Towards ML-based diagnostics of focused laser pulse

Currently, machine learning (ML) methods are widely used to process the results of physical experiments. In some cases, due to the limited amount of experimental data, ML-models can be pre-trained on synthetic data simulated based on the analytical theory and then fine-tuned using experimental data....

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Rodimkov, Y. R, Volokitin, V. D, Meyerov, I. B, Efimenko, E. S
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Rodimkov, Y. R
Volokitin, V. D
Meyerov, I. B
Efimenko, E. S
description Currently, machine learning (ML) methods are widely used to process the results of physical experiments. In some cases, due to the limited amount of experimental data, ML-models can be pre-trained on synthetic data simulated based on the analytical theory and then fine-tuned using experimental data. A limitation of this approach is the presence of the latent parameters