Saved in:
Bibliographic Details
Main Authors: Molinaro, Roberto, Siegenheim, Niall, Poulsen, Niels, Daubinet, Jordan Dane, Martin, Henry, Frey, Mark, Thiart, Kevin, Dautel, Alexander Jakob, Schlueter, Andreas, Grigoryev, Alex, Danciu, Bogdan, Ekhtiari, Nikoo, Steunebrink, Bas, Wagner, Leonie, Gabler, Marvin Vincent
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.09703
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913939704512512
author Molinaro, Roberto
Siegenheim, Niall
Poulsen, Niels
Daubinet, Jordan Dane
Martin, Henry
Frey, Mark
Thiart, Kevin
Dautel, Alexander Jakob
Schlueter, Andreas
Grigoryev, Alex
Danciu, Bogdan
Ekhtiari, Nikoo
Steunebrink, Bas
Wagner, Leonie
Gabler, Marvin Vincent
author_facet Molinaro, Roberto
Siegenheim, Niall
Poulsen, Niels
Daubinet, Jordan Dane
Martin, Henry
Frey, Mark
Thiart, Kevin
Dautel, Alexander Jakob
Schlueter, Andreas
Grigoryev, Alex
Danciu, Bogdan
Ekhtiari, Nikoo
Steunebrink, Bas
Wagner, Leonie
Gabler, Marvin Vincent
contents We present EPT-2, the latest iteration in our Earth Physics Transformer (EPT) family of foundation AI models for Earth system forecasting. EPT-2 delivers substantial improvements over its predecessor, EPT-1.5, and sets a new state of the art in predicting energy-relevant variables-including 10m and 100m wind speed, 2m temperature, and surface solar radiation-across the full 0-240h forecast horizon. It consistently outperforms leading AI weather models such as Microsoft Aurora, as well as the operational numerical forecast system IFS HRES from the European Centre for Medium-Range Weather Forecasts (ECMWF). In parallel, we introduce a perturbation-based ensemble model of EPT-2 for probabilistic forecasting, called EPT-2e. Remarkably, EPT-2e significantly surpasses the ECMWF ENS mean-long considered the gold standard for medium- to longrange forecasting-while operating at a fraction of the computational cost. EPT models, as well as third-party forecasts, are accessible via the app.jua.ai platform.
format Preprint
id arxiv_https___arxiv_org_abs_2507_09703
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EPT-2 Technical Report
Molinaro, Roberto
Siegenheim, Niall
Poulsen, Niels
Daubinet, Jordan Dane
Martin, Henry
Frey, Mark
Thiart, Kevin
Dautel, Alexander Jakob
Schlueter, Andreas
Grigoryev, Alex
Danciu, Bogdan
Ekhtiari, Nikoo
Steunebrink, Bas
Wagner, Leonie
Gabler, Marvin Vincent
Machine Learning
Artificial Intelligence
We present EPT-2, the latest iteration in our Earth Physics Transformer (EPT) family of foundation AI models for Earth system forecasting. EPT-2 delivers substantial improvements over its predecessor, EPT-1.5, and sets a new state of the art in predicting energy-relevant variables-including 10m and 100m wind speed, 2m temperature, and surface solar radiation-across the full 0-240h forecast horizon. It consistently outperforms leading AI weather models such as Microsoft Aurora, as well as the operational numerical forecast system IFS HRES from the European Centre for Medium-Range Weather Forecasts (ECMWF). In parallel, we introduce a perturbation-based ensemble model of EPT-2 for probabilistic forecasting, called EPT-2e. Remarkably, EPT-2e significantly surpasses the ECMWF ENS mean-long considered the gold standard for medium- to longrange forecasting-while operating at a fraction of the computational cost. EPT models, as well as third-party forecasts, are accessible via the app.jua.ai platform.
title EPT-2 Technical Report
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2507.09703