Integrating Earth Observation Data into Causal Inference

Authors: Connor Jerzak | Fredrik Johansson | Adel Daoud

Motivation

In recent years, the technology world has experienced a space renaissance, with the number of satellites doubling since 2019 and with the space economy reaching $424 billion in economic value in 2020. Much of this innovation has come in the form of new earth observation technologies. About 1/3 of all satellites are earth observation in nature, meaning that these satellites are devoted to imaging the earth. Moreover, from firms such as Maxar, 15-by-15 cm resolution satellite images are now available to researchers for nearly every place on earth. This means that even small objects such can now be reliably discerned from space.

Despite this space renaissance, the social science communityhas as of yet not yet explored the full potential of earth observation data for improving the practice of quantitative social science. These earth observation data have important strengths for social science: they are not subject to missingness due to the action of the people being studied, they are available for nearly every place on earth, they can be obtained (in some cases) on a daily basis, a nearly unparalleled temporal resolution compared to many social science datasets that are accessible on a yearly basis at best.

Paper Contributions

In this paper, we explore these strengths of earth observation data for social science, especially social science using causal inference methods. We argue that the data stream can provide valuable information about neighborhood-level confounders that otherwise make the practice of causal inference difficult. These confounders are what separate correlation from causation. For example, communities that do receive an aide program in the African context may be at baseline different from those that do not. Satellite data can bring to bear significant and qualitatively new information to model—and adjust for—these kinds of differences.

To support our argument, our paper contains several broad lines of investigation. Analytically, we investigate the assumptions required to formally prove what is known as identification, which allows one to argue for causality when using satellite images in observational causal inference. Via simulation, we probe the role of resolution and model misspecification in affecting the quality of causal effect estimates when using earth observation data in the research pipeline. We discuss how to learn about what in the earth observation data is associated with different treatment decisions via the application of a computational tool known as automatic differentiation.

Finally, we apply earth observation data to the study of anti-poverty assistance in Nigeria, where we find that the satellite information is useful in separating out causation from correlation. Throughout the paper, we keep our eye to the future—to how this unique data stream may come to shape quantitative social science in the years to come.

Table comparing properties of tabular, text, network, and earth observation data streams, including origin, high dimensionality, interpretability, and availability

Pair of directed acyclic graphs demonstrating image-based confounding at the scene level and confounding due to objects not in the image

Pair of directed acyclic graphs demonstrating image-based confounding at the scene level and confounding due to objects not in the image (dark mode)

Maps showing Nigeria highlighted in Africa and Nigeria with treatment and control sites indicated by black and gray points

Maps showing Nigeria highlighted in Africa and Nigeria with treatment and control sites indicated by black and gray points (dark mode)

–

References

Connor T. Jerzak, Fredrik Johansson, Adel Daoud. Integrating Earth Observation Data into Causal Inference: Challenges and Opportunities. ArXiv Preprint, 2023.

@article{jerzak2023integrating,
  title={Integrating Earth Observation Data into Causal Inference: Challenges and Opportunities},
  author={Jerzak, Connor T. and Fredrik Johansson and Adel Daoud},
  journal={ArXiv Preprint},
  year={2023},
  pages={},
  publisher={}
}

[Code][Data]

–

Related Work

Markus B. Pettersson, Connor T. Jerzak, Adel Daoud. Debiasing Machine Learning Predictions for Causal Inference Without Additional Ground Truth Data: 'One Map, Many Trials' in Satellite-Driven Poverty Analysis. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI-2026), Special Track on AI for Social Impact, 40: 39106-39115, 2026.

@article{pettersson2026debiasing,
  title={Debiasing Machine Learning Predictions for Causal Inference Without Additional Ground Truth Data: 'One Map, Many Trials' in Satellite-Driven Poverty Analysis},
  author={Pettersson, Markus B. and Connor T. Jerzak and Adel Daoud},
  journal={Proceedings of the AAAI Conference on Artificial Intelligence (AAAI-2026), Special Track on AI for Social Impact},
  year={2026},
  volume={40},
  pages={39106-39115},
  publisher={}
}

[Overview][Code][>]

–

Adel Daoud, Cindy Conlin, Connor T. Jerzak. Chinese vs. World Bank Development Projects: Insights from Earth Observation and Computer Vision on Wealth Gains in Africa, 2002-2013. World Development, 202: 107328, 2026.

