Evaluating Spatio-Temporal Forecasting Trade-offs Between Graph Neural Networks and Foundation Models

TL;DR

This study systematically compares classical, neural, graph neural, and foundation models for environmental spatio-temporal forecasting, revealing their strengths and limitations under different sensor deployment scenarios.

Contribution

It provides a comprehensive analysis of how various forecasting models perform with different sensor densities and sampling rates, highlighting the advantages of multivariate foundation models.

Findings

STGNNs excel with sparse sensors and moderate sampling rates.

TSFMs perform well at high sampling frequencies but decline with reduced spatial coverage.

Moirai, a multivariate TSFM, outperforms other models by learning cross-sensor dependencies.

Abstract

Modern IoT deployments for environmental sensing produce high volume spatiotemporal data to support downstream tasks such as forecasting, typically powered by machine learning models. While existing filtering and strategic deployment techniques optimize collected data volume at the edge, they overlook how variations in sampling frequencies and spatial coverage affect downstream model performance. In many forecasting models, incorporating data from additional sensors denoise predictions by providing broader spatial contexts. This interplay between sampling frequency, spatial coverage and different forecasting model architectures remain underexplored. This work presents a systematic study of forecasting models - classical models (VAR), neural networks (GRU, Transformer), spatio-temporal graph neural networks (STGNNs), and time series foundation models (TSFMs: Chronos Moirai, TimesFM) under varying spatial sensor nodes density and sampling intervals using real-world temperature data in a wireless sensor network. Our results show that STGNNs are effective when sensor deployments are sparse and sampling rate is moderate, leveraging spatial correlations via encoded graph structure to compensate for limited coverage. In contrast, TSFMs perform competitively at high frequencies but degrade when spatial coverage from neighboring sensors is reduced. Crucially, the multivariate TSFM Moirai outperforms all models by natively learning cross-sensor dependencies. These findings offer actionable insights for building efficient forecasting pipelines in spatio-temporal systems. All code for model configurations, training, dataset, and logs are open-sourced for reproducibility: https://github.com/UIUC-MONET-Projects/Benchmarking-Spatiotemporal-Forecast-Models