Machine Learning for Spatiotemporal Sequence Forecasting: A Survey

TL;DR

This survey comprehensively reviews machine learning approaches for spatiotemporal sequence forecasting, categorizing methods, discussing challenges, and highlighting future research directions in this complex field.

Contribution

It provides the first unified classification and systematic comparison of machine learning methods for STSF, addressing key challenges and proposing future research directions.

Findings

Deep learning methods outperform classical ML in accuracy.

Multi-step forecasting remains a core challenge.

Unified framework aids future research in STSF.

Abstract

Spatiotemporal systems are common in the real-world. Forecasting the multi-step future of these spatiotemporal systems based on the past observations, or, Spatiotemporal Sequence Forecasting (STSF), is a significant and challenging problem. Although lots of real-world problems can be viewed as STSF and many research works have proposed machine learning based methods for them, no existing work has summarized and compared these methods from a unified perspective. This survey aims to provide a systematic review of machine learning for STSF. In this survey, we define the STSF problem and classify it into three subcategories: Trajectory Forecasting of Moving Point Cloud (TF-MPC), STSF on Regular Grid (STSF-RG) and STSF on Irregular Grid (STSF-IG). We then introduce the two major challenges of STSF: 1) how to learn a model for multi-step forecasting and 2) how to adequately model the spatial and temporal structures. After that, we review the existing works for solving these challenges, including the general learning strategies for multi-step forecasting, the classical machine learning based methods for STSF, and the deep learning based methods for STSF. We also compare these methods and point out some potential research directions.