Comment by moktonar

I’ve read the article and skimmed the paper, but they don’t seem to say if the model has to be retrained every few days or every now and then. Because if it’s trained on marginals it seems to me that the model essentially learns to forecast weather at each location (a bit like locals do), but weather patterns might change over time so I guess they’ll have to retrain it. The retraining frequency might be a deal breaker if for example you have to train it for 3 wall lock days every, say, 7 days.