Efficient Monte Carlo simulation of streamer discharges with deep-learning denoising models
Electric breakdown in non-conducting gases is a complex process that in its first stages is characterized by filamentary discharges called streamers. Streamer dynamics are inherently nonlinear and span broad temporal and spatial scales, making numerical simulation challenging. Although Monte Carlo m...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2025-01-01
|
| Series: | Machine Learning: Science and Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2632-2153/adaca1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823858120827338752 |
|---|---|
| author | F M Bayo-Muñoz A Malagón-Romero A Luque |
| author_facet | F M Bayo-Muñoz A Malagón-Romero A Luque |
| author_sort | F M Bayo-Muñoz |
| collection | DOAJ |
| description | Electric breakdown in non-conducting gases is a complex process that in its first stages is characterized by filamentary discharges called streamers. Streamer dynamics are inherently nonlinear and span broad temporal and spatial scales, making numerical simulation challenging. Although Monte Carlo methods are intuitive and they model the full electron energy distribution without a priori prescriptions, they suffer from artificial sampling noise which, combined with the non-linearity of streamers, distorts their evolution. Here we investigate the use of deep-learning techniques to mitigate the noise introduced by Monte Carlo sampling. We observe that traditional techniques for noise reduction in images are not satisfactory because they do not impose strict conservation of electric charge. Then we present a charge-conserving denoising filter to improve the efficiency of Monte Carlo simulations of streamers. |
| format | Article |
| id | doaj-art-5f560f29846b489a96d4c8c48075203b |
| institution | Kabale University |
| issn | 2632-2153 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Machine Learning: Science and Technology |
| spelling | doaj-art-5f560f29846b489a96d4c8c48075203b2025-02-11T13:51:55ZengIOP PublishingMachine Learning: Science and Technology2632-21532025-01-016101503610.1088/2632-2153/adaca1Efficient Monte Carlo simulation of streamer discharges with deep-learning denoising modelsF M Bayo-Muñoz0https://orcid.org/0000-0001-8516-6322A Malagón-Romero1https://orcid.org/0000-0002-2891-9700A Luque2https://orcid.org/0000-0002-7922-8627Instituto de Astrofísica de Andalucía (IAA) , CSIC, Granada, SpainInstituto de Astrofísica de Andalucía (IAA) , CSIC, Granada, Spain; Centrum Wiskunde and Informatica (CWI) , Amsterdam, The NetherlandsInstituto de Astrofísica de Andalucía (IAA) , CSIC, Granada, SpainElectric breakdown in non-conducting gases is a complex process that in its first stages is characterized by filamentary discharges called streamers. Streamer dynamics are inherently nonlinear and span broad temporal and spatial scales, making numerical simulation challenging. Although Monte Carlo methods are intuitive and they model the full electron energy distribution without a priori prescriptions, they suffer from artificial sampling noise which, combined with the non-linearity of streamers, distorts their evolution. Here we investigate the use of deep-learning techniques to mitigate the noise introduced by Monte Carlo sampling. We observe that traditional techniques for noise reduction in images are not satisfactory because they do not impose strict conservation of electric charge. Then we present a charge-conserving denoising filter to improve the efficiency of Monte Carlo simulations of streamers.https://doi.org/10.1088/2632-2153/adaca1streamersmonte carloparticle-in-celldeep learningdenoising |
| spellingShingle | F M Bayo-Muñoz A Malagón-Romero A Luque Efficient Monte Carlo simulation of streamer discharges with deep-learning denoising models Machine Learning: Science and Technology streamers monte carlo particle-in-cell deep learning denoising |
| title | Efficient Monte Carlo simulation of streamer discharges with deep-learning denoising models |
| title_full | Efficient Monte Carlo simulation of streamer discharges with deep-learning denoising models |
| title_fullStr | Efficient Monte Carlo simulation of streamer discharges with deep-learning denoising models |
| title_full_unstemmed | Efficient Monte Carlo simulation of streamer discharges with deep-learning denoising models |
| title_short | Efficient Monte Carlo simulation of streamer discharges with deep-learning denoising models |
| title_sort | efficient monte carlo simulation of streamer discharges with deep learning denoising models |
| topic | streamers monte carlo particle-in-cell deep learning denoising |
| url | https://doi.org/10.1088/2632-2153/adaca1 |
| work_keys_str_mv | AT fmbayomunoz efficientmontecarlosimulationofstreamerdischargeswithdeeplearningdenoisingmodels AT amalagonromero efficientmontecarlosimulationofstreamerdischargeswithdeeplearningdenoisingmodels AT aluque efficientmontecarlosimulationofstreamerdischargeswithdeeplearningdenoisingmodels |