University of Twente Student Theses
The role of machine learning in closing the moments of the stationary radiative transfer equation
Veurink, T.R. (2024) The role of machine learning in closing the moments of the stationary radiative transfer equation.
|
PDF
777kB |
| Abstract: | When solving the radiative transfer equation, it is common to take the moments against the Legendre polynomials. However, solving this set of equations is difficult because it has n variables and n+1 unknowns. In this paper we take a look if this gap in knowledge can be overcome with a solution in the form of machine learning. We experiment with proper normalizations and try to offer good neural network structures to circumvent not knowing 1 of the moments. We find that neural networks with the gradients, fluxes, and moments, all give good approximations to the fifth moment. Here the gradients perform best and the moments perform worst. Even though a normalization with m0 did significantly improve the performance of a neural network with moments as inputs, good normalization factor were not found for the other structures. |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 31 mathematics |
| Programme: | Applied Mathematics BSc (56965) |
| Link to this item: | https://purl.utwente.nl/essays/104656 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page