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.
Great, thank you for the helpful tip! We can work with the variables you mentioned in our customized endpoints, even though they’re not currently included in the standardized subscriptions. We're considering standardizing aviation parameters in the future. Do you have any other suggestions or features that would be useful for you?