Towards Modeling Geographical Processes with Generative Adversarial Networks (GANs) (Short Paper)

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. 2012 ACM Subject Classification Computing methodologies → Neural networks

[1]  Yu Tian,et al.  A Deep Generative Adversarial Architecture for Network-Wide Spatial-Temporal Traffic-State Estimation , 2018, Transportation Research Record: Journal of the Transportation Research Board.

[2]  Emanuele Strano,et al.  Modeling Urbanization Patterns with Generative Adversarial Networks , 2018, IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium.

[3]  Dit-Yan Yeung,et al.  Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting , 2015, NIPS.

[4]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[5]  Andrew L. Maas.  Rectifier Nonlinearities Improve Neural Network Acoustic Models , 2013 .

[6]  P. Torrens,et al.  Geosimulation: Automata-based modeling of urban phenomena , 2004 .

[7]  Arief Koesdwiady,et al.  Improving Multi-Step Traffic Flow Prediction , 2018, ArXiv.

[8]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[9]  Cláudio Elízio Calazans Campelo,et al.  Identifying Geographical Processes from Time-Stamped Data , 2011, GeoS.

[10]  Patrice Langlois.  Simulation of Complex Systems in GIS: Langlois/Simulation of Complex Systems in GIS , 2013 .

[11]  Bin Ran,et al.  Space-mean-speed Prediction Based on the Fusion of Multi-source Data , 2017 .

[12]  Marc P. Armstrong,et al.  Temporality in Spatial Databases , 1988 .

[13]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[14]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[15]  Yang Zhang,et al.  Road Topology Refinement via a Multi-Conditional Generative Adversarial Network , 2019, Sensors.

[16]  Master Gardener,et al.  Mathematical games: the fantastic combinations of john conway's new solitaire game "life , 1970 .

[17]  Christophe Claramunt,et al.  A Survey of Modelling Trends in Temporal GIS , 2018, ACM Comput. Surv..

[18]  Galit Shmueli,et al.  To Explain or To Predict? , 2010, 1101.0891.

[19]  Eric P. Xing,et al.  Dual Motion GAN for Future-Flow Embedded Video Prediction , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[20]  Pieter Abbeel,et al.  InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets , 2016, NIPS.

[21]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[22]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[23]  Sergey Levine,et al.  Stochastic Adversarial Video Prediction , 2018, ArXiv.