CN112561125A - Wind speed forecast multi-data fusion correction method - Google Patents
Wind speed forecast multi-data fusion correction method Download PDFInfo
- Publication number
- CN112561125A CN112561125A CN202011308401.5A CN202011308401A CN112561125A CN 112561125 A CN112561125 A CN 112561125A CN 202011308401 A CN202011308401 A CN 202011308401A CN 112561125 A CN112561125 A CN 112561125A
- Authority
- CN
- China
- Prior art keywords
- wind speed
- forecast
- correction
- mode
- fusion
- 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
- 238000012937 correction Methods 0.000 title claims abstract description 45
- 230000004927 fusion Effects 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000012544 monitoring process Methods 0.000 claims abstract description 14
- 238000005457 optimization Methods 0.000 claims abstract description 12
- 238000012628 principal component regression Methods 0.000 claims abstract description 12
- 238000002156 mixing Methods 0.000 claims abstract description 8
- 230000001419 dependent effect Effects 0.000 claims description 7
- 239000006185 dispersion Substances 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 10
- 238000011160 research Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000004445 quantitative analysis Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000009897 systematic 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Abstract
The invention discloses a wind speed forecast multi-data fusion correction method, which comprises the following steps of firstly, adopting a multi-element principal component regression technology to carry out optimization correction on a mode forecast wind speed to obtain an optimized correction mode forecast wind speed; and then, fusing and optimizing the mode forecast wind speed and the optimized correction mode forecast wind speed by adopting a Linear Blending fusion technology to obtain a fused and optimized forecast wind speed. The prediction wind speed optimized by the correction scheme has better correlation with monitoring, the dispersion of the prediction data is obviously reduced, and the root mean square error of the wind speed is also obviously improved after further fusion and optimization.
Description
Technical Field
The invention belongs to the technical field of weather forecast.
Background
The ocean resources in Zhejiang province are abundant, the total length of the coastline is 6486.24 kilometers, which accounts for 20.3% of China and is the top of China. There are more than 3000 coastal islands, which are the most provinces of islands in China. Five main resources of ports, fishery, tourism, oil gas and mudflat are extremely thick, and the combination advantage is remarkable. The daily work of these industries is closely related to the wind speed live and forecast for the region, and thus wind forecasting has been one of the meteorological services of great concern to governments and people in coastal regions.
The real-time wind measurement data on the coastal region and the ocean is less, and the forecasting and service requirements are more dependent on the satellite inversion wind field and the numerical weather forecast. Around a series of key problems of multi-source wind measurement and forecast technology development, quantitative evaluation, information fusion, comprehensive application and the like, scholars at home and abroad do a lot of work with great effect. In the aspect of statistical technology, Wangxin et al propose a correction method for 24h short-term wind speed numerical prediction by combining harmonic analysis and artificial neural network, the average absolute error of two independent sample tests is respectively reduced by 26.6% and 28.8%, and the systematic deviation of wind speed numerical prediction is obviously reduced after correction. Yang Cheng and the like use partial least square regression technology to correct and evaluate the near-ground wind speed of the mode forecast of the mesoscale region in Zhejiang province, and quantitative analysis can prove that the overall improvement effect in the west region of Zhejiang is the best, and the effective site accounts for 91.7%; the improvement sites in the middle area account for 86.5%; improved sites in the eastern coastal region account for 67%. In the aspect of multi-element data fusion, Wujiamin and the like perform assimilation tests on QuikSCAT, windSAT and multi-source anemometry fusion data by utilizing a WRF mode and a 3DVAR assimilation system thereof, and the results show that: the different data have different influences on wind field simulation, and the effect of assimilating multi-source fusion data of the satellite and the satellite is the best, and the result is QuikSCAT times. Huhaichuan and the like utilize an ECMWF ensemble prediction 10m wind field and 88 representative sites on the coast and the inshore of China to observe wind speed live, establish an ECMWF ensemble prediction mode-based Chinese inshore ocean surface 10m wind speed objective correction method, comprehensively consider the prediction probability of historical data and the distribution condition of each member of the ensemble prediction to perform objective correction, and corrected wind speed products have good prediction effects on the weather process of inshore cold air and typhoon in China.
