Articles | Volume 14, issue 11
https://doi.org/10.5194/amt-14-7007-2021
https://doi.org/10.5194/amt-14-7007-2021
Research article
 | 
05 Nov 2021
Research article |  | 05 Nov 2021

Leveraging machine learning for quantitative precipitation estimation from Fengyun-4 geostationary observations and ground meteorological measurements

Xinyan Li, Yuanjian Yang, Jiaqin Mi, Xueyan Bi, You Zhao, Zehao Huang, Chao Liu, Lian Zong, and Wanju Li

Data sets

ERA5 hourly data on single levels from 1979 to present Copernicus Climate Change Service https://cds.climate.copernicus.eu/cdsapp#!/dataset/reanalysis-era5-single-levels?tab=form

AGRI L1 Full Disk, 4KM, Cloud Top Temperature(CTT), Cloud Top Height(CTH), Cloud Type(CLT), Cloud Phase(CLP) FENGYUN Satellite Data Center (under National Satellite Meteorological Center of China Meteorological Administration) http://satellite.nsmc.org.cn/PortalSite/Data/Satellite.aspx

Advanced Spaceborne Thermal Emission and Reflection Radiometer Global Digital Elevation Model 30M resolution digital elevation data Geospatial Data Cloud (under Computer Network Information Centre Chinese Academy of Sciences) http://www.gscloud.cn/sources/?cdataid=302&pdataid=10

Download
Short summary
A random forest (RF) model framework for Fengyun-4A (FY-4A) daytime and nighttime quantitative precipitation estimation (QPE) is established using FY-4A multi-band spectral information, cloud parameters, high-density precipitation observations and physical quantities from reanalysis data. The RF model of FY-4A QPE has a high accuracy in estimating precipitation at the heavy-rain level or below, which has advantages for quantitative estimation of summer precipitation over East Asia in future.