
Thomas Ratsakatika (Department of Geography, University of Cambridge, Cambridge, UK), Mihai Zotta (Fundatia Conservation Carpathia, Brasov, Romania), Srinivasan Keshav (Department of Computer Science and Technology, University of Cambridge, Cambridge, UK), Emily R. Lines (Department of Geography, University of Cambridge, Cambridge, UK)
· 1 min read
Geospatial embeddings detect old-growth forests but buffered spatial validation narrows their advantage over Sentinel features
Original source
This story was published by arXiv cs.LG and written by Thomas Ratsakatika (Department of Geography, University of Cambridge, Cambridge, UK), Mihai Zotta (Fundatia Conservation Carpathia, Brasov, Romania), Srinivasan Keshav (Department of Computer Science and Technology, University of Cambridge, Cambridge, UK), Emily R. Lines (Department of Geography, University of Cambridge, Cambridge, UK). SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


