A grid-free attention-based deep learning model interpolates surface-level PM2.5 concentrations across the US using sparse sensor data and auxiliary geospatial features.
For spatial consistency with the modeling framework, the population data were aggregated to H3 level-8 hexagons
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Mechanistic Anomaly Detection via Functional Attribution
A grid-free attention-based deep learning model interpolates surface-level PM2.5 concentrations across the US using sparse sensor data and auxiliary geospatial features.