Windy Community
    • Unread
    • Categories
    • Groups
    • Go to windy.com
    • Register
    • Login

    How accurate are Windy forecasts for your location?

    Scheduled Pinned Locked Moved General Discussion
    4 Posts 4 Posters 334 Views 1 Watching
    Loading More Posts
    • Oldest to Newest
    • Newest to Oldest
    • Most Votes
    Reply
    • Reply as topic
    Log in to reply
    This topic has been deleted. Only users with topic management privileges can see it.
    • W Offline
      williamcorlin
      last edited by

      Hi everyone,

      I’ve been using Windy quite regularly and I’m curious how accurate the forecasts are for other people. In my area, I sometimes notice that the forecast can change quite a bit from one update to another, especially for rain and thunderstorms.

      Do you usually rely on one forecast model, or do you compare ECMWF, GFS, ICON and the other available models? I’d be interested to hear which model tends to work best in your location and what weather conditions are hardest for Windy to predict accurately.

      az games

      DavidGAD 健 2 Replies Last reply Reply Quote 0
      • DavidGAD Offline
        DavidGA @williamcorlin | Premium
        last edited by

        @williamcorlin This really depends where you live. The ECMWF is the best global model, and the best default fallback when you have no better local model.

        In the USA the HRRR is more accurate, but only predicts the next 48 hours.

        In the UK the Met Office "UKM" model is generally the most accurate.

        Other locations may have their own local high-resolution models.

        There's a new "Meteoblue AI" forecast that isn't really a model but it is some kind of forecast-only thing. I'd like to see more accuracy data for that.

        idefix37I 1 Reply Last reply Reply Quote 1
        • idefix37I Offline
          idefix37 Sailor Moderator @DavidGA
          last edited by idefix37

          @DavidGA
          Meteoblue is not actually a new model in Windy. It was introduced many years ago and was already based on multiple models. It has benefited from ML training since 2018.

          See historical development and some insights

          It is undoubtedly the best model for temperature forecasting in mountainous areas.

          1 Reply Last reply Reply Quote 1
          • 健 Offline
            健 伍 @williamcorlin | Premium
            last edited by

            @williamcorlin 更新后准确性偏差

            1 Reply Last reply Reply Quote 0
            • idefix37I idefix37 referenced this topic
            • First post
              Last post
            Windy Community  |  Powered by excellent NodeBB
            Terms of Use     Privacy Policy     Windy.com