Diapozitive principale:

Materiale atelier:

¹

² (22 iunie 2026). The next day, I showed some practical ways to implement these ideas in a workshop called (23 iunie 2026). Both focused on the same general question: how can we evaluate spatial machine learning in a way that reflects the actual prediction task?

• We can predict everywhere. În practică, validăm unde avem date, dar prezicem în locuri care pot fi slab reprezentate de eșantionul de antrenament. Tools such as Area of Applicability (AoA) and Local Point Density (LPD) help identify parts of the prediction domain where environmental conditions are more or less supported by the available data.

Este de asemenea

@online{nowosad2026,
  author = {Nowosad, Jakub},
  title = {Rethinking {Validation} for {Spatial} {Machine} {Learning:}
    {Takeaways} from the {Talk}},
  date = {2026-07-03},
  url = {https://jakubnowosad.com/posts/2026-07-03-ml4eo/},
  langid = {en}
}