ERA5

ERA5 is a dataset that contains high-resolution weather data comprising multiple variables, used to evaluate the effectiveness of contrastive learning in generating robust embeddings for downstream tasks such as forecasting and extreme-weather detection.

Papers using ERA5 (4)

Regional data-driven weather modeling with a global stretched-grid2024 · 5 citesPhysics-Assisted and Topology-Informed Deep Learning for Weather Prediction2025Contrastive Learning Boosts Deterministic and Generative Models for Weather Data2026Adaptive Spatio-Temporal Graphs with Self-Supervised Pretraining for Multi-Horizon Weather Forecasting2025