Determination of Surface Precipitation Type Based on the Data Fusion Approach

作     者：Marek PÓŁROLNICZAK Leszek KOLENDOWICZ Bartosz CZERNECKI Mateusz TASZAREK Gabriella TÓTH Marek PÓŁROLNICZAK;Leszek KOLENDOWICZ;Bartosz CZERNECKI;Mateusz TASZAREK;Gabriella TÓTH

作者机构：Department of Meteorology and ClimatologyInstitute of Physical Geography and Environmental PlanningAdam Mickiewicz University61-680 PoznańPoland Department of Weather Forecasting and ClimatologyHungarian Meteorological ServiceH-1024 BudapestHungary 

出 版 物：《Advances in Atmospheric Sciences》 (大气科学进展（英文版）)

年 卷 期：2021年第38卷第3期

页      面：387-399页

核心收录：

学科分类：07[理学] 070601[理学-气象学] 0706[理学-大气科学] 0816[工学-测绘科学与技术] 0825[工学-航空宇航科学与技术] 

基　　金：This research was supported by grants from the Polish National Science Centre(project numbers 2015/19/B/ST10/02158 and 2017/27/B/ST10/00297) The computations were partly performed in the PoznańSupercomputing and Networking Center(Grant No.331) We would like to thank the Polish Institute of Meteorology and Water Management-National Research Institute,for providing the radar-derived products 

主　　题：precipitation type forecast data fusion Random Forest ERA5 Poland 

摘      要：Hazardous events related to atmospheric precipitation depend not only on the intensity of surface precipitation,but also on its *** related to determination of the precipitation type(PT)leads to financial losses in many areas of human activity,such as the power industry,agriculture,transportation,and many *** this study,we use machine learning(ML)algorithms with the data fusion approach to more accurately determine surface *** on surface synoptic observations,ERA5 reanalysis,and radar data,we distinguish between liquid,mixed,and solid precipitation *** study domain considers the entire area of Poland and a period from 2015 to *** purpose of this work is to address the question:“How can ML techniques applied in observational and NWP data help to improve the recognition of the surface PT?Despite testing 33 parameters,it was found that a combination of the near-surface air temperature and the depth of the warm layer in the 0-1000 m above ground level(AGL)layer contains most of the signal needed to determine surface *** accrued probability of detection for liquid,solid,and mixed PTs according to the developed Random Forest model is 98.0%,98.8%,and 67.3%,*** application of the ML technique and data fusion approach allows to significantly improve the robustness of PT prediction compared to commonly used baseline models and provides promising results for operational forecasters.