SubseasonalClimateUSA: A Dataset for Subseasonal Forecasting and Benchmarking

Soukayna Mouatadid, Paulo Orenstein, Genevieve Elaine Flaspohler, Miruna Oprescu, Judah Cohen, Franklyn Wang, Sean Edward Knight, Maria Geogdzhayeva, Samuel James Levang, Ernest Fraenkel, Lester Mackey

Keywords: weather and climate prediction, subseasonal forecasting, deep learning, subseasonal benchmark dataset, bias correction, statistical postprocessing

TL;DR: This paper introduces SubseasonalClimateUSA, a dataset for training and benchmarking dynamical and learning-based subseasonal forecasting models in the United States.

Abstract: Subseasonal forecasting of the weather two to six weeks in advance is critical for resource allocation and advance disaster notice but poses many challenges for the forecasting community. At this forecast horizon, physics-based dynamical models have limited skill, and the targets for prediction depend in a complex manner on both local weather variables and global climate variables. Recently, machine learning methods have shown promise in advancing the state of the art but only at the cost of complex data curation, integrating expert knowledge with aggregation across multiple relevant data sources, file formats, and temporal and spatial resolutions. To streamline this process and accelerate future development, we introduce SubseasonalClimateUSA, a curated dataset for training and benchmarking subseasonal forecasting models in the United States. We use this dataset to benchmark a diverse suite of models, including operational dynamical models, classical meteorological baselines, and ten state-of-the-art machine learning and deep learning-based methods from the literature. Overall, our benchmarks suggest simple and effective ways to extend the accuracy of current operational models. SubseasonalClimateUSA is regularly updated and accessible via the https://github.com/microsoft/subseasonal_data/ Python package.

Submission Number: 595