Abstract
Abstract. Creating spatially coherent rainfall patterns with high temporal resolution from data with lower temporal resolution is necessary in many geoscientific applications. From a statistical perspective, this presents a high- dimensional, highly underdetermined problem. Recent advances in machine learning provide methods for learning such probability distributions. We test the usage of generative adversarial networks (GANs) for estimating the full probability distribution of spatial rainfall patterns with high temporal resolution, conditioned on a field of lower temporal resolution. The GAN is trained on rainfall radar data with hourly resolution. Given a new field of daily precipitation sums, it can sample scenarios of spatiotemporal patterns with sub-daily resolution. While the generated patterns do not perfectly reproduce the statistics of observations, they are visually hardly distinguishable from real patterns. Limitations that we found are that providing additional input (such as geographical information) to the GAN surprisingly leads to worse results, showing that it is not trivial to increase the amount of used input information. Additionally, while in principle the GAN should learn the probability distribution in itself, we still needed expert judgment to determine at which point the training should stop, because longer training leads to worse results.
Highlights
Precipitation time series at sub-daily temporal resolution are required for numerous applications in environmental modeling
generative adversarial networks (GANs) are a special class of artificial neural networks that were originally developed for estimating the probability distribution of images, with the goal of sampling images from these distributions
Due to the many possible patterns that can be associated with a single daily sum, there is a lot of variation in the GAN-generated patterns
Summary
Precipitation time series at sub-daily temporal resolution are required for numerous applications in environmental modeling. Peßenteiner: Temporal disaggregation spatial rainfall with GANs to generate a corresponding 3D field of sub-daily precipitation (tres × nlat × nlon) yabs. Since this is a highly underdetermined problem, it is our goal to model the probability distribution. GANs are a special class of artificial neural networks that were originally developed for estimating the probability distribution of images, with the goal of sampling (or “generating”) images from these distributions (widely known as “deep fakes”) In their conditional formulation (Mirza and Osindero, 2014) they are potentially very useful for physics-related problems, such as the one considered in this study. Here we refer to these strictly as “patterns”
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
