Explainable AI in Spatial Analysis

TL;DR

This paper explores the integration of explainable AI techniques, especially Shapley values, into spatial analysis to improve understanding of machine learning models applied to spatial data, demonstrated through voting behavior analysis.

Contribution

It introduces the application of Shapley value-based XAI methods in spatial analysis and compares them with traditional spatial models like geographically weighted regression.

Findings

Shapley values effectively explain machine learning model outputs in spatial contexts.

XAI methods enhance transparency and model diagnosis in spatial data science.

Comparison shows strengths and limitations of XAI versus traditional spatial models.

Abstract

This chapter discusses the opportunities of eXplainable Artificial Intelligence (XAI) within the realm of spatial analysis. A key objective in spatial analysis is to model spatial relationships and infer spatial processes to generate knowledge from spatial data, which has been largely based on spatial statistical methods. More recently, machine learning offers scalable and flexible approaches that complement traditional methods and has been increasingly applied in spatial data science. Despite its advantages, machine learning is often criticized for being a black box, which limits our understanding of model behavior and output. Recognizing this limitation, XAI has emerged as a pivotal field in AI that provides methods to explain the output of machine learning models to enhance transparency and understanding. These methods are crucial for model diagnosis, bias detection, and ensuring the reliability of results obtained from machine learning models. This chapter introduces key concepts and methods in XAI with a focus on Shapley value-based approaches, which is arguably the most popular XAI method, and their integration with spatial analysis. An empirical example of county-level voting behaviors in the 2020 Presidential election is presented to demonstrate the use of Shapley values and spatial analysis with a comparison to multi-scale geographically weighted regression. The chapter concludes with a discussion on the challenges and limitations of current XAI techniques and proposes new directions.