首页|Researchers from North China Electric Power University Report Details of New Stu dies and Findings in the Area of Machine Learning (A Forecasting Method for Corr ected Numerical Weather Prediction Precipitation Based On Modal Decomposition an d ...)
Researchers from North China Electric Power University Report Details of New Stu dies and Findings in the Area of Machine Learning (A Forecasting Method for Corr ected Numerical Weather Prediction Precipitation Based On Modal Decomposition an d ...)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
2024 OCT 09 (NewsRx)-By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Investigators publish new report on Machine Learn ing. According to news reporting out of Beijing, People's Republic of China, by NewsRx editors, research stated, "Numerical weather models often face significan t challenges in achieving high prediction accuracy. To enhance the predictive pe rformance of these models, a solution involving the integration of deep learning algorithms has been proposed." Financial support for this research came from National Natural Science Foundatio n of China (NSFC). Our news journalists obtained a quote from the research from North China Electri c Power University, "This paper introduces a machine learning approach for corre cting the numerical weather forecast results from the Weather Research and Forec asting (WRF) model. Initially, the WRF model is used to simulate summer precipit ation in the Jinsha River Basin. Subsequently, the adaptive noise-robust empiric al mode decomposition (CEEMDAN) method is employed to decompose WRF simulation e rrors. These decomposed subsequences are then input into four machine learning a lgorithms and two metaheuristic optimization algorithms to predict the error seq uences. Finally, the predicted error subsequences are merged and superimposed on the WRF simulation values to obtain the corrected precipitation. Research findi ngs demonstrate that the integration of machine learning algorithms with WRF sig nificantly improves prediction accuracy. The correlation coefficient of the opti mal model increases by 158%, and Nash-Sutcliffe Efficiency (NSE) in creases by 149% compared to before correction."
BeijingPeople's Republic of ChinaAsi aAlgorithmsCyborgsEmerging TechnologiesMachine LearningNorth China Ele ctric Power University
NETL
NSTL
