Prompt Federated Learning for Weather Forecasting: Toward Foundation Models on Meteorological Data
This addresses the need for a collaborative platform to improve weather forecasting for global climate challenges, though it appears incremental by combining federated learning with existing Transformer and prompt techniques.
The paper tackled the problem of collaborative weather forecasting across regions with heterogeneous meteorological data by developing a federated learning approach with a spatio-temporal Transformer-based foundation model and prompt learning, demonstrating effectiveness on classical forecasting tasks using three datasets.
To tackle the global climate challenge, it urgently needs to develop a collaborative platform for comprehensive weather forecasting on large-scale meteorological data. Despite urgency, heterogeneous meteorological sensors across countries and regions, inevitably causing multivariate heterogeneity and data exposure, become the main barrier. This paper develops a foundation model across regions capable of understanding complex meteorological data and providing weather forecasting. To relieve the data exposure concern across regions, a novel federated learning approach has been proposed to collaboratively learn a brand-new spatio-temporal Transformer-based foundation model across participants with heterogeneous meteorological data. Moreover, a novel prompt learning mechanism has been adopted to satisfy low-resourced sensors' communication and computational constraints. The effectiveness of the proposed method has been demonstrated on classical weather forecasting tasks using three meteorological datasets with multivariate time series.