TY - JOUR
T1 - The Role of Water Vapor Observations in Satellite Rainfall Detection Highlighted by a Deep Learning Approach
AU - Estébanez-Camarena, Mónica
AU - Curzi, Fabio
AU - Taormina, Riccardo
AU - van de Giesen, Nick
AU - ten Veldhuis, Marie-Claire
PY - 2023
Y1 - 2023
N2 - West African food systems and rural socio-economics are based on rainfed agriculture, which makes society highly vulnerable to rainfall uncertainty and frequent floods and droughts. Reliable rainfall information is currently missing. There is a sparse and uneven rain gauge distribution and, despite continuous efforts, rainfall satellite products continue to show weak correlations with ground measurements. This paper aims to investigate whether water vapor (WV) observations together with temporal information can complement thermal infrared (TIR) data for satellite rainfall retrieval in a Deep Learning (DL) framework. This is motivated by the fact that water vapor plays a key role in the highly seasonal West African rainfall dynamics. We present a DL model for satellite rainfall detection based on WV and TIR channels of Meteosat Second Generation and temporal information. Results show that the WV inhibition of low-level features enables the depiction of strong convective motions usually related to heavy rainfall. This is especially relevant in areas where convective rainfall is dominant, such as the tropics. Additionally, WV data allow us to detect dry air masses over our study area, that are advected from the Sahara Desert and create discontinuities in precipitation events. The developed DL model shows strong performance in rainfall binary classification, with less false alarms and lower rainfall overdetection (FBias <2.0) than the state-of-the-art Integrated MultisatellitE Retrievals for GPM (IMERG) Final Run.
AB - West African food systems and rural socio-economics are based on rainfed agriculture, which makes society highly vulnerable to rainfall uncertainty and frequent floods and droughts. Reliable rainfall information is currently missing. There is a sparse and uneven rain gauge distribution and, despite continuous efforts, rainfall satellite products continue to show weak correlations with ground measurements. This paper aims to investigate whether water vapor (WV) observations together with temporal information can complement thermal infrared (TIR) data for satellite rainfall retrieval in a Deep Learning (DL) framework. This is motivated by the fact that water vapor plays a key role in the highly seasonal West African rainfall dynamics. We present a DL model for satellite rainfall detection based on WV and TIR channels of Meteosat Second Generation and temporal information. Results show that the WV inhibition of low-level features enables the depiction of strong convective motions usually related to heavy rainfall. This is especially relevant in areas where convective rainfall is dominant, such as the tropics. Additionally, WV data allow us to detect dry air masses over our study area, that are advected from the Sahara Desert and create discontinuities in precipitation events. The developed DL model shows strong performance in rainfall binary classification, with less false alarms and lower rainfall overdetection (FBias <2.0) than the state-of-the-art Integrated MultisatellitE Retrievals for GPM (IMERG) Final Run.
KW - West Africa
KW - deep learning
KW - satellite rainfall retrieval
KW - rainfall detection
KW - CNN
KW - water vapor
UR - http://www.scopus.com/inward/record.url?scp=85163931498&partnerID=8YFLogxK
U2 - 10.3390/atmos14060974
DO - 10.3390/atmos14060974
M3 - Article
SN - 2073-4433
VL - 14
JO - Atmosphere
JF - Atmosphere
IS - 6
M1 - 974
ER -