Synthetic geospatial data and fake geography: A case study on the implications of AI-derived data in a data-intensive society

Abstract

This paper presents a case study that aims to analyze and compare original and synthetic geospatial data at the intra-urban scale. The goal is to explore the potential implications of the spread of synthetic data in scenarios where geospatial data are essential for decoding socio-spatial changes and where Geo-visualization is pivotal for spatial decision support. The methodology is based on a) the production of a synthetic dataset and b) the evaluation of the spatial similarity with the original one. Specifically, we employ a synthetic data provider, namely Mostly.AI, alongside geospatial data related to Airbnb listings in Florence, Italy. Results show which criticalities are linked to AI-derived data compared to the original ones, highlighting crucial spatial similarities and dissimilarities. Finally, the work critically discusses the broader societal implications of the widespread online synthetic data platforms, exploring the impacts of such a technological (re)evolution in a data-intensive society.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 12 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.