Envisioning generative artificial intelligence in cartography: mapmaking, map use, and ethics

Abstract

Generative artificial intelligence (GenAI), including large language models, diffusion-based image generation models and GenAI agents, has opened up new possibilities for advancing cartography, spanning both mapmaking and map use. With its exceptional ability to encode extensive knowledge, adapt across contexts, create diverse artistic styles and integrate multimodal information, GenAI holds great potential to enhance cartographic design decisions. It enables efficient, personalized, and creative mapmaking (e.g., conceptualization, data preparation, map design, and map evaluation), and map use (e.g., map reading, interpretation, and analysis). In this paper, we explore why and how GenAI can contribute to cartography through four case studies, including stylesheet design, icon design, map reading, and map evaluation. Despite its unprecedented potential, we also identify its current limitations, particularly in tasks that require high precision, reliability, and a deep understanding of cartographic principles. Moreover, we emphasize the need to consider ethical and social implications, such as issues related to confabulation and hallucination, reproducibility, biases, copyrights, explainability, and sustainability. Overall, this work lays the foundation and provides a roadmap for future studies at the promising yet challenging intersection of GenAI and cartography.

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 — 2 citations exist upstream.

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