Das Paper "ConvMOS: climate model output statistics with deep learning" ist nun verfügbar

Die Forschung im BigData@Geo-Projekt zum Thema Klimadaten und Machine Learning hat einige Früchte getragen. Eine davon ist nun im Journal “Data Mining and Knowledge Discovery” erschienen. Die wissenschaftliche Arbeit “ConvMOS: climate model output statistics with deep learning” von Michael Steininger, Daniel Abel, Katrin Ziegler, Anna Krause, Heiko Paeth und Andreas Hotho ist nun online verfügbar. In dem Paper geht es um die Verbesserung der Ausgabe von Klimamodellen mithilfe von neuronalen Netzen.

Zusammenfassung auf Englisch

Climate models are the tool of choice for scientists researching climate change. Like all models they suffer from errors, particularly systematic and location-specific representation errors. One way to reduce these errors is model output statistics (MOS) where the model output is fitted to observational data with machine learning. In this work, we assess the use of convolutional Deep Learning climate MOS approaches and present the ConvMOS architecture which is specifically designed based on the observation that there are systematic and location-specific errors in the precipitation estimates of climate models. We apply ConvMOS models to the simulated precipitation of the regional climate model REMO, showing that a combination of per-location model parameters for reducing location-specific errors and global model parameters for reducing systematic errors is indeed beneficial for MOS performance. We find that ConvMOS models can reduce errors considerably and perform significantly better than three commonly used MOS approaches and plain ResNet and U-Net models in most cases. Our results show that non-linear MOS models underestimate the number of extreme precipitation events, which we alleviate by training models specialized towards extreme precipitation events with the imbalanced regression method DenseLoss. While we consider climate MOS, we argue that aspects of ConvMOS may also be beneficial in other domains with geospatial data, such as air pollution modeling or weather forecasts.