文献类型：期刊文献

英文题名：Enhancing Extreme Precipitation Forecasts through Machine Learning Quality Control of Precipitable Water Data from Satellite FengYun-2E: A Comparative Study of Minimum Covariance Determinant and Isolation Forest Methods

作者：Shen, Wenqi[1,2];Chen, Siqi[2];Xu, Jianjun[2,3];Zhang, Yu[1];Liang, Xudong[4];Zhang, Yong[5]

机构：[1]Guangdong Ocean Univ, Coll Ocean & Meteorol, Zhanjiang 524088, Peoples R China;[2]Guangdong Ocean Univ, CMA GDOU Joint Lab, Zhanjiang 524088, Peoples R China;[3]Guangdong Ocean Univ, Shenzhen Inst, Shenzhen 518120, Peoples R China;[4]Chinese Acad Meteorol Sci, State Key Lab Severe Weather, Beijing 100081, Peoples R China;[5]China Meteorol Adm, Meteorol Observat Ctr, Beijing 100081, Peoples R China

年份：2024

卷号：16

期号：16

外文期刊名：REMOTE SENSING

收录：SCI-EXPANDED(收录号：WOS:001304891600001)、、EI(收录号：20243516965829)、Scopus(收录号：2-s2.0-85202439918)、WOS

基金：This work was jointly supported by the National Natural Science Foundation of China, Grant No. 42130605; the Major Program of the National Natural Science Foundation of China, Grant No. 72293604; and the National Natural Science Foundation of China, Grant No. 42375159.

语种：英文

外文关键词：machine learning quality control; satellite data assimilation; numerical weather prediction; heavy precipitation forecasting; precipitable water

外文摘要：Variational data assimilation theoretically assumes Gaussian-distributed observational errors, yet actual data often deviate from this assumption. Traditional quality control methods have limitations when dealing with nonlinear and non-Gaussian-distributed data. To address this issue, our study innovatively applies two advanced machine learning (ML)-based quality control (QC) methods, Minimum Covariance Determinant (MCD) and Isolation Forest, to process precipitable water (PW) data derived from satellite FengYun-2E (FY2E). We assimilated the ML QC-processed TPW data using the Gridpoint Statistical Interpolation (GSI) system and evaluated its impact on heavy precipitation forecasts with the Weather Research and Forecasting (WRF) v4.2 model. Both methods notably enhanced data quality, leading to more Gaussian-like distributions and marked improvements in the model's simulation of precipitation intensity, spatial distribution, and large-scale circulation structures. During key precipitation phases, the Fraction Skill Score (FSS) for moderate to heavy rainfall generally increased to above 0.4. Quantitative analysis showed that both methods substantially reduced Root Mean Square Error (RMSE) and bias in precipitation forecasting, with the MCD method achieving RMSE reductions of up to 58% in early forecast hours. Notably, the MCD method improved forecasts of heavy and extremely heavy rainfall, whereas the Isolation Forest method demonstrated a superior performance in predicting moderate to heavy rainfall intensities. This research not only provides a basis for method selection in forecasting various precipitation intensities but also offers an innovative solution for enhancing the accuracy of extreme weather event predictions.