# Debiasing Machine Learning Predictions for Causal Inference Without Additional Ground Truth Data: "One Map, Many Trials" in Satellite-Driven Poverty Analysis

arXiv: https://arxiv.org/abs/2508.01341 · HTML: https://mlsanity.com/paper/2508.01341/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 35 references that are in the map.
- First posted on arXiv 2 Aug 2025.

## Builds on (most cited first, 15 of 15)

- [Prediction-Powered Inference](https://mlsanity.com/paper/2301.09633/) (2023)
- [Using satellite imagery to understand and promote sustainable development](https://mlsanity.com/paper/2010.06988/) (2020)
- [SSL4EO-L: Datasets and Foundation Models for Landsat Imagery](https://mlsanity.com/paper/2306.09424/) (2023)
- [Using Imperfect Surrogates for Downstream Inference: Design-based Supervised Learning for Social Science Applications of Large Language Models](https://mlsanity.com/paper/2306.04746/) (2023)
- [Micro-Estimates of Wealth for all Low- and Middle-Income Countries](https://mlsanity.com/paper/2104.07761/) (2021)
- [Image-based Treatment Effect Heterogeneity](https://mlsanity.com/paper/2206.06417/) (2022)
- [Statistical modeling: the three cultures](https://mlsanity.com/paper/2012.04570/) (2020)
- [Conceptualizing Treatment Leakage in Text-based Causal Inference](https://mlsanity.com/paper/2205.00465/) (2022)
- [Using Satellite Imagery and Machine Learning to Estimate the Livelihood Impact of Electricity Access](https://mlsanity.com/paper/2109.02890/) (2021)
- [Integrating Earth Observation Data into Causal Inference: Challenges and Opportunities](https://mlsanity.com/paper/2301.12985/) (2023)
- [Benchmarking Debiasing Methods for LLM-based Parameter Estimates](https://mlsanity.com/paper/2506.09627/) (2025)
- [A Scoping Review of Earth Observation and Machine Learning for Causal Inference: Implications for the Geography of Poverty](https://mlsanity.com/paper/2406.02584/) (2024)
- [Regression coefficient estimation from remote sensing maps](https://mlsanity.com/paper/2407.13659/) (2024)
- [Optimizing Multi-Scale Representations to Detect Effect Heterogeneity Using Earth Observation and Computer Vision: Applications to Two Anti-Poverty RCTs](https://mlsanity.com/paper/2411.02134/) (2024)
- [A High Resolution Urban and Rural Settlement Map of Africa Using Deep Learning and Satellite Imagery](https://mlsanity.com/paper/2411.02935/) (2024)

## Built on by (most cited first, 2 of 2)

- [Detecting and Mitigating Treatment Leakage in Text-Based Causal Inference: Distillation and Sensitivity Analysis](https://mlsanity.com/paper/2601.02400/) (2025)
- [Transfer Learning for Socioeconomic Estimation in Forced-Displacement Settings](https://mlsanity.com/paper/2609.15773/) (2026)

## Abstract (arXiv)

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's correction approach -- that substantially reduce shrinkage-induced prediction bias without relying on newly collected labeled data. LCC applies a simple linear transformation estimated on a held-out calibration split; Tweedie's method locally de-shrink predictions using density score estimates and a noise scale learned upstream. We provide practical diagnostics for when a correction is warranted and discuss practical limitations. Across analytical results, simulations, and experiments with Demographic and Health Surveys (DHS) data, both approaches reduce attenuation; Tweedie's correction yields nearly unbiased treatment-effect estimates, enabling a "one map, many trials" paradigm. Although we demonstrate on EO-ML wealth mapping, the methods are not geospatial-specific: they apply to any setting where imputed outcomes are reused downstream (e.g., pollution indices, population density, or LLM-derived indicators).