Weather Forecasting

AI Weather Forecasting for Renewables: EPT-2 Beats ECMWF

1 / 5

EPT-2 outperforms ECMWF HRES on 100 m wind and surface solar radiation at every lead time from 0–240 hours according to June 2026 benchmarks.

2 / 5

Jua’s rapid-refresh variant (EPT-2 RR) updates up to 24 times per day, far exceeding the 2–4 daily cycles of traditional NWP models.

3 / 5

Sub-daily probabilistic forecasts from EPT-2e deliver measurable P&L gains, with accuracy improvements translating to €1.5–3 million annual savings per GW for wind and solar portfolios.

4 / 5

The Jua platform combines EPT-2, ECMWF, and other models behind a unified API and Athena AI agent that generates 90-second natural-language briefings.

5 / 5

See Athena and EPT-2 on your own assets in a live workflow demo and connect AI weather intelligence directly to your trading stack.

Read the full analysis

Jua's EPT-2 outperforms ECMWF HRES at every lead time, saving wind & solar traders €1.5–3M per GW annually. See Europe's most accurate AI forecast.

Read the full article