Research fellow at @OxfordPhysics + @NCEOscience focusing on satellite data for weather and climate | Occasional Pilot | he/him | 
Voit lisätä twiitteihisi sijainnin, esimerkiksi kaupungin tai tarkemman paikan, verkosta ja kolmannen osapuolen sovellusten kautta. Halutessasi voit poistaa twiittisi sijaintihistorian myöhemmin. Lue lisää
Great! So how come after over a decade of machine learning research to produce cloud masks for remote sensing days there's still very few that perform better than the expert cloudmasks? That's a lot of weekends of training we've had!
days = data. Machine learning text prediction ain't as good as expert typing either ;-)
Are there better cloud masking algorithms than the ML-based ones? I’m thinking of the @sinergise open source model for Sentinel-2, for instance. Haven’t seen it compared to Fmask but I would guess it’s betterhttps://link.medium.com/sbSiHhcP5lb
But it's pixel-based (fast!) and using LightGBM tree-based gradient boosting, so no DL and nothing spatially-aware. IMHO not that far from the point being made here that these kind of efforts are still in the top position at the global scale.
Twitter saattaa olla ruuhkautunut tai ongelma on muuten hetkellinen. Yritä uudelleen tai käy Twitterin tilasivulla saadaksesi lisätietoja.
