A Scoping Review of Earth Observation and Machine Learning for Causal Inference: Implications for the Geography of Poverty

2024-05-30

AI Summary

A systematic review and practical framework for integrating Earth observation (EO) data with machine learning (ML) to enable causal inference in poverty geography remains absent. Method: This paper introduces the first taxonomy of five EO-based paradigms for causal inference—including outcome imputation, image-based deconfounding, and heterogeneous treatment effect modeling—and establishes a standardized EO-ML causal analysis workflow aligned with the Sustainable Development Goals. The workflow integrates spatial statistics, computer vision, causal discovery, and counterfactual reasoning, emphasizing structured remote sensing representation and causally interpretable modeling. Contribution/Results: We deliver an actionable guideline covering data selection, model adaptation, and evaluation metrics, enhancing credibility and reproducibility of causal analyses across multidimensional development indicators—particularly health outcomes and housing conditions.

Technology Category

• Machine Learning: Causal Learning
• Computer Vision: Remote Sensing / Geospatial AI
• Reasoning under Uncertainty: Causality

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Earth observation (EO) data such as satellite imagery can have far-reaching impacts on our understanding of the geography of poverty, especially when coupled with machine learning (ML) and computer vision. Early research in computer vision used predictive models to estimate living conditions, especially in contexts where data availability on poverty was scarce. Recent work has progressed beyond using EO data to predict such outcomes -- now also using it to conduct causal inference. However, how such EO-ML models are used for causality remains incompletely mapped. To address this gap, we conduct a scoping review where we first document the growth of interest in using satellite images and other sources of EO data in causal analysis. We then trace the methodological relationship between spatial statistics and ML methods before discussing five ways in which EO data has been used in scientific workflows -- (1) outcome imputation for downstream causal analysis, (2) EO image deconfounding, (3) EO-based treatment effect heterogeneity, (4) EO-based transportability analysis, and (5) image-informed causal discovery. We consolidate these observations by providing a detailed workflow for how researchers can incorporate EO data in causal analysis going forward -- from data requirements to choice of computer vision model and evaluation metrics. While our discussion focuses on health and living conditions outcomes, our workflow applies to other measures of sustainable development where EO data are informative.

Problem

• EO-ML methods lack documentation for causal inference
• Need best practices for EO data in causal analysis
• Protocol for integrating EO into causal workflows

Innovation

• EO-ML for causal inference in poverty geography
• Five EO data approaches in causal workflows
• Protocol for EO data integration in analysis