Deep Learning-based Parameter Transfer in Meteorological Data
Fatemeh Farokhmanesh1, Kevin Höhlein1, Tobias Necker2, Martin Weissmann2, Takemasa Miyoshi3, Rüdiger Westermann1
1 Chair for Computer Graphics and Visualization, Technical University of Munich, Germany
2 Department of Meteorology and Geophysics, University of Vienna, Austria
3 RIKEN Center for Computational Science, Kobe, Japan
Abstract
Numerical simulations in earth-system sciences consider a multitude of physical parameters in space and time, leading to severe I/O bandwidth requirements and challenges in subsequent data analysis tasks. Deep-learning based identification of redundant parameters and prediction of those from other parameters, i.e. Variable-to-Variable (V2V) transfer, has been proposed as an approach to lessening the bandwidth requirements and streamlining subsequent data analysis. In this paper, we examine the applicability of V2V to meteorological reanalysis data. We find that redundancies within pairs of parameter fields are limited, which hinders application of the original V2V algorithm. Therefore, we assess the predictive strength of reanalysis parameters by analyzing the learning behavior of V2V reconstruction networks in an ablation study. We demonstrate that efficient V2V transfer becomes possible when considering groups of parameter fields for transfer, and propose an algorithm to implement this. We investigate further whether the neural networks trained in the V2V process can yield insightful representations of recurring patterns in the data. The interpretability of these representations is assessed via layer-wise relevance propagation that highlights field areas and parameters of high importance for the reconstruction model. Applied to reanalysis data, this allows uncovering mutual relationships between landscape orography and different regional weather situations. We see our approach as an effective means to reduce bandwidth requirements in numerical weather simulations, which can be used on top of conventional data compression schemes. The proposed identification of multi-parameter features can spawn further research on the importance of regional weather situations for parameter prediction, also in other kinds of simulation data.
Associated publications
Deep Learning-based Parameter Transfer in Meteorological Data
Fatemeh Farokhmanesh, Kevin Höhlein, Tobias Necker, Martin Weissmann, Takemasa Miyoshi, Rüdiger Westermann
Artificial Intelligence for the Earth Systems 2022
[PDF]