Spatio-Temporal Functional Neural Networks

TL;DR

This paper introduces two novel spatio-temporal extensions of the Functional Neural Network to effectively model and predict complex spatio-temporal data, outperforming existing methods in simulations and real-world precipitation forecasting.

Contribution

The paper presents new spatio-temporal functional neural network models that better capture spatial and temporal dependencies compared to prior models like CovLSTM and functional linear models.

Findings

Models outperform existing methods in simulation studies.

Effective in handling varying spatial correlations.

Successfully applied to precipitation prediction.

Abstract

Explosive growth in spatio-temporal data and its wide range of applications have attracted increasing interests of researchers in the statistical and machine learning fields. The spatio-temporal regression problem is of paramount importance from both the methodology development and real-world application perspectives. Given the observed spatially encoded time series covariates and real-valued response data samples, the goal of spatio-temporal regression is to leverage the temporal and spatial dependencies to build a mapping from covariates to response with minimized prediction error. Prior arts, including the convolutional Long Short-Term Memory (CovLSTM) and variations of the functional linear models, cannot learn the spatio-temporal information in a simple and efficient format for proper model building. In this work, we propose two novel extensions of the Functional Neural Network (FNN), a temporal regression model whose effectiveness and superior performance over alternative sequential models have been proven by many researchers. The effectiveness of the proposed spatio-temporal FNNs in handling varying spatial correlations is demonstrated in comprehensive simulation studies. The proposed models are then deployed to solve a practical and challenging precipitation prediction problem in the meteorology field.