Spatiotemporal double machine learning to estimate the impact of Cambodian land concessions on deforestation

2026-02-20

AI Summary

This study evaluates the causal effect of land concessions on deforestation in Cambodia, addressing the challenges posed by spatiotemporal correlation and unobserved confounding that hinder conventional approaches. To this end, the authors propose a novel causal inference framework that integrates double machine learning with spatiotemporal modeling. Building upon a two-way spatial regression, the method incorporates a temporal dimension and combines Bayesian Additive Regression Trees (BART) with spatial embedding techniques to identify policy effects through residual comparisons. Extensive simulations and empirical analyses demonstrate that, under complex spatiotemporal dependencies, the proposed approach substantially outperforms traditional difference-in-differences methods and provides the first robust quantification of the significant positive impact of land concessions on deforestation.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Environmental policy evaluation frequently requires thoughtful consideration of space and time in causal inference. We use novel statistical methods to analyze the causal effect of land concessions on deforestation rates in Cambodia. Standard approaches, such as difference-in-differences regression, effectively address spatiotemporally-correlated treatments under some conditions, but they are limited in their ability to account for unobserved confounders affecting both treatment and outcome. Double Spatial Regression (DSR) is an approach that uses double machine learning to address these scenarios. DSR resolves the confounding variables for both treatment and outcome, comparing the residuals to estimate treatment effectiveness. We improve upon DSR by considering time in our analysis of policy interventions with spatial effects. We conduct a large-scale simulation study using Bayesian Additive Regression Trees (BART) with spatial embeddings and find that, under certain conditions, our DSR model outperforms standard approaches for addressing unobserved spatial confounding. We then apply our method to evaluate the policy impacts of land concessions on deforestation in Cambodia.

Problem

• land concessions
• deforestation
• causal inference
• spatiotemporal confounding
• environmental policy evaluation

Innovation

• spatiotemporal double machine learning
• Double Spatial Regression
• unobserved confounding
• causal inference
• Bayesian Additive Regression Trees