Hi, the exact improvement heavily depends on the specific location and the weather patterns at the time. Generally though, we see roughly a 10% improvement in day-ahead forecasts for core variables like temperature and cloudiness compared to the raw ensemble average. The difference is even bigger if you compare it to the standard single-model approach that most weather APIs use.

That's a meaningful improvement — 10% on day-ahead forecasts is actually significant when you compound it across a week of planning. Makes sense that location variance would be high though; I'd imagine coastal vs inland vs mountainous locations behave very differently for your correction models.