree Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 238000001556 precipitation Methods 0.000 claims description 3
- 230000003068 static effect Effects 0.000 claims description 3
- 230000001052 transient effect Effects 0.000 claims 1
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012917 library technology Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a hydrological prediction method based on space-time big data, which comprises the steps of obtaining a multi-source space-time historical data set of a forecast object; extracting M flood courses from multi-source time-space historical data set; screening out the characteristic information which is maximally related to the water incoming process and has minimum redundancy in each flood process; dividing the flood process of the M fields into L scenes according to the screened characteristic information, and generating a scene set; constructing a hydrological forecasting model, and calibrating the hydrological forecasting model under L scenes in a scene set; the method comprises the steps of determining a scene closest to the current state based on feature information screened out from the current state of the forecast object basin, and adopting a hydrologic forecast model corresponding to the scene to forecast the future process of the forecast object basin.
Description
Technical Field
The invention belongs to the technical field of hydrologic prediction, and particularly relates to a hydrologic prediction method and a hydrologic prediction system based on space-time big data.
Background
With the continuous development of computer technology and mathematical optimization algorithm technology, hydrologic forecast model library technology and forecast model parameter automatic optimization and calibration technology have been widely applied, but mainly focus on selecting the 'best weapon' in the hydrologic forecast model weapon library, and in fact, at present, most hydrologic forecast models have certain experience, so that the so-called 'best model' is often difficult to find, or the optimal model is difficult to determine. From the actual hydrological characteristics, the performance of the model does not have good consistency under different time and space dimensions.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a hydrological prediction method and a hydrological prediction system based on space-time big data, which can find a model which best represents in a specific scene to predict hydrological data.
The technical problem to be solved by the invention is realized by the following technical scheme:
in a first aspect, the present invention provides a hydrological prediction method based on spatiotemporal big data, including:
acquiring a multi-source time-space historical data set of a forecast object;
extracting M fields of flood processes from the multi-source time-space historical data set;
screening out the characteristic information which is maximally related to the water incoming process and has minimum redundancy in each flood process;
dividing the flood process of the M fields into L scenes according to the screened characteristic information, and generating a scene set;
constructing a hydrological forecasting model, and calibrating the hydrological forecasting model under L scenes in a scene set;
and determining a scene closest to the current state based on the feature information screened out from the current state of the forecast object basin, and predicting the future process of the forecast object basin by adopting a hydrological forecasting model corresponding to the scene.
With reference to the first aspect, further, if the correlation degrees of the current state of the prediction object basin and all scenes in the scene set are smaller than the threshold value of the correlation degrees, the current state of the prediction object basin is added to the scene set.
With reference to the first aspect, further, the acquiring a multi-source spatiotemporal historical dataset of a forecast object includes:
extracting static characteristic information of a watershed to be predicted;
extracting the space-time distribution information of the vegetation index of the watershed to be predicted, the soil humidity at different depths, the surface air temperature and the precipitation;
extracting rainfall and water level information of a watershed to be predicted;
a data set is established based on the above various information.
With reference to the first aspect, further, the extracting M-field flood process includes:
presetting a historical flood peak flow threshold value, and extracting M fields of flood with flow larger than the flow threshold value according to the process of intensively forecasting the historical flow fluctuation of the object by multi-source time-space historical data;
obtaining information of each flood according to the starting and ending time of M floods and the multi-source time-space historical data set;
and extracting N characteristics based on the information of each flood to generate an array of dimension M multiplied by N.
With reference to the first aspect, further, the screening out feature information that is maximally related to the incoming water process and has minimal redundancy in each flood process includes:
normalizing elements in the array of the dimension of M multiplied by N;
clustering the N groups of features into K classes;
and selecting the index with the maximum correlation degree with the water incoming process from each class of characteristic indexes, generating K multiplied by M dimensional characteristic index information with M fields of flood, and taking the K multiplied by M dimensional characteristic index information as the characteristic information with the maximum correlation and the minimum redundancy of the water incoming of the forecast object.
