WeatherBench 2: A benchmark for the next generation of data‐driven global weather models

S Rasp, S Hoyer, A Merose, I Langmore… - Journal of Advances …, 2024 - Wiley Online Library
WeatherBench 2 is an update to the global, medium‐range (1–14 days) weather forecasting
benchmark proposed by (Rasp et al., 2020, https://doi. org/10.1029/2020ms002203) …

Foundation models for weather and climate data understanding: A comprehensive survey

S Chen, G Long, J Jiang, D Liu, C Zhang - arxiv preprint arxiv:2312.03014, 2023 - arxiv.org
As artificial intelligence (AI) continues to rapidly evolve, the realm of Earth and atmospheric
sciences is increasingly adopting data-driven models, powered by progressive …

[HTML][HTML] The EUPPBench postprocessing benchmark dataset v1. 0

J Demaeyer, J Bhend, S Lerch, C Primo… - Earth System …, 2023 - essd.copernicus.org
Statistical postprocessing of medium-range weather forecasts is an important component of
modern forecasting systems. Since the beginning of modern data science, numerous new …

Digital typhoon: Long-term satellite image dataset for the spatio-temporal modeling of tropical cyclones

A Kitamoto, J Hwang, B Vuillod… - Advances in …, 2024 - proceedings.neurips.cc
This paper presents the official release of the Digital Typhoon dataset, the longest typhoon
satellite image dataset for 40+ years aimed at benchmarking machine learning models for …

[HTML][HTML] Improving medium-range ensemble weather forecasts with hierarchical ensemble transformers

ZB Bouallègue, JA Weyn, MCA Clare… - … Intelligence for the …, 2024 - journals.ametsoc.org
Statistical postprocessing of global ensemble weather forecasts is revisited by leveraging
recent developments in machine learning. Verification of past forecasts is exploited to learn …

Precipitation nowcasting with generative diffusion models

A Asperti, F Merizzi, A Paparella, G Pedrazzi… - arxiv preprint arxiv …, 2023 - arxiv.org
In recent years traditional numerical methods for accurate weather prediction have been
increasingly challenged by deep learning methods. Numerous historical datasets used for …

Histgnn: Hierarchical spatio-temporal graph neural network for weather forecasting

M Ma, P **e, F Teng, B Wang, S Ji, J Zhang, T Li - Information Sciences, 2023 - Elsevier
Weather forecasting is an attractive yet challenging task due to its significant impacts on
human life and the intricate nature of atmospheric motion. Deep learning-based techniques …

OCEANBENCH: the sea surface height edition

JE Johnson, Q Febvre, A Gorbunova… - Advances in …, 2024 - proceedings.neurips.cc
The ocean is a crucial component of the Earth's system. It profoundly influences human
activities and plays a critical role in climate regulation. Our understanding has significantly …

Spatial mixture-of-experts

N Dryden, T Hoefler - Advances in Neural Information …, 2022 - proceedings.neurips.cc
Many data have an underlying dependence on spatial location; it may be weather on the
Earth, a simulation on a mesh, or a registered image. Yet this feature is rarely taken …

Diffda: a diffusion model for weather-scale data assimilation

L Huang, L Gianinazzi, Y Yu, PD Dueben… - arxiv preprint arxiv …, 2024 - arxiv.org
The generation of initial conditions via accurate data assimilation is crucial for reliable
weather forecasting and climate modeling. We propose the DiffDA as a machine learning …