EPT-1.5 Technical Report
Roberto Molinaro, Jordan Dane Daubinet, Alexander Jakob Dautel,, Andreas Schlueter, Alex Grigoryev, Nikoo Ekhtiari, Bas Steunebrink, Kevin, Thiart, Roan John Song, Henry Martin, Leonie Wagner, Andrea Giussani, and, Marvin Vincent Gabler

TL;DR
EPT-1.5 is a new Earth Physics Transformer model optimized for the European energy sector, significantly improving wind and solar predictions and outperforming existing AI and numerical weather models.
Contribution
The paper introduces EPT-1.5, a novel foundation AI earth system model tailored for energy applications, with enhanced accuracy over previous models and state-of-the-art wind prediction performance.
Findings
EPT-1.5 outperforms existing AI weather models in wind prediction.
EPT-1.5 surpasses the ECMWF IFS HRES in wind forecasting accuracy.
EPT-1.5 demonstrates substantial improvements over its predecessor, EPT-1.5.
Abstract
We announce the release of EPT-1.5, the latest iteration in our Earth Physics Transformer (EPT) family of foundation AI earth system models. EPT-1.5 demonstrates substantial improvements over its predecessor, EPT-1. Built specifically for the European energy industry, EPT-1.5 shows remarkable performance in predicting energy-relevant variables, particularly 10m & 100m wind speed and solar radiation. Especially in wind prediction, it outperforms existing AI weather models like GraphCast, FuXi, and Pangu-Weather, as well as the leading numerical weather model, IFS HRES by the European Centre for Medium-Range Weather Forecasts (ECMWF), setting a new state of the art.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsParticle accelerators and beam dynamics · Nuclear reactor physics and engineering · Scientific Measurement and Uncertainty Evaluation
MethodsDense Connections · Layer Normalization · Residual Connection · Position-Wise Feed-Forward Layer · SPEED: Separable Pyramidal Pooling EncodEr-Decoder for Real-Time Monocular Depth Estimation on Low-Resource Settings · Attention Is All You Need · Adam · Linear Layer · Softmax · Multi-Head Attention
