Research
1 / 5
European day-ahead electricity price forecasts still show material sMAPE gaps across major bidding zones, with the largest errors during Dunkelflaute and heatwave events.
2 / 5
Physics-constrained foundation models like EPT-2 beat ECMWF HRES and Microsoft Aurora at every lead time for the four weather variables that most directly drive electricity prices.
3 / 5
Pan-European spatiotemporal architectures capture cross-border flows and teleconnections that national models structurally miss, which reduces imbalance exposure for multi-zone portfolios.
4 / 5
Twenty-four daily refresh cycles deliver accuracy gains worth €1.5–3 M per GW annually by getting revisions to traders before intraday markets re-price.
5 / 5
Book a demo with Jua to benchmark EPT-2 against your current provider and quantify accuracy and refresh-frequency gains for your region.
Only 47% of traders trust their models. See how Jua's physics-constrained AI cuts sMAPE errors across European bidding zones. Book a demo.