Explainable artificial intelligence in the spatial domain (X-GeoAI)

Emmanuel Papadakis, Ben Adams, Song Gao, Bruno Martins, George Baryannis, Alina Ristea

Research output: Contribution to journalEditorialpeer-review

Abstract

Recent advances in artificial intelligence (AI) research, the significant increase in computational power, and the large-scale availability of data have ushered in a new era of data-intensive science. In the context of GIScience, GeoAI aims to employ AI methods to analyze complex geographic phenomena. The majority of GeoAI applications rely on machine learning (ML) algorithms to extract generalizable predictive patterns in the form of mathematical models that provide useful insights about the phenomenon in question. ML excels in efficiency, scalability, and accuracy; however, this comes at the cost of reduced explainability. A clear reasoning path from data to conclusions is not always evident, but is readily available in traditional analysis of geographic phenomena using a combination of conceptual and statistical models. In addition, the integration of ML techniques in the geographic context is not always straightforward.
Original languageEnglish
Pages (from-to)2413-2414
Number of pages2
JournalTransactions in GIS
Volume26
Issue number6
Early online date26 Sep 2022
DOIs
Publication statusPublished - 26 Sep 2022

Fingerprint

Dive into the research topics of 'Explainable artificial intelligence in the spatial domain (X-GeoAI)'. Together they form a unique fingerprint.

Cite this