Future Cartography

Can AI help make maps that are both accurate and beautiful?

The GISense Lab has been pioneering AI in cartography for decades. Our work ranges from the seminal Map Style Transfer that uses Generative Adversarial Networks to learn cartographic styles from existing maps and art and reapply them across multiscale maps, to a comprehensive Review of GeoAI for cartography, a Perspective of Generative AI for cartography, an Ethical Framework of AI-generated maps, and the next generation AI-assisted map design Agentic system CartoAgent. Together, these projects provide a path for how GeoAI can be integrated into mapmaking practice.

Looking forward, AI is not only a black-box map generator, but also a co-designer that helps empower human creativity and encode cartographic expertise to create ethical and visually appealing maps.

Beyond research, Dr. Kang teaches Cartography and Maps at UT-Austin. Students not only learn traditional practices of mapmaking, but also integrate AI to train a new generation of cartographers.

References

Kang, Y., Gao, S. and Roth, R.E., 2019. Transferring multiscale map styles using generative adversarial networks. International Journal of Cartography, 5(2-3), pp.115-141.

Kang, Y., Gao, S. and Roth, R.E., 2024. Artificial intelligence studies in cartography: a review and synthesis of methods, applications, and ethics. Cartography and Geographic Information Science, 51(4), pp.599-630.

Wang, C., Kang, Y., Gong, Z., Zhao, P., Feng, Y., Zhang, W. and Li, G., 2025. CartoAgent: a multimodal large language model-powered multi-agent cartographic framework for map style transfer and evaluation. International Journal of Geographical Information Science, pp.1-34.

Kang, Y. and Wang, C., 2025. Envisioning Generative Artificial Intelligence in Cartography and Mapmaking. arXiv preprint arXiv:2508.09028

Zhang, Q., Kang, Y. and Roth, R., 2023. The Ethics of AI-Generated Maps: DALL· E 2 and AI’s Implications for Cartography (Short Paper). In 12th International conference on geographic information science (GIScience 2023) (pp. 93-1). Schloss Dagstuhl–Leibniz-Zentrum für Informatik.

Kang, Y., Rao, J., Wang, W., Peng, B., Gao, S. and Zhang, F., 2020, May. Towards cartographic knowledge encoding with deep learning: A case study of building generalization. In Proceedings of the AutoCarto (pp. 1-6).

Kang, Y., Wang, C., Feng, Y., Touya, G. and Kim, J., 2025. Artificial Intelligence for Cartography and Maps. In GeoAI and Human Geography: The Dawn of a New Spatial Intelligence Era (pp. 219-237). Cham: Springer Nature Switzerland.