PredBench: Benchmarking Spatio-Temporal Prediction across Diverse Disciplines

TL;DR

PredBench provides a comprehensive benchmark for evaluating diverse spatio-temporal prediction models across multiple datasets and metrics, addressing the lack of standardized evaluation frameworks in the field.

Contribution

It introduces a large-scale, multi-dimensional benchmarking framework for spatio-temporal prediction networks, integrating 12 methods and 15 datasets with standardized experimental protocols.

Findings

Benchmark reveals strengths and weaknesses of current models.

Provides insights for future research directions.

Ensures fair comparison through standardized settings.

Abstract

In this paper, we introduce PredBench, a benchmark tailored for the holistic evaluation of spatio-temporal prediction networks. Despite significant progress in this field, there remains a lack of a standardized framework for a detailed and comparative analysis of various prediction network architectures. PredBench addresses this gap by conducting large-scale experiments, upholding standardized and appropriate experimental settings, and implementing multi-dimensional evaluations. This benchmark integrates 12 widely adopted methods with 15 diverse datasets across multiple application domains, offering extensive evaluation of contemporary spatio-temporal prediction networks. Through meticulous calibration of prediction settings across various applications, PredBench ensures evaluations relevant to their intended use and enables fair comparisons. Moreover, its multi-dimensional evaluation framework broadens the analysis with a comprehensive set of metrics, providing deep insights into the capabilities of models. The findings from our research offer strategic directions for future developments in the field. Our codebase is available at https://github.com/OpenEarthLab/PredBench.