RainDisaggGAN - Temporal Disaggregation of Spatial Rainfall Fields with Generative Adversarial Networks

This is a Preprint and has not been peer reviewed. This is version 1 of this Preprint.


Download Preprint

Supplementary Files

Sebastian Scher, Stefanie Peßenteiner


Creating spatially coherent rainfall patterns with high temporal resolution
from data with lower temporal resolution is an important topic in
many geoscientific applications. From a statistical perspective, this
presents a high-dimensional and highly under-determined
problem. However, recent advances in unsupervised machine learning
provide methods for learning such high-dimensional probability distributions.
We show that it is possible to use Generative Adversarial Networks
(GANs) for estimating the full probability distribution of spatial
rainfall patterns with high temporal resolution, conditioned on a
spatial field of lower temporal resolution, requiring no knowledge
of the underlying processes. The GAN is trained on rainfall radar
data. Given a new field of daily precipitation sums, it can be used
to sample scenarios of spatiotemporal patterns with sub-daily resolution,
at very low computational cost. While the generated patterns do not
perfectly reproduce the statistics of the observations, they are visually
hardly distinguishable from the real patterns.




Artificial Intelligence and Robotics, Computer Sciences, Earth Sciences, Hydrology, Physical Sciences and Mathematics


machine learning, hydrology, Neural Networks, Artificial Intelligence, Precipitation, disaggregation, downscaling, GAN


Published: 2020-03-30 16:03


CC BY Attribution 4.0 International

Add a Comment

You must log in to post a comment.


There are no comments or no comments have been made public for this article.