With reference to the first aspect, further, the dividing the flood process of the M-field into L scenarios includes:
based on the generated K multiplied by M dimensional characteristic index information, a decision tree algorithm is adopted to divide M-field flood into L types, namely L scenes.
With reference to the first aspect, further, the calibrating the hydrologic forecast models in L scenes in the scene set includes:
and constructing a hydrologic prediction model suitable for the prediction object basin, and calibrating the hydrologic prediction model under the L scenes respectively based on an automatic rate parameter algorithm.
With reference to the first aspect, further, the determining a scene closest to the current state includes:
extracting and forecasting the current state of the drainage basin to screen out the characteristic information which is maximally related to the current state and has the minimum redundancy;
and finding out the scene closest to the current state from the scene set based on the characteristic information.
In a second aspect, a hydrological prediction method based on space-time big data is provided, and includes:
the data acquisition module is used for acquiring a multi-source time-space historical data set of a forecast object;
the characteristic generating module is used for extracting an M field flood process from the multi-source time-space historical data set;
screening out characteristic information which is maximally related to the incoming water process and is minimally redundant in each flood process;
the scene division module is used for dividing the M-field flood process into L scenes according to the screened characteristic information and generating a scene set;
the model determining module is used for constructing a hydrological forecasting model and calibrating the hydrological forecasting model under L scenes in the scene set;
and the forecasting module is used for determining a scene closest to the current state based on the characteristic information screened out from the current state of the forecasting object basin, and forecasting the future water process of the forecasting object basin by adopting a hydrological forecasting model corresponding to the scene.
The invention has the beneficial effects that: according to different hydrological meteorological conditions, the optimal set prediction model is selected by identifying and model matching scenes, and the forecasting precision and reliability of the water coming from the cascade hydropower station are improved. On the basis of constructing a multisource time-space data set, extracting historical flood and screening characteristic indexes with maximum correlation and minimum redundancy; dividing the historical flood field and the corresponding characteristic indexes into a plurality of scenes through processing such as cluster analysis, similarity judgment and the like; automatically identifying an optimal model scene according to the current basin time-space data state, and performing model prediction; with the continuous growth of meteorological hydrological data, the scene can be self-expanded, self-optimized and self-learned.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
To further describe the technical features and effects of the present invention, the present invention will be further described with reference to the accompanying drawings and detailed description.
Example 1
As shown in fig. 1, a hydrological prediction method based on spatiotemporal big data includes the following steps:
step one, acquiring a multi-source time-space historical data set of a forecast object
11) Extracting static characteristic information of the forecast drainage basin, comprising the following steps: a) extracting information such as gradient, river, water system and the like of a river basin based on Digital Elevation Model (DEM) data; b) extracting river basin land utilization information based on a WESTDC land utilization data product with the national width of 1 km; c) and extracting classification information of the watershed soil based on a Chinese soil information system.
12) Space-time distribution information of vegetation indexes, soil humidity at different depths, earth surface temperature, precipitation and the like in a current domain is obtained based on satellite remote sensing information inversion or a meteorological department, the spatial resolution of the information is about 3, 5 or 10 kilometers of grids, and the time resolution is 1 hour or 1 day.
13) Historical rainfall, water level and flow data of rainfall (rainfall station), water level (water level station) and hydrological measuring station in the drainage basin are obtained from a hydrological department or a drainage basin power station management department, and the time resolution of the data is 1 hour.
A data set is established based on the above various information.
Step two, extracting M field flood process from multi-source space-time historical data set
21) Firstly, presetting a historical flood peak flow threshold value, and extracting a plurality of fields of flood with flow larger than the flow threshold value according to the process of intensively forecasting the historical flow fluctuation of the object by multi-source time-space historical data, wherein the field of flood is assumed to be an M field;
22) obtaining the information of each flood according to the starting and ending time of M floods and the multi-source time-space historical data set;
based on the information of each flood, N characteristics (such as rainfall, rainfall duration, early-stage influence rainfall, rising flow and the like) related to the flood are extracted, and an array of M multiplied by N dimensions is generated.
