DINO self-supervised features from Sentinel-2 imagery predict piped water and sewage access at 2.56 km resolution in Africa, achieving AUROCs of 91.54% and 93.24% with R² alignments of 0.92 and 0.72 to JMP statistics.
arXiv preprint , year =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Seeing SDG 6 from space: local-scale monitoring of piped water and sewage system access across Africa using satellite imagery and self-supervised learning
DINO self-supervised features from Sentinel-2 imagery predict piped water and sewage access at 2.56 km resolution in Africa, achieving AUROCs of 91.54% and 93.24% with R² alignments of 0.92 and 0.72 to JMP statistics.