There are multiple efforts and a good number of VC working on AI DA system. DA is fundamentally a hand-crafted optimization process just like NN. I once reimplemented an EnKF in pytorch and it works amazingly fast. But our observations are so dirty and sparse. ECMWF tuned their system so well. NOAA definitely has potential being even better, but no hope any soon future IMHO.

As someone who has served as a reviewer for several MDPI journals, I personally haven’t found their overall quality to be particularly high—which was a factor in my decision to stop reviewing for them. Of course, it’s possible that some specific journals or articles are exceptions, but I would encourage readers to critically evaluate work published by MDPI on a case-by-case basis.