23) M floods and N characteristic indexes of each flood form an array of dimension M multiplied by N.
Screening out the characteristic information which is maximally related to the water incoming process and is minimally redundant in each flood process;
31) since each flood characteristic index reflects different characteristics of flood, data difference is large, and in order to remove data difference among different indexes, absolute values of the indexes need to be changed into a certain relative value relation, N groups of index data are respectively subjected to normalization processing.
32) And converging the N groups of characteristic information into K classes by adopting dispersion standardization, zscore standardization or other clustering methods and combining the clustering analysis result and the physical significance of the characteristic indexes.
33) The 1 index with the largest correlation with the water inflow process is selected from each type of characteristic indexes, K multiplied by M dimensional characteristic index information of the basin is formed corresponding to M fields of flood, and K groups of characteristic indexes can be called as characteristic information with the largest correlation and the smallest redundancy with the water inflow of the basin.
34) The indexes related to the correlation with the incoming water process can be defined as flood peak correlation, flood volume correlation, flood process correlation and the like according to the prediction target requirement, and the judgment indexes maintain the flood peak similarity, the flood volume similarity, the shape similarity, the gray correlation and the like.
Step four, scene division
Based on a K multiplied by M dimensional array formed by K pieces of characteristic information and M fields of flood, the M fields of flood are classified by adopting a decision tree algorithm, the M fields of flood are divided into L types, namely L scenes, and a scene set is generated.
Step five, determining a model
51) Constructing a hydrological forecasting model suitable for forecasting the target basin, wherein the model is a distributed or semi-distributed conceptual model, and model parameters have certain correlation with basin characteristic information;
52) and respectively calibrating the hydrologic prediction model corresponding to each scene in the scene set based on an automatic rate parameter algorithm, and obtaining corresponding prediction model parameters for each scene.
Most parameters in the model can be obtained through calculation of feature information such as vegetation, soil, gradient and the like.
Step six, hydrologic prediction
61) And during real-time forecasting, extracting K pieces of characteristic information of the current state of the forecasting object basin.
62) And calculating and selecting the scene closest to the current state based on the association rule, and if the correlations between the current state and all the scenes are smaller than a set correlation threshold (set according to an empirical value), defining the current state as a new scene, wherein the number of the scenes is changed into L + 1.
63) And calculating based on the real-time water and rain condition information, the forecasting model and the model parameters of the selected scene to obtain the future water inflow process of the forecasting object.
After the flood is passed, the comparison between the predicted incoming water and the actual incoming water process is calculated according to the water and rain condition data and the original forecasting scheme to carry out parameter adjustment, and forecasting model parameters suitable for the current scene are obtained.
The method can be adopted to check and correct hydrological scenes of the watershed and forecast model parameters of the scenes according to the latest multi-source space-time data every year.
Example 2
The invention also provides a hydrological prediction method based on the space-time big data, which comprises the following steps:
the data acquisition module is used for acquiring a multi-source time-space historical data set of a forecast object;
the characteristic generating module is used for extracting an M field flood process from the multi-source time-space historical data set;
screening out characteristic information which is maximally related to the incoming water process and is minimally redundant in each flood process;
the scene dividing module is used for dividing the M-field flood process into L scenes according to the screened characteristic information and generating a scene set;
the model determining module is used for constructing a hydrological forecasting model and calibrating the hydrological forecasting model under L scenes in the scene set;
and the forecasting module is used for determining a scene closest to the current state based on the characteristic information screened out from the current state of the forecasting object basin, and forecasting the future water process of the forecasting object basin by adopting a hydrological forecasting model corresponding to the scene.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
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.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: although the present invention has been described in detail with reference to the above embodiments, it should be understood by those skilled in the art that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (9)
1. A hydrological prediction method based on space-time big data is characterized by comprising the following steps:
acquiring a multi-source time-space historical data set of a forecast object;
extracting M flood courses from multi-source time-space historical data set;
screening out characteristic information which is maximally related to the incoming water process and is minimally redundant in each flood process;
dividing the flood process of the M fields into L scenes according to the screened characteristic information, and generating a scene set;
constructing a hydrological forecasting model, and calibrating the hydrological forecasting model under L scenes in a scene set;
and determining a scene closest to the current state based on the feature information screened out from the current state of the forecast object basin, and predicting the future process of the forecast object basin by adopting a hydrological forecasting model corresponding to the scene.
