Short-term daily precipitation forecasting with seasonally-integrated autoencoder

TL;DR

This paper introduces a seasonally-integrated autoencoder model that effectively captures nonlinear and seasonal patterns in daily precipitation data, significantly improving short-term forecasting accuracy across different climate zones.

Contribution

The study presents a novel SSAE model combining two LSTM autoencoders to simultaneously learn short-term dynamics and seasonality in precipitation time series.

Findings

SSAE outperforms traditional time series models across climate types.

SSAE achieves lower output variance than other deep learning models.

Seasonality component improves forecast correlation from 4% to 37%.

Abstract

Short-term precipitation forecasting is essential for planning of human activities in multiple scales, ranging from individuals' planning, urban management to flood prevention. Yet the short-term atmospheric dynamics are highly nonlinear that it cannot be easily captured with classical time series models. On the other hand, deep learning models are good at learning nonlinear interactions, but they are not designed to deal with the seasonality in time series. In this study, we aim to develop a forecasting model that can both handle the nonlinearities and detect the seasonality hidden within the daily precipitation data. To this end, we propose a seasonally-integrated autoencoder (SSAE) consisting of two long short-term memory (LSTM) autoencoders: one for learning short-term dynamics, and the other for learning the seasonality in the time series. Our experimental results show that not only does the SSAE outperform various time series models regardless of the climate type, but it also has low output variance compared to other deep learning models. The results also show that the seasonal component of the SSAE helped improve the correlation between the forecast and the actual values from 4% at horizon 1 to 37% at horizon 3.