Deep learning cosmic ray transport from density maps of simulated, turbulent gas
The coarse-grained propagation of galactic cosmic rays (CRs) is traditionally constrained by phenomenological models of Milky Way CR propagation fit to a variety of direct and indirect observables; however, constraining the fine-grained transport of CRs along individual magnetic field lines—for inst...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2024-01-01
|
| Series: | Machine Learning: Science and Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2632-2153/ad262a |
| _version_ | 1797310816837435392 |
|---|---|
| author | Chad Bustard John Wu |
| author_facet | Chad Bustard John Wu |
| author_sort | Chad Bustard |
| collection | DOAJ |
| description | The coarse-grained propagation of galactic cosmic rays (CRs) is traditionally constrained by phenomenological models of Milky Way CR propagation fit to a variety of direct and indirect observables; however, constraining the fine-grained transport of CRs along individual magnetic field lines—for instance, diffusive vs streaming transport models—is an unsolved challenge. Leveraging a recent training set of magnetohydrodynamic turbulent box simulations, with CRs spanning a range of transport parameters, we use convolutional neural networks (CNNs) trained solely on gas density maps to classify CR transport regimes. We find that even relatively simple CNNs can quite effectively classify density slices to corresponding CR transport parameters, distinguishing between streaming and diffusive transport, as well as magnitude of diffusivity, with class accuracies between 92% and 99%. As we show, the transport-dependent imprints that CRs leave on the gas are not all tied to the resulting density power spectra: classification accuracies are still high even when image spectra are flattened (85%–98% accuracy), highlighting CR transport-dependent changes to turbulent phase information. We interpret our results with saliency maps and image modifications, and we discuss physical insights and future applications. |
| first_indexed | 2024-03-08T01:48:33Z |
| format | Article |
| id | doaj.art-e9d803a0f6e549128c749bb495232055 |
| institution | Directory Open Access Journal |
| issn | 2632-2153 |
| language | English |
| last_indexed | 2024-03-08T01:48:33Z |
| publishDate | 2024-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Machine Learning: Science and Technology |
| spelling | doaj.art-e9d803a0f6e549128c749bb4952320552024-02-14T12:33:42ZengIOP PublishingMachine Learning: Science and Technology2632-21532024-01-015101502810.1088/2632-2153/ad262aDeep learning cosmic ray transport from density maps of simulated, turbulent gasChad Bustard0https://orcid.org/0000-0002-8366-2143John Wu1https://orcid.org/0000-0002-5077-881XKavli Institute for Theoretical Physics, University of California—Santa Barbara , Kohn Hall, Santa Barbara, CA 93107, United States of AmericaSpace Telescope Science Institute , 3700 San Martin Dr, Baltimore, MD 21218, United States of America; Department of Physics & Astronomy, Johns Hopkins University , 3400 N Charles St, Baltimore, MD 21218, United States of AmericaThe coarse-grained propagation of galactic cosmic rays (CRs) is traditionally constrained by phenomenological models of Milky Way CR propagation fit to a variety of direct and indirect observables; however, constraining the fine-grained transport of CRs along individual magnetic field lines—for instance, diffusive vs streaming transport models—is an unsolved challenge. Leveraging a recent training set of magnetohydrodynamic turbulent box simulations, with CRs spanning a range of transport parameters, we use convolutional neural networks (CNNs) trained solely on gas density maps to classify CR transport regimes. We find that even relatively simple CNNs can quite effectively classify density slices to corresponding CR transport parameters, distinguishing between streaming and diffusive transport, as well as magnitude of diffusivity, with class accuracies between 92% and 99%. As we show, the transport-dependent imprints that CRs leave on the gas are not all tied to the resulting density power spectra: classification accuracies are still high even when image spectra are flattened (85%–98% accuracy), highlighting CR transport-dependent changes to turbulent phase information. We interpret our results with saliency maps and image modifications, and we discuss physical insights and future applications.https://doi.org/10.1088/2632-2153/ad262aturbulenceconvolutional neural networkcosmic raysmagnetohydrodynamics |
| spellingShingle | Chad Bustard John Wu Deep learning cosmic ray transport from density maps of simulated, turbulent gas Machine Learning: Science and Technology turbulence convolutional neural network cosmic rays magnetohydrodynamics |
| title | Deep learning cosmic ray transport from density maps of simulated, turbulent gas |
| title_full | Deep learning cosmic ray transport from density maps of simulated, turbulent gas |
| title_fullStr | Deep learning cosmic ray transport from density maps of simulated, turbulent gas |
| title_full_unstemmed | Deep learning cosmic ray transport from density maps of simulated, turbulent gas |
| title_short | Deep learning cosmic ray transport from density maps of simulated, turbulent gas |
| title_sort | deep learning cosmic ray transport from density maps of simulated turbulent gas |
| topic | turbulence convolutional neural network cosmic rays magnetohydrodynamics |
| url | https://doi.org/10.1088/2632-2153/ad262a |
| work_keys_str_mv | AT chadbustard deeplearningcosmicraytransportfromdensitymapsofsimulatedturbulentgas AT johnwu deeplearningcosmicraytransportfromdensitymapsofsimulatedturbulentgas |