The previous research results show that the statistical correction method and the data fusion technology have better improvement effect on the refined forecast correction of the wind speed. Wind measurement in coastal areas is often local due to the influence of factors such as terrain and altitude.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide a wind speed forecast multi-data fusion correction method, improve the refinement level of wind speed forecast in coastal areas, and provide effective and reasonable guidance suggestions for daily operation of multiple industries such as ship entering and leaving port planning, tourism industry development, fishing industry safety operation and the like in the areas.
In order to solve the technical problems, the invention adopts the following technical scheme:
a wind speed forecast multi-data fusion correction method comprises the following steps:
firstly, optimizing and correcting the mode forecast wind speed by adopting a multi-element principal component regression technology to obtain an optimized and corrected mode forecast wind speed;
and then, fusing and optimizing the mode forecast wind speed and the optimized correction mode forecast wind speed by adopting a Linear Blending fusion technology to obtain a fused and optimized forecast wind speed.
Preferably, the multi-element principal component regression technology uses the air pressure, the air temperature, the relative humidity and the 10-minute average wind speed which are obtained by observation of the corresponding meteorological monitoring station as dependent variables; and (3) taking the air pressure, temperature and humidity of the mode forecast and the near-ground latitude/longitude wind speed as independent variables, taking forecast values and observation values 20 days before correction, and modeling data at the same forecast time.
Preferably, assuming that a forecast result with a reporting time t is modeled, a forecast value and an observed value 20 days before correction are selected as historical samples, and corresponding dependent variable y and independent variable x are calculatediThen, a regression coefficient alpha of each independent variable is calculated by a multi-element principal component regression technologyiFinally, the argument X of the time t of the start of the report is usediThe wind speed correction result Y at the future time t + Δ t is obtained.
Preferably, the forecasting weight of the mode forecasting wind speed and the forecasting weight of the optimized and corrected mode forecasting wind speed are calculated by adopting a factor weight method, and then fusion optimization is carried out.
Preferably, the monitored wind speed is VobsMode forecast wind speed is VwrfOptimizing the correction mode to forecast the wind speed as Vdz_obsFusing the optimized forecast wind speed Vmix，
If m mode prediction results are set and m optimized correction prediction results are correspondingly generated, the wind speed at nt moments after fusion is predicted:
where F is the weight of each prediction amount calculated by the factor weight method.
The method adopts a multi-element principal component regression technology to optimize and correct the mode forecast wind speed, and adopts a Linear Blending fusion technology to fuse and optimize the mode forecast wind speed and the optimized and corrected mode forecast wind speed to obtain a fused and optimized forecast wind speed. Therefore, the following beneficial effects are achieved:
the prediction wind speed optimized by the correction scheme has better correlation with monitoring, the dispersion of the prediction data is obviously reduced, and the root mean square error of the wind speed is also obviously improved after further fusion and optimization.
And (3) quantitatively detecting the difference between the wind speed and the actually monitored wind speed after the initial mode prediction and the final fusion optimization of all the stations, wherein most of the stations have positive effects after being corrected by the method, and the improvement effect of 27% of the stations is over 40% after being corrected.
The following detailed description will explain the present invention and its advantages.
Drawings
The invention is further described with reference to the accompanying drawings and the detailed description below:
FIG. 1 is a flow chart of a wind speed forecast multi-data fusion correction method according to the present invention.
FIG. 2 is a flow chart of optimization correction of formula forecasted wind speed by dynamic statistics optimization modeling.
Fig. 3 is a conceptual diagram of errors of different prediction schemes.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments of the present invention, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention effectively combines effective wind speed fine research technical methods in the previous research, reasonably optimizes the timeliness difference between monitoring data, forecast data and actual application, aims to improve the fine level of wind power forecast in coastal areas, and provides effective and reasonable guidance suggestions for daily operation of multiple industries such as ship port-entering and port-exiting planning, tourism industry development, fishing industry safety operation and the like in the areas.
As shown in fig. 1, a wind speed forecast multi-data fusion correction method includes the following steps:
firstly, optimizing and correcting the mode forecast wind speed by adopting a multi-element principal component regression technology to obtain an optimized and corrected mode forecast wind speed;
and then, fusing and optimizing the mode forecast wind speed and the optimized correction mode forecast wind speed by adopting a Linear Blending fusion technology to obtain a fused and optimized forecast wind speed.
