An Application of Deep Learning Technique to Improve Subseasonal to Seasonal Rainfall Forecast over Java Island, Indonesia

Abstract

Subseasonal to seasonal (S2S) rainfall forecast can benefit several sectors, such as water resources, hazard management, and agriculture. However, the forecast remains challenging due to its lack of skill. This study applies Convolutional AutoEncoders (ConvAE), a deep learning technique, to improve the quality of the S2S rainfall forecast. Seven S2S model output incorporated with Subseasonal Experiments Projects (SubX), including CCSM4, CFSv2, FIMr1p1, GEFS, GEOS_v2p1, GEPS6, and NESM, are corrected using the ConvAE approach. We combine 407 ground observations and the CHIRPS dataset using regression kriging methods producing gridded daily precipitation data with 0.05° spatial resolution. We utilize this dataset as a label to train ConvAE models and to perform bias corrections to all members of the SubX forecasts data. The results show that ConvAE is able to increase the quality of weekly S2S rainfall forecasts over Java, Indonesia. The Correlation Coefficient for 1 – 4 weeks lead time are improved from: 0.76, 0.715, 0.692 and 0.722 towards 0.809, 0.751, 0.719 and 0.74, respectively. Furthermore, the average CRPSS improves between 20 – 30% for all lead times.

Keywords

• bias correction; convolutional autoencoders; rainfall forecasts; sub-seasonal to seasonal