Flexcast enables flexible weather forecasts from changing data sets
FlexCast: Adaptive Weather Forecasting from Arbitrary Field Sets
Machine Learning
Summary
Weather forecasts typically use fixed sets of weather data, which makes it hard to reuse models when the available data changes. The authors introduce FlexCast, a system that can take any subset of weather measurements from a large database and make forecasts using one unified method. It adjusts its calculations to handle different types and numbers of weather variables, making forecasts more adaptable. Tests show that FlexCast works well when it has compatible weather data but struggles if the data context is mismatched.
What this means in practice
- •For meteorological model developers: Build weather forecasting models that adapt to different sets of atmospheric variables without retraining for each configuration.
- •For renewable energy operators: Produce flexible weather forecasts from available sensor data to optimize energy generation under varying data availability.
Authors
Yuang Zhang, Chen Hui, Weisi Lin, Haiqi Zhu, Xiulai Wang, Sun-Yuan Kung, Feng Jiang
Abstract
Most deep learning weather models assign a fixed set of variables and pressure levels to predefined channels, limiting transfer across atmospheric field configurations. This dependence on a fixed field set limits the transferability of trained models across atmospheric field configurations. We propose FlexCast, a field-adaptive weather forecasting model that uses a single set of parameters to produce identity-aligned forecasts for variable-cardinality subsets drawn from a 69-field ERA5 registry. Specifically, a metadata-conditioned adapter the first encodes variable identity, pressure level, and field type and combines them with spatial features. Then, shared rank-16 projec?tions are modulated by metadata-dependent gates to produce field?specific features, while masked set fusion aggregates the available fields into a fixed-width representation. Subsequently, a multiscale U-Transformer processes the fused atmospheric features, while an identity-aware query decoder produces forecasts for the requested fields. Finally, FlexCast learns a standardized six-hour increment and applies it recursively to generate forecasts at longer lead times. Experiments on the 2020 ERA5 test set demonstrate that FlexCast operates across varying field configurations. Compatible cross-field context is associated with lower forecast errors, whereas mismatched context increases them.