Half-hourly Rainfall Monitoring over the Indochina Area from MTSAT Infrared Measurements: Development of Rain Estimation Algorithm using an Artificial Neural Network

Abstract

Summary and Discussion To estimate rain rates over the Indochina regionwhere highly populated residential areas are prone tonatural disasters, in particular those associated withheavy rainfall, we developed an ANN-based retrievalalgorithm. The method was developed by training theIR-based cloud top temperature and the temperaturedifference between the 11-µm and water vaporchannels against collocated PMW-based rain ratesusing the counter propagation network, which consistsof three layers and a linear output layer. The surfacetype and geographical location were also included asinitial inputs. We aimed to produce surface rain rateswith a 0.04 o ×0.04 o grid area and a 30-minute timeinterval from the Japanese geostationary satelliteMTSAT measurements. Training was carried out foreach individual month from June to September 2005,and the results were applied to the same months for2006.The results for the June to September 2006 rainyseason reveal that the ANN technique appears toenhance our capability for rain estimation fromgeostationary satellite imagery over the Indochinaregion, in terms of output quality and temporalresolution. It has also been shown that instantaneousrain rates with a 0.25