Simulation of Fluvial Patterns With GANs Trained on a Data Set of Satellite Imagery

Models that can generate realistic Earth surface patterns are important both for geomorphological applications and as prior models for underdetermined inverse problems. Generative machine learning methods such as GANs and the increasing availability of large remote sensing data sets represents an exciting combination for this purpose. Several studies show promising results for GANs trained on artificial data sets in geostatistics, but it is necessary to further quantify how well such models reproduce and generalize real data. The conditioning ability of GANs is often evaluated based on output which originates from a trained generator. In reality, geophysical data necessarily arises from elsewhere. Here, we use more realistic training data than in previous studies and evaluate performance using an extensive set of metrics and real images outside the training data set. The data set consists of multispectral satellite imagery of 38 large river deltas, a type of Earth surface pattern which is limited in number. The channel network is used to create training images with four sedimentary facies, which are subsequently used to train a Wasserstein GAN of deltaic 2D patterns. GANs successfully reproduce all training data characteristics and produce manifold the number of combinations with respect to the training data. However, there does not seem to be an infinite number of discrete combinations of facies, and the posterior landscapes are not well-shaped for efficient exploration in the presence of so-called hard data. Thus, GANs should have many exciting applications in geosciences, but it will depend on the type of measurement data.

Automated summary

Models that can generate realistic Earth surface patterns are important for geomorphological applications and underdetermined inverse problems. Generative machine learning methods like GANs, when trained on artificial data sets in geostatistics, show promising results but further quantification is needed to evaluate their ability to reproduce and generalize real data efficiently.