Prompt Federated Learning for Weather Forecasting: Toward Foundation Models on Meteorological Data

2023/01/22 by Shengchao Chen, Chen, Shengchao, Guodong Long +5 · 3 citations
Environmental Science · #Cartography #Computer science #Data science #Foundation (evidence) #Geography #Hydrological Forecasting Using AI #Meteorology #Scale (ratio) #Weather prediction

paper · pdf · doi:10.48550/arxiv.2301.09152

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2023/01/22 · openalex created_date 2023/01/25 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• Evaluating Adversarial Attacks on Federated Learning for Temperature Forecasting
• FeDaL: Federated Dataset Learning for Time Series Foundation Models
• Lethe: How Hard Is It to Forget? A Benchmark for Federated Unlearning in Medical Imaging

Related

• Federated Prompt Learning for Weather Foundation Models on Devices
• A Distributed Approach to Meteorological Predictions: Addressing Data Imbalance in Precipitation Prediction Models through Federated Learning and GANs
• WeatherGFM: Learning A Weather Generalist Foundation Model via In-context Learning
• ClimateLLM: Efficient Weather Forecasting via Frequency-Aware Large Language Models
• VarteX: Enhancing Weather Forecast through Distributed Variable Representation