Projects per year
Abstract
Specialized Gaussian process regression is presented for data that are known to fulfill a given linear differential equation with vanishing or localized sources. The method allows estimation of system parameters as well as strength and location of point sources. It is applicable to a wide range of data from measurement and simulation. The underlying principle is the wellknown invariance of the Gaussian probability distribution under linear operators, in particular differentiation. In contrast to approaches with a generic covariance function/kernel, we restrict the Gaussian process to generate only solutions of the homogeneous part of the differential equation. This requires specialized kernels with a direct correspondence of certain kernel hyperparameters to parameters in the underlying equation and leads to more reliable regression results with less training data. Inhomogeneous contributions from linear superposition of point sources are treated via a linear model over fundamental solutions. Maximum likelihood estimates for hyperparameters and source positions are obtained by nonlinear optimization. For differential equations representing laws of physics the present approach generates only physically possible solutions, and estimated hyperparameters represent physical properties. After a general derivation, modeling of sourcefree data and parameter estimation is demonstrated for Laplace’s equation and the heat/diffusion equation. Finally, the Helmholtz equation with point sources is treated, representing scalar wave data such as acoustic pressure in the frequency domain.
Original language  English 

Article number  152 
Journal  Entropy 
Volume  22 
Issue number  2 
DOIs  
Publication status  Published  27 Jan 2020 
Keywords
 Field reconstruction
 Gaussian process regression
 Kernel methods
 Meshless methods
 Partial differential equations
 Physicsinformed methods
 Source localization
ASJC Scopus subject areas
 Physics and Astronomy(all)
Fingerprint
Dive into the research topics of 'Gaussian Process Regression for Data Fulfilling Linear Differential Equations with Localized Sources'. Together they form a unique fingerprint.Projects
 1 Active

EUROFusion  Transport and Heating in Fusion Plasmas
Kernbichler, W., Albert, C., Eder, M., Kasilov, S., Markl, M., Buchholz, R., Graßler, G. S., Kamendje, R. L., Babin, R. & Lainer, P.
1/01/21 → 31/12/23
Project: Research project