Weather Forecasting
1 / 5
EPT-2 now leads ECMWF HRES across 0–240 hours on 10 m wind, 100 m wind, 2 m temperature, and surface solar radiation, the core energy P&L drivers.
2 / 5
EPT-2e, Jua’s ensemble variant, delivers stronger probabilistic skill than the 50-member ECMWF ENS mean at most lead times, widening the gap between AI and traditional NWP.
3 / 5
AI peers such as Microsoft Aurora and Google DeepMind GraphCast trail EPT-2 on the variables they cover and currently lack productised ensembles or refresh schedules that match EPT-2 RR’s 24 runs per day.
4 / 5
EPT-2 RR delivers up to 24 updates daily. Its ~0.25 kWh per simulation cost makes those frequent runs practical while still maintaining higher resolution and earlier delivery than traditional NWP.
5 / 5
Energy traders can benchmark these results on the Jua platform in minutes; book a personalized demo with Jua to see the accuracy edge on your own region and variables.
See how Jua's EPT-2 outperforms ECMWF HRES & GFS on wind, temperature & solar. Explore the best weather prediction models for energy trading.