Stanford's Tempov Foundation Model Predicts Village Wealth from Satellite Imagery Alone
anselm · x · 2026-07-25
Stanford researchers recently published Tempov, a geospatial foundation model trained on three million pairs of Landsat images spanning two decades. It processes raw satellite imagery to predict asset wealth at the village level across entire continents in near real-time.
Benchmark numbers show the model explains 87% and 74% of the variation in household wealth in Malawi and Mozambique respectively, using just six spectral bands. It operates entirely without census forms, field enumerators, or mobile phone metadata.
Addressing a harder problem than previous static models, Tempov is designed to track actual wealth changes over time rather than just capturing a single static snapshot.
More from Research
- Study examines how LLMs could lower the bar for chemical weapons attacks — davidmanheim · 2026-10-28
- SG-Splat: Pose-Free Feed-Forward 3DGS Decouples Geometry and Attributes for Stability — zhenjun_zhao · 2026-10-28
- CVPR 2026 Highlight: Pose Graph Optimization Fixes ACE-Zero Drift, Matches COLMAP — zhenjun_zhao · 2026-10-28
- VGGT Knows More About Its Pose Failures Than It Reports: Linear Probe Hits 93.5% AUC — zhenjun_zhao · 2026-10-28
- TLP: Single-Parameter Point Cloud Registration with Truncated Lp Functions — zhenjun_zhao · 2026-10-28
- AI labor paper: Amdahl's Law explains who gets hit and who's shielded — not just the young — soumitrashukla9 · 2026-10-28