Same with weekly climatology: Looking back at how warm it was, at a given location, that same week two years ago, does not in general sound like a bad strategy.

Second, the DL baseline shown is as basic as it can get, architecture- as well as parameter-wise. More sophisticated and powerful architectures have been developed that not just by far surpass the baselines, but can even compete with physical models (cf. especially Rasp and Thuerey [@rasp2020purely] already mentioned above). Unfortunately, models like that need to be trained on a lot of data.

However, other weather-related applications (other than medium-range forecasting, that is) may be more in reach for individuals interested in the topic. For those, we hope we have given a useful introduction. Thanks for reading!