The AI & Global Development Lab fuses modern machine‑learning with Earth‑observation data to illuminate the causes and consequences of human development across time and space — from neighbourhood‑level poverty mapping to the evaluation of large‑scale aid programmes. Our interdisciplinary team of computer scientists, economists, sociologists and political scientists works at the intersection of AI, earth observation and causal inference to generate open data, open models and open‑source software for the global research community.
Official code repository for IJCAI 2023 paper "Time series of satellite imagery improve deep learning estimates of neighborhood-level poverty in Africa"
[AAAI 2026, oral] unshrink: post-hoc debiasing of machine learning predictions to reduce shrinkage-induced attenuation bias in downstream causal inference -- without requiring fresh ground-truth data
[AAAI 2026, oral] unshrink: post-hoc debiasing of machine learning predictions to reduce shrinkage-induced attenuation bias in downstream causal inference -- without requiring fresh ground-truth data
[AAAI 2026] Debiasing Machine Learning Predictions for Causal Inference Without Additional Ground Truth Data: “One Map, Many Trials” in Satellite-Driven Poverty Analysis
There was an error while loading. Please reload this page.
Most used topics
Loading…
Uh oh!
There was an error while loading. Please reload this page.
You are visitor 01402503 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.