arXiv subjects

Alex Bihlo

Publications and source records attributed to Alex Bihlo.

23 records · Page 2Linked to original sources

arXiv2022

Improving trajectory calculations using deep learning inspired single image superresolution

Lagrangian trajectory or particle dispersion models as well as semi-Lagrangian advection schemes require meteorological data such as wind, temperature and geopotential at the exact spatio-temporal locations of the particles that move independently from a regular grid. Traditionally, this high-resolution data has been obtained by interpolating the meteorological parameters from the gridded data of a meteorological model or reanalysis, e.g. using linear interpolation in space and time. However, interpolation errors are a large source of error for these models. Reducing them requires meteorological input fields with high space and time resolution, which may not always be available and can cause severe data storage and transfer problems. Here, we interpret this problem as a single image superresolution task. We interpret meteorological fields available at their native resolution as low-resolution images and train deep neural networks to up-scale them to higher resolution, thereby providing more accurate data for Lagrangian models. We train various versions of the state-of-the-art Enhanced Deep Residual Networks for Superresolution on low-resolution ERA5 reanalysis data with the goal to up-scale these data to arbitrary spatial resolution. We show that the resulting up-scaled wind fields have root-mean-squared errors half the size of the winds obtained with linear spatial interpolation at acceptable computational inference costs. In a test setup using the Lagrangian particle dispersion model FLEXPART and reduced-resolution wind fields, we demonstrate that absolute horizontal transport deviations of calculated trajectories from "ground-truth" trajectories calculated with undegraded 0.5° winds are reduced by at least 49.5% (21.8%) after 48 hours relative to trajectories using linear interpolation of the wind data when training on 2° to 1° (4° to 2°) resolution data.

physics.ao-ph↗

arXiv2022

Computing the ensemble spread from deterministic weather predictions using conditional generative adversarial networks

Ensemble prediction systems are an invaluable tool for weather forecasting. Practically, ensemble predictions are obtained by running several perturbations of the deterministic control forecast. However, ensemble prediction is associated with a high computational cost and often involves statistical post-processing steps to improve its quality. Here we propose to use deep-learning-based algorithms to learn the statistical properties of an ensemble prediction system, the ensemble spread, given only the deterministic control forecast. Thus, once trained, the costly ensemble prediction system will not be needed anymore to obtain future ensemble forecasts, and the statistical properties of the ensemble can be derived from a single deterministic forecast. We adapt the classical pix2pix architecture to a three-dimensional model and also experiment with a shared latent space encoder-decoder model, and train them against several years of operational (ensemble) weather forecasts for the 500 hPa geopotential height. The results demonstrate that the trained models indeed allow obtaining a highly accurate ensemble spread from the control forecast only.

cs.LG↗

arXiv2022

Physics-informed neural networks for the shallow-water equations on the sphere

We propose the use of physics-informed neural networks for solving the shallow-water equations on the sphere in the meteorological context. Physics-informed neural networks are trained to satisfy the differential equations along with the prescribed initial and boundary data, and thus can be seen as an alternative approach to solving differential equations compared to traditional numerical approaches such as finite difference, finite volume or spectral methods. We discuss the training difficulties of physics-informed neural networks for the shallow-water equations on the sphere and propose a simple multi-model approach to tackle test cases of comparatively long time intervals. Here we train a sequence of neural networks instead of a single neural network for the entire integration interval. We also avoid the use of a boundary value loss by encoding the boundary conditions in a custom neural network layer. We illustrate the abilities of the method by solving the most prominent test cases proposed by Williamson et al. [J. Comput. Phys. 102 (1992), 211-224].

physics.comp-ph↗

arXiv2021

Invariant Variational Schemes for Ordinary Differential Equations

We propose a novel algorithmic method for constructing invariant variational schemes of systems of ordinary differential equations that are the Euler-Lagrange equations of a variational principle. The method is based on the invariantization of standard, non-invariant discrete Lagrangian functionals using equivariant moving frames. The invariant variational schemes are given by the Euler-Lagrange equations of the corresponding invariantized discrete Lagrangian functionals. We showcase this general method by constructing invariant variational schemes of ordinary differential equations that preserve variational and divergence symmetries of the associated continuous Lagrangians. Noether's theorem automatically implies that the resulting schemes are exactly conservative. Numerical simulations are carried out and show that these invariant variational schemes outperform standard numerical discretizations.

math.NA↗

arXiv2020

On the development of symmetry-preserving finite element schemes for ordinary differential equations

In this paper we introduce a procedure, based on the method of equivariant moving frames, for formulating continuous Galerkin finite element schemes that preserve the Lie point symmetries of initial value problems for ordinary differential equations. Our methodology applies to projectable and non-projectable symmetry group actions, to ordinary differential equations of arbitrary order, and finite element approximations of arbitrary polynomial degree. Several examples are included to illustrate various features of the symmetry-preserving process. We summarise extensive numerical experiments showing that symmetry-preserving finite element schemes may provide better long term accuracy than their non-invariant counterparts and can be implemented on larger elements.

math.NA↗