2026-07-23T12:54:51Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:11119 2024-03-06T10:47:25Z ddc:004 open_access

Towards Modeling Geographical Processes with Generative Adversarial Networks (GANs) (Short Paper) Jonietz, David Kopp, Michael GAN generative modeling deep learning geosimulation game of life Recently, Generative Adversarial Networks (GANs) have demonstrated great potential for a range of Machine Learning tasks, including synthetic video generation, but have so far not been applied to the domain of modeling geographical processes. In this study, we align these two problems and - motivated by the potential advantages of GANs compared to traditional geosimulation methods - test the capability of GANs to learn a set of underlying rules which determine a geographical process. For this purpose, we turn to Conway’s well-known Game of Life (GoL) as a source for spatio-temporal training data, and further argue for its (and simple variants of it) usefulness as a potential standard training data set for benchmarking generative geographical process models. Schloss Dagstuhl – Leibniz-Zentrum für Informatik David Jonietz and Michael Kopp 2019 Is Part Of LIPIcs, Volume 142, 14th International Conference on Spatial Information Theory (COSIT 2019) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/LIPIcs.COSIT.2019.27 urn:nbn:de:0030-drops-111193 https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.COSIT.2019.27 eng https://creativecommons.org/licenses/by/3.0/legalcode