Connectivity-informed Drainage Network Generation using Deep Convolution Generative Adversarial Networks

TL;DR

This paper introduces a novel connectivity-informed method for training Deep Convolutional GANs to efficiently generate realistic drainage networks, improving over traditional methods by better capturing network connectivity and reducing computational costs.

Contribution

The study develops a connectivity-informed approach that transforms drainage networks into directional and connectivity data, enhancing DCGAN training and network reproduction accuracy.

Findings

Connectivity-informed method outperforms other training data types

DCGANs effectively reproduce complex drainage networks

Improved network generation efficiency and accuracy

Abstract

Stochastic network modeling is often limited by high computational costs to generate a large number of networks enough for meaningful statistical evaluation. In this study, Deep Convolutional Generative Adversarial Networks (DCGANs) were applied to quickly reproduce drainage networks from the already generated network samples without repetitive long modeling of the stochastic network model, Gibb's model. In particular, we developed a novel connectivity-informed method that converts the drainage network images to the directional information of flow on each node of the drainage network, and then transform it into multiple binary layers where the connectivity constraints between nodes in the drainage network are stored. DCGANs trained with three different types of training samples were compared; 1) original drainage network images, 2) their corresponding directional information only, and 3) the connectivity-informed directional information. Comparison of generated images demonstrated that the novel connectivity-informed method outperformed the other two methods by training DCGANs more effectively and better reproducing accurate drainage networks due to its compact representation of the network complexity and connectivity. This work highlights that DCGANs can be applicable for high contrast images common in earth and material sciences where the network, fractures, and other high contrast features are important.