Debiasing Machine Learning Predictions for Causal Inference Without Additional Ground Truth Data: “One Map, Many Trials” in Satellite-Driven Poverty Analysis
Markus B. Pettersson, Connor Thomas Jerzak, Adel Daoud
Abstract
Machine learning models trained on Earth observation data, such as satellite imagery, have demonstrated significant promise in predicting household-level wealth indices, enabling the creation of high-resolution wealth maps that can be leveraged across multiple causal trials while addressing chronic data scarcity in global development research. However, because standard training objectives prioritize overall predictive accuracy, these predictions often suffer from shrinkage toward the mean, leading to attenuated estimates of causal treatment effects and limiting their utility in policy evaluations. Existing debiasing methods, such as Prediction-Powered Inference (PPI), can handle this attenuation bias but require additional fresh ground-truth data at the downstream stage of causal inference, which restricts their applicability in data-scarce environments. We introduce and evaluate two post-hoc correction methods—Linear Calibration Correction (LCC) and a Tweedie
BibTeX
@inproceedings{aaai2026_debiasingmachine,
title = {Debiasing Machine Learning Predictions for Causal Inference Without Additional Ground Truth Data: “One Map, Many Trials” in Satellite-Driven Poverty Analysis},
author = {Markus B. Pettersson and Connor Thomas Jerzak and Adel Daoud},
booktitle = {AAAI 2026},
year = {2026}
}