Wind Field Reconstruction with Adaptive Random Fourier Features

by   Jonas Kiessling, et al.

We investigate the use of spatial interpolation methods for reconstructing the horizontal near-surface wind field given a sparse set of measurements. In particular, random Fourier features is compared to a set of benchmark methods including Kriging and Inverse distance weighting. Random Fourier features is a linear model β( x) = ∑_k=1^K β_k e^iω_k x approximating the velocity field, with frequencies ω_k randomly sampled and amplitudes β_k trained to minimize a loss function. We include a physically motivated divergence penalty term |∇·β( x)|^2, as well as a penalty on the Sobolev norm. We derive a bound on the generalization error and derive a sampling density that minimizes the bound. Following (arXiv:2007.10683 [math.NA]), we devise an adaptive Metropolis-Hastings algorithm for sampling the frequencies of the optimal distribution. In our experiments, our random Fourier features model outperforms the benchmark models.



There are no comments yet.


page 15

page 16

page 17


Adaptive random Fourier features with Metropolis sampling

The supervised learning problem to determine a neural network approximat...

Smaller generalization error derived for deep compared to shallow residual neural networks

Estimates of the generalization error are proved for a residual neural n...

Large-Scale Learning with Fourier Features and Tensor Decompositions

Random Fourier features provide a way to tackle large-scale machine lear...

The Fourier Loss Function

This paper introduces a new loss function induced by the Fourier-based M...

Sparse Fourier Transforms on Rank-1 Lattices for the Rapid and Low-Memory Approximation of Functions of Many Variables

We consider fast, provably accurate algorithms for approximating functio...

Fourier Sparse Leverage Scores and Approximate Kernel Learning

We prove new explicit upper bounds on the leverage scores of Fourier spa...

Bayesian Assessments of Aeroengine Performance

Aeroengine performance is determined by temperature and pressure profile...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.