Simple and robust forecasting of spatiotemporally correlated small Earth data with a tabular foundation model

Abstract

Spatiotemporally correlated small Earth data refer to geoscience time-series observations in which short-term monitoring provides limited informative variation, resulting in only sparse but meaningful measurements. Spatiotemporal forecasting on such data is crucial for understanding geoscientific processes despite their small scale. However, conventional deep learning models for spatiotemporal forecasting require task-specific training for different scenarios. Foundation models do not need task-specific training, but they often exhibit forecasting bias toward the global mean of the pretraining distribution. Here we propose a simple and robust approach for spatiotemporally correlated small Earth data forecasting. The essential idea is to characterize and quantify spatiotemporal patterns of small Earth data and then utilize tabular foundation models for accurate forecasting across different scenarios. Comparative results across three typical scenarios demonstrate that our forecasting approach achieves superior accuracy compared to the graph deep learning model and tabular foundation model in the majority of instances, exhibiting stronger robustness.