As shown in FIG. 2, the present invention adopts a multi-factor principal component regression technique to optimize and correct the pattern prediction, and can simultaneously realize three mathematical analysis techniques of multiple regression modeling, data structure simplification and correlation analysis between two groups of variables. The multi-element principal component regression technology uses the air pressure, the air temperature, the relative humidity and the 10-minute average wind speed which are obtained by observation of a corresponding meteorological monitoring station as dependent variables; mode-forecasted barometric pressure, temperature, humidity and near-ground weft/warp wind speed as selfAnd (4) taking the forecast value and the observed value 20 days before correction, and modeling the data at the same forecast time. Assuming that a forecast result with the time of starting to report as t is modeled, selecting a forecast value and an observed value 20 days before correction as historical samples, and calculating corresponding dependent variable y and independent variable xiThen, a regression coefficient alpha of each independent variable is calculated by a multi-element principal component regression technologyiFinally, the argument X of the time t of the start of the report is usediThe wind speed correction result Y at the future time t + Δ t is obtained.
The mainstream fusion technology comprises bagging, boosting, Blending, stacking and the like, and the idea of the Linear Blending fusion technology is adopted according to the actual application requirement. The fusion technology considers that uniform fusion is suitable for use when the performance of the individual learners is close, and when the performance of the individual learners is greatly different, the weighted average is used for obtaining the optimal weight for each data set and then fusing. Because the performance difference of different wind speed optimization schemes cannot be judged, in order to ensure that the fusion technology achieves the optimal effect, the invention firstly calculates the forecast weight of each scheme by using a factor weight method and then performs fusion optimization.
FIG. 3 is a conceptual diagram of errors of different prediction schemes. In the theoretical mode prediction, due to the fact that a parameterization scheme of the model prediction considers numerous physical processes, the prediction is always kept continuous, and errors tend to be stable along with the extension of prediction timeliness. The dynamic statistics forecasting scheme of monitoring is considered, the influence of monitoring data is applied to the early forecasting stage, and the forecasting error is smaller than the mode forecasting error. However, as the prediction time is prolonged, the influence of the monitoring data is gradually reduced, and the prediction error is linearly increased. The predicted errors of both will coincide at some point in time as shown in fig. 3. Therefore, in order to effectively reduce errors, the research plans to inversely calculate the forecast effect weights F of the two types of errors at different timeliness through historical data, and then performs data fusion.
Monitoring wind speed is called VobsThe mode forecasted wind speed is called VwrfBased on the monitoring, the forecast wind speed is corrected and called Vdz_obsThe fusion forecast wind speed is called Vmix。
If m mode prediction results are provided, m correction predictions can be generated according to the dynamic statistics optimization module, and the wind speed at nt moments after fusion is predicted:
f in the formula is the weight of each prediction amount calculated by the factor weight method.
Analysis of individual case
The 09 # ultrastrong typhoon "liqima" in 2019 was generated on the north west pacific ocean surface in the southeast direction in taiwan, and then moved to the northwest direction, and the intensity was gradually strengthened. When the wind power is about 45 minutes at 01 th day 8, 10 th day, the wind power reaches 16 grade around the center, and the lowest air pressure is 930 hPa. Under the influence of the wind, 757 thousands of people in Zhejiang caused by the 'Liqima' in 14 months and 8 death of 45 people, the direct economic loss is 407.2 hundred million yuan, which is the fifth super-strong typhoon landing in continental areas of China since 1949.
The landing point is located near the south town of the Wenling mountain city, the near-ground wind speed exceeding 50m/s (16-level) can be monitored in the southeast direction of the Wenling mountain city, and the wind speed of the whole inland is more than 10m/s because the inland is just in the landing stage of typhoon and the wind speed of the inland area does not have a larger magnitude. The mode forecast simultaneously simulates the ground wind speed, so that the landing position of typhoon and the asymmetric structure of a typhoon windband are better simulated, but the forecast of the mode to the maximum wind speed point of which the southeast azimuth of the landing position exceeds 50m/s is smaller, and the forecast wind speed is less than 30m/s at the position. Meanwhile, the wind speed forecast of the whole inland area is larger, and the forecast wind speed is about 20 m/s. The wind speed is forecasted through an optimized correction mode, the depiction near the typhoon wind ring is not clear, and the asymmetric dynamic structure of the typhoon wind ring cannot be completely reflected. But the scheme has obvious improvement on correction of coastal wind speed, and the position of the maximum wind speed point is predicted. There is also a significant improvement in the prediction of inland wind speed. But at the same time the solution relies heavily on monitored data, i.e. there is a significant improvement in forecasting wind speed at locations where there is monitored data.
According to the invention, a Linear Blending fusion technology is adopted to perform fusion optimization on the forecast wind speed of No. 09 superstrong typhoon Liqima in 2019, and the fact that in a login stage, the fused forecast wind speed not only improves a larger mode forecast but also adjusts a smaller correction forecast, and the fusion forecast wind speed in coastal four cities or inland areas is more in line with actual monitoring and is closest to the monitoring fact. As for the whole process wind speed forecasting, quantitative analysis can know that the improvement effect of the fusion forecasting wind speed is optimal within 12 hours, and the forecasting effects of the fusion forecasting wind speed, the fusion forecasting wind speed and the fusion forecasting wind speed are not ideal after the forecasting aging time exceeds 18 hours.
While the invention has been described with reference to specific embodiments, it will be understood by those skilled in the art that the invention is not limited thereto, and may be embodied in other forms without departing from the spirit or essential characteristics thereof. Any modification which does not depart from the functional and structural principles of the present invention is intended to be included within the scope of the claims.
Claims (5)
1. A wind speed forecast multi-data fusion correction method is characterized by comprising the following steps:
firstly, optimizing and correcting the mode forecast wind speed by adopting a multi-element principal component regression technology to obtain an optimized and corrected mode forecast wind speed;
and then, fusing and optimizing the mode forecast wind speed and the optimized correction mode forecast wind speed by adopting a Linear Blending fusion technology to obtain a fused and optimized forecast wind speed.
2. The method for fusion correction of wind speed forecast multiple data according to claim 1, wherein: the multi-element principal component regression technology uses the air pressure, the air temperature, the relative humidity and the 10-minute average wind speed which are obtained by observation of a corresponding meteorological monitoring station as dependent variables; and (3) taking the air pressure, temperature and humidity of the mode forecast and the near-ground latitude/longitude wind speed as independent variables, taking forecast values and observation values 20 days before correction, and modeling data at the same forecast time.
3. The method as claimed in claim 2, wherein the wind speed forecast multi-data fusion correction method comprises: supposing that the forecast result with the time t of starting to report is establishedFirstly, selecting the forecast value and observed value 20 days before correction as historical samples, and calculating the corresponding dependent variable y and independent variable xiThen, a regression coefficient alpha of each independent variable is calculated by a multi-element principal component regression technologyiFinally, the argument X of the time t of the start of the report is usediThe wind speed correction result Y at the future time t + Δ t is obtained.
4. The method for fusion correction of wind speed forecast multiple data according to claim 1, wherein: and calculating the forecasting weight of the mode forecasting wind speed and optimizing the forecasting weight of the mode forecasting wind speed after correction by adopting a factor weight method, and then performing fusion optimization.
5. The method as claimed in claim 4, wherein the wind speed forecast multi-data fusion correction method comprises: monitoring wind speed as VobsMode forecast wind speed is VwrfOptimizing the correction mode to forecast the wind speed as Vdz_obsFusing the optimized forecast wind speed Vmix，
If m mode prediction results are set and m optimized correction prediction results are correspondingly generated, the wind speed at nt moments after fusion is predicted:
where F is the weight of each prediction amount calculated by the factor weight method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011308401.5A CN112561125A (en) | 2020-11-20 | 2020-11-20 | Wind speed forecast multi-data fusion correction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011308401.5A CN112561125A (en) | 2020-11-20 | 2020-11-20 | Wind speed forecast multi-data fusion correction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112561125A true CN112561125A (en) | 2021-03-26 |
Family
ID=75044082
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011308401.5A Pending CN112561125A (en) | 2020-11-20 | 2020-11-20 | Wind speed forecast multi-data fusion correction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112561125A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113516320A (en) * | 2021-09-14 | 2021-10-19 | 国能日新科技股份有限公司 | Wind speed correction and predicted wind speed optimization method and device based on multi-objective genetic algorithm |
| CN116205138A (en) * | 2023-01-16 | 2023-06-02 | 中国气象局广州热带海洋气象研究所（广东省气象科学研究所） | Wind speed forecast correction method and device |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109358381A (en) * | 2018-09-12 | 2019-02-19 | 浙江省气象科学研究所 | A kind of website forecast correction wind method |
-
2020
- 2020-11-20 CN CN202011308401.5A patent/CN112561125A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109358381A (en) * | 2018-09-12 | 2019-02-19 | 浙江省气象科学研究所 | A kind of website forecast correction wind method |
Non-Patent Citations (4)
| Title |
|---|
| NIU CODE: ""模型融合 Blending 和 Stacking"", 《百度》 * |
| 杨程等: "基于偏最小二乘回归的区域换式风速预报订正技术研究", 《气象》 * |
| 石岚等: "多模式风速融合预报应用研究", 《高原气象》 * |
| 陈昱文等: "基于ECMWF产品的站点气温预报集成学习误差订正", 《应用气象学报》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113516320A (en) * | 2021-09-14 | 2021-10-19 | 国能日新科技股份有限公司 | Wind speed correction and predicted wind speed optimization method and device based on multi-objective genetic algorithm |
| CN113516320B (en) * | 2021-09-14 | 2021-12-10 | 国能日新科技股份有限公司 | Wind speed correction and predicted wind speed optimization method and device based on multi-objective genetic algorithm |
| CN116205138A (en) * | 2023-01-16 | 2023-06-02 | 中国气象局广州热带海洋气象研究所（广东省气象科学研究所） | Wind speed forecast correction method and device |
| CN116205138B (en) * | 2023-01-16 | 2023-11-03 | 中国气象局广州热带海洋气象研究所（广东省气象科学研究所） | Wind speed forecast correction method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108227041B (en) | Horizontal visibility forecasting method based on site measured data and mode result | |
| CN114280696A (en) | Intelligent sea fog level forecasting method and system | |
| Genç | Determination of the most appropriate site selection of wind power plants based Geographic Information System and Multi-Criteria Decision-Making approach in Develi, Turkey | |
| CN111428942B (en) | Line icing thickness prediction method for extracting micro-terrain factors based on variable grid technology | |
| CN109726867B (en) | High-resolution electric power weather forecasting method based on multi-mode set | |
| CN112561125A (en) | Wind speed forecast multi-data fusion correction method | |
| El Alimi et al. | Modeling and investigation of the wind resource in the gulf of Tunis, Tunisia | |
| CN110766134A (en) | Photovoltaic power station short-term power prediction method based on cyclic neural network | |
| CN113128758B (en) | Maximum wave height forecasting system constructed based on offshore buoy wave observation data | |
| CN113987912A (en) | Pollutant on-line monitoring system based on geographic information | |
| CN108808671A (en) | A kind of short-term wind speed DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM method of wind power plant | |
| Tan et al. | Short term wind energy resource prediction using WRF model for a location in western part of Turkey | |
| Wang et al. | Decreasing precipitation occurs in daily extreme precipitation intervals across China in observations and model simulations | |
| CN114511061A (en) | Shoreside region sea fog visibility forecasting method based on depth neural network | |
| CN112001090A (en) | Wind field numerical simulation method | |
| CN116842839A (en) | Power distribution facility rain and waterlogging submerged power outage risk prediction method and related device | |
| CN115511192A (en) | Rainfall forecasting method and system based on lightning data assimilation | |
| CN111596384B (en) | Inclined plane radiation prediction method based on weather type effective identification | |
| CN115912334A (en) | Method for establishing prediction model of output guarantee rate of wind power plant and prediction method | |
| Yu et al. | An operational application of NWP models in a wind power forecasting demonstration experiment | |
| CN113032510A (en) | LBGM method initial value disturbance generation method based on Gaussian weight | |
| Nishida et al. | Optimization of integrated weather routing systems for sailing cargo ships | |
| CN117828490B (en) | Typhoon disaster forecasting method and system based on ensemble learning | |
| Tang et al. | Assessment of coastal wind energy resources in Ningbo Zhoushan Port Area based on WRF model and MERRA-2 data | |
| CN114626578B (en) | Method for forecasting freezing rain by using artificial intelligence |
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 |
Application publication date: 20210326 |
|
| RJ01 | Rejection of invention patent application after publication |