2. The hydrological prediction method based on spatiotemporal big data as claimed in claim 1, further comprising:
and if the correlation degrees of the current state of the forecast object basin and all scenes in the scene set are smaller than the threshold value of the correlation degrees, adding the current state of the forecast object basin into the scene set.
3. The hydrologic prediction method based on spatiotemporal big data according to claim 1, wherein said obtaining a multi-source spatiotemporal historical dataset of a forecast object comprises:
extracting static characteristic information of a watershed to be predicted;
extracting the space-time distribution information of the vegetation index of the watershed to be predicted, the soil humidity of different depths, the surface air temperature and the precipitation;
extracting rainfall and water level information of a watershed to be predicted;
a data set is established based on the above various information.
4. The hydrologic prediction method based on spatio-temporal big data according to claim 1, characterized in that said extracting M-field flood process comprises:
presetting a historical flood peak flow threshold value, and extracting M fields of flood with the flow larger than the flow threshold value according to the process of intensively forecasting the historical flow fluctuation of the object by multi-source time-space historical data;
obtaining the information of each flood according to the starting and ending time of M floods and the multi-source time-space historical data set;
and extracting N characteristics based on the information of each flood field to generate an array with dimension of M multiplied by N.
5. The method for hydrologic prediction based on spatio-temporal big data according to claim 4, wherein said screening out the feature information with the largest correlation and the smallest redundancy with the incoming water process in each flood process comprises:
normalizing elements in the array of the dimension of M multiplied by N;
clustering the N groups of features into K classes;
and selecting the index with the maximum correlation degree with the water incoming process from each class of characteristic indexes, generating K multiplied by M dimensional characteristic index information with M fields of flood, and taking the K multiplied by M dimensional characteristic index information as the characteristic information with the maximum correlation and the minimum redundancy of the water incoming of the forecast object.
6. The spatio-temporal big data-based hydrological prediction method according to claim 5, wherein said dividing M-field flood process into L scenes comprises:
based on the generated K multiplied by M dimensional characteristic index information, a decision tree algorithm is adopted to divide M-field flood into L types, namely L scenes.
7. The method for hydrologic prediction based on spatio-temporal big data according to claim 1, wherein said rating hydrologic prediction models for L scenes in a scene set comprises:
and constructing a hydrological prediction model suitable for the prediction object drainage basin, and calibrating the hydrological prediction model under the L scenes respectively based on an automatic rate parameter algorithm.
8. The system for controlling transient overvoltage of sending-end system according to claim 1, wherein said determining a scene closest to a current state comprises:
extracting and forecasting the current state of the drainage basin to screen out the characteristic information which is maximally related to the drainage basin and has the minimum redundancy during real-time forecasting;
and finding out a scene closest to the current state from the scene set based on the characteristic information.
