Rainfall Prediction Using Deep Learning Based on Satellite Positioning and Meteorological Sensors

• Published in: Shisutemu Seigyo Jouhou Gakkai rombunshi Vol. 36; no. 9; pp. 296 - 305
• Main Authors: Nakagawa, Yutaka, Higashino, Takeshi, Okada, Minoru
• Format: Journal Article
• Language: English; Japanese
• Published: Kyoto THE INSTITUTE OF SYSTEMS, CONTROL AND INFORMATION ENGINEERS (ISCIE) 15.09.2023; Japan Science and Technology Agency
• Subjects: Algorithms; Deep learning; Forecasting; Global navigation satellite system; GNSS-ZTD; LSTM; Machine learning; Mathematical models; meteorological sensor; Neural networks; Prediction models; Rainfall; time series prediction; Water vapor
• ISSN: 1342-5668; 2185-811X
• DOI: 10.5687/iscie.36.296

In recent years, the occurrence of local torrential rain has increased, and an accurate prediction model is required. Atmospheric water vapor measurement based on the zenith total delay (ZTD) produced by the precise point positioning processing employed in the Global Navigation Satellite System (GNSS) is effective for forecasting. Recently, there has been a lot of research into applying deep learning to forecasting, however, it could not be practical. In this paper, we introduce the Long Short-Term Memory (LSTM) built by a neural network algorithm to effectively model the discrete time series of rain rate, the ZTD and the meteorological sensing data work as explanatory variables. A key message from this analysis is that a deep learning model has the capability to follow the climate variation as long as a short-term event even though it exists spatial locality.