@article{daoud2026chinese,
  title={Chinese vs. World Bank Development Projects: Insights from Earth Observation and Computer Vision on Wealth Gains in Africa, 2002-2013},
  author={Daoud, Adel and Cindy Conlin and Connor T. Jerzak},
  journal={World Development},
  year={2026},
  volume={202},
  pages={107328},
  publisher={}
}

[Overview][Data]

–

Adel Daoud, Connor T. Jerzak. Planetary Causal Inference: Understanding the Environment, Society, and Economy through Earth Observation and AI Systems. A Book Project, 2026+.

@article{daoud2026+planetary,
  title={Planetary Causal Inference: Understanding the Environment, Society, and Economy through Earth Observation and AI Systems},
  author={Daoud, Adel and Connor T. Jerzak},
  journal={A Book Project},
  year={2026+},
  volume={},
  pages={},
  publisher={Under contract with Cambridge University Press}
}

–

Warren Zhu Fucheng, Connor T. Jerzak, Adel Daoud. Optimizing Multi-Scale Representations to Detect Effect Heterogeneity Using Earth Observation and Computer Vision: Applications to Two Anti-Poverty RCTs. Proceedings of the Fourth Conference on Causal Learning and Reasoning (CLeaR), Proceedings of Machine Learning Research (PMLR), 2025.

@article{fucheng2025optimizing,
  title={Optimizing Multi-Scale Representations to Detect Effect Heterogeneity Using Earth Observation and Computer Vision: Applications to Two Anti-Poverty RCTs},
  author={Fucheng, Warren Zhu and Connor T. Jerzak and Adel Daoud},
  journal={Proceedings of the Fourth Conference on Causal Learning and Reasoning (CLeaR), Proceedings of Machine Learning Research (PMLR)},
  year={2025},
  volume={},
  pages={},
  publisher={}
}

[Overview][Data][Code]
[Video][>]

–

Connor T. Jerzak, Ritwik Vashistha, Adel Daoud. Effect Heterogeneity with Earth Observation in Randomized Controlled Trials: Exploring the Role of Data, Model, and Evaluation Metric Choice. ArXiv Preprint, 2024.

@article{jerzak2024effect,
  title={Effect Heterogeneity with Earth Observation in Randomized Controlled Trials: Exploring the Role of Data, Model, and Evaluation Metric Choice},
  author={Jerzak, Connor T. and Ritwik Vashistha and Adel Daoud},
  journal={ArXiv Preprint},
  year={2024},
  volume={},
  pages={},
  publisher={}
}

[Overview]

–

Connor T. Jerzak, Fredrik Johansson, Adel Daoud. Image-based Treatment Effect Heterogeneity. Proceedings of the Second Conference on Causal Learning and Reasoning (CLeaR), Proceedings of Machine Learning Research (PMLR), 213: 531-552, 2023.

@article{jerzak2023image,
  title={Image-based Treatment Effect Heterogeneity},
  author={Jerzak, Connor T. and Fredrik Johansson and Adel Daoud},
  journal={Proceedings of the Second Conference on Causal Learning and Reasoning (CLeaR), Proceedings of Machine Learning Research (PMLR)},
  year={2023},
  volume={213},
  pages={531-552},
  publisher={}
}

[Overview][Data][Code]

–

Kazuki Sakamoto, Connor T. Jerzak, Adel Daoud. A Scoping Review of Earth Observation and Machine Learning for Causal Inference: Implications for the Geography of Poverty. To appear in: Hall, Ola and Ibrahim Wahab (eds.), Geography of Poverty, 2024.

@article{sakamoto2024scoping,
  title={A Scoping Review of Earth Observation and Machine Learning for Causal Inference: Implications for the Geography of Poverty},
  author={Sakamoto, Kazuki and Connor T. Jerzak and Adel Daoud},
  journal={To appear in: Hall, Ola and Ibrahim Wahab (eds.), Geography of Poverty},
  year={2024},
  volume={},
  pages={},
  publisher={Edward Elgar Publishing (Cheltenham, UK)}
}

[Overview][Data]

–

Connor T. Jerzak, Adel Daoud. CausalImages: An R Package for Causal Inference with Earth Observation, Bio-medical, and Social Science Images. ArXiv Preprint, 2023.

@article{jerzak2023causalimages,
  title={CausalImages: An R Package for Causal Inference with Earth Observation, Bio-medical, and Social Science Images},
  author={Jerzak, Connor T. and Adel Daoud},
  journal={ArXiv Preprint},
  year={2023},
  volume={},
  pages={},
  publisher={}
}

[Overview][Code]

–

Back to Research
Back to Home