9. A hydrological prediction method based on space-time big data is characterized by comprising the following steps:
the data acquisition module is used for acquiring a multi-source time-space historical data set of a forecast object;
the characteristic generating module is used for extracting an M field flood process from the multi-source time-space historical data set;
screening out the characteristic information which is maximally related to the water incoming process and has minimum redundancy in each flood process;
the scene dividing module is used for dividing the M-field flood process into L scenes according to the screened characteristic information and generating a scene set;
the model determining module is used for constructing a hydrological forecasting model and calibrating the hydrological forecasting model under L scenes in the scene set;
and the forecasting module is used for determining a scene closest to the current state based on the characteristic information screened out from the current state of the forecasting object basin, and forecasting the future water process of the forecasting object basin by adopting a hydrological forecasting model corresponding to the scene.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210502777.2A CN114792168A (en) | 2022-05-10 | 2022-05-10 | Hydrological prediction method and system based on space-time big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210502777.2A CN114792168A (en) | 2022-05-10 | 2022-05-10 | Hydrological prediction method and system based on space-time big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114792168A true CN114792168A (en) | 2022-07-26 |
Family
ID=82461995
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210502777.2A Pending CN114792168A (en) | 2022-05-10 | 2022-05-10 | Hydrological prediction method and system based on space-time big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114792168A (en) |
Citations (3)
| 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 |
| CN110619432A (en) * | 2019-09-17 | 2019-12-27 | 长江水利委员会水文局 | Feature extraction hydrological forecasting method based on deep learning |
| CN112711917A (en) * | 2021-03-26 | 2021-04-27 | 长江水利委员会水文局 | Real-time flood forecasting intelligent method based on face recognition algorithm |
-
2022
- 2022-05-10 CN CN202210502777.2A patent/CN114792168A/en active Pending
Patent Citations (3)
| 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 |
| CN110619432A (en) * | 2019-09-17 | 2019-12-27 | 长江水利委员会水文局 | Feature extraction hydrological forecasting method based on deep learning |
| CN112711917A (en) * | 2021-03-26 | 2021-04-27 | 长江水利委员会水文局 | Real-time flood forecasting intelligent method based on face recognition algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 刘可新等: "基于主成分分析的K均值聚类法在洪水预报中的应用", 武汉大学学报（工学版）, vol. 48, no. 4, 31 August 2015 (2015-08-31), pages 447 - 458 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114254561B (en) | Waterlogging prediction method, system and storage medium | |
| CN109840587B (en) | Reservoir warehousing flow prediction method based on deep learning | |
| CN111612055A (en) | Weather situation typing method, air pollution condition prediction method and device | |
| CN111861023A (en) | Statistical-based hybrid wind power prediction method and device | |
| CN115730684A (en) | Air quality detection system based on LSTM-CNN model | |
| CN116702627B (en) | Urban storm waterlogging rapid simulation method based on deep convolutional neural network | |
| Zhuang et al. | Long-lead prediction of extreme precipitation cluster via a spatiotemporal convolutional neural network | |
| CN111325376A (en) | Wind speed prediction method and device | |
| CN113570132A (en) | Wind power prediction method for space-time meteorological feature extraction and deep learning | |
| Zhang et al. | A multi-strategy-mode waterlogging-prediction framework for urban flood depth | |
| Yu et al. | The study of artificial intelligence for predicting land use changes in an arid ecosystem | |
| CN117332291B (en) | Distributed photovoltaic-oriented regional resource monitoring layout method and system | |
| KR101703972B1 (en) | System and method for predicting groundwater potential area using spatial information | |
| CN117892162A (en) | Watershed runoff forecasting method based on nonnegative matrix factorization and machine learning | |
| Xu et al. | Extremecast: Boosting extreme value prediction for global weather forecast | |
| CN114792168A (en) | Hydrological prediction method and system based on space-time big data | |
| CN115438590B (en) | Precipitation prediction correction method and system based on BP neural network | |
| CN115376309B (en) | Missing traffic data restoration method based on multi-view time matrix decomposition | |
| CN116454875A (en) | Regional wind farm mid-term power probability prediction method and system based on cluster division | |
| CN115689067A (en) | Solar irradiance prediction method, device and storage medium | |
| Zhang et al. | Modelling urban expansion with cellular automata supported by urban growth intensity over time | |
| CN117154704B (en) | Photovoltaic power prediction method based on multiscale space-time diagram attention convolution network | |
| CN117391221B (en) | NDVI prediction integrated optimization method and system based on machine learning | |
| CN118174291A (en) | Distributed photovoltaic output self-adaptive prediction method and device under multi-time space scale | |
| Lian et al. | Mining persistent and dynamic spatio-temporal change in global climate 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 |