Deep Causal Inference for Point-referenced Spatial Data with Continuous Treatments

TL;DR

This paper introduces a neural network framework combined with Gaussian processes and propensity scores to improve causal inference in spatial data with continuous treatments, outperforming traditional methods in accuracy and decision-making.

Contribution

The paper presents a novel neural network approach integrated with Gaussian processes and propensity scores for causal inference in spatial data with continuous treatments, handling high-dimensional inputs and unobserved confounding.

Findings

Neural network models outperform linear regression in causal effect estimation.

NN-based models provide more reasonable causal effect predictions in real-world applications.

Framework effectively manages spatial interference and unobserved confounding.

Abstract

Causal reasoning is often challenging with spatial data, particularly when handling high-dimensional inputs. To address this, we propose a neural network (NN) based framework integrated with an approximate Gaussian process to manage spatial interference and unobserved confounding. Additionally, we adopt a generalized propensity-score-based approach to address partially observed outcomes when estimating causal effects with continuous treatments. We evaluate our framework using synthetic, semi-synthetic, and real-world data inferred from satellite imagery. Our results demonstrate that NN-based models significantly outperform linear spatial regression models in estimating causal effects. Furthermore, in real-world case studies, NN-based models offer more reasonable predictions of causal effects, facilitating decision-making in relevant applications.