Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Wind speed prediction method based on ensemble prediction data

A technology of ensemble forecasting and wind speed forecasting, which is applied in the fields of meteorological research and forecasting, can solve problems such as system errors and model errors, and achieve the effect of improving the impact of forecasting accuracy, high precision, and improving wind speed forecasting performance

Pending Publication Date: 2019-11-22
TIANJIN UNIV
View PDF9 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The data provided by the ensemble forecast can provide a reference for the forecast work of meteorological researchers, but there are inevitable model errors and system errors in the results, and the ensemble forecast results need to be corrected or regressed based on the forecast results when they are used

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Wind speed prediction method based on ensemble prediction data
  • Wind speed prediction method based on ensemble prediction data
  • Wind speed prediction method based on ensemble prediction data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] In order to overcome the deficiencies of the prior art, the present invention aims to propose a wind speed prediction method based on ensemble forecast data, which can better use the means of data mining and the results of ensemble forecast members to improve the accuracy of wind speed forecast. According to the 51 forecast members produced by the ensemble forecast product ECWMF for each forecast period, the CART pruning method is used to select the optimal members, and the optimal members are used to construct the GBDT model, and finally the wind speed prediction based on the ensemble forecast data is realized. For this reason, the technical scheme that the present invention adopts is, a kind of wind speed prediction method based on ensemble forecast data, and the steps are as follows:

[0033] (1) Preprocessing of ensemble forecast data

[0034] 1) Use the measured wind speed data of platform A in Bohai Bay to determine the wind speed tag data;

[0035] 2) Read out t...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to the field of meteorological research and forecasting, and provides a wind speed forecasting method based on ensemble forecasting data. The method can better use the means of data mining and the results of ensemble forecasting members to improve the accuracy of wind speed forecasting. Therefore, the technical scheme adopts a wind speed prediction method based on ensemble prediction data. A product is ensembled and forecasted according to the European mid-term weather forecast center; generating 51 forecasting members by each forecasting timeliness; selecting an optimalmember by using a CART (Classification Analysis Tree) pruning method; and the optimal member is utilized to construct a GBDT (Graphic Boosting Definition Tree) model, and finally, wind speed prediction based on ensemble prediction data is realized. The method is mainly applied to meteorological research and forecast occasions.

Description

technical field [0001] The invention relates to the fields of meteorological research and forecasting, in particular to a wind speed forecasting method based on ensemble forecast data. Background technique [0002] Wind speed prediction is one of the objects that people pay more attention to in weather forecasting. Whether the wind speed prediction results are accurate or not affects the groups living and working in the coast. [0003] Wind speed prediction generally adopts the method of ensemble forecasting. Ensemble forecasting is a means of weather forecasting. It is derived from numerical forecasting. Through mathematical modeling of the physical laws inside the atmosphere, the air thermodynamics, capacity conservation, and water vapor change laws of the real atmosphere are simulated. Wait. Usually, the mathematical equations for simulating the real atmospheric state are relatively large, and these models are calculated by high-performance computers to obtain some weath...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/18G01P5/00
CPCG06F17/18G01P5/00
Inventor 路志英倪天琦闫靖春
Owner TIANJIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products