Self-supervised learning features from satellite imagery predict below-ground ectomycorrhizal fungal richness, explaining over half the variance across 12,000 samples at 10m resolution.
• The final output is a collection of .npy files, where each file corresponds to a sample and contains a 3x3x128 feature tensor
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Below-ground Fungal Biodiversity Can be Monitored Using Self-Supervised Learning Satellite Features
Self-supervised learning features from satellite imagery predict below-ground ectomycorrhizal fungal richness, explaining over half the variance across 12,000 samples at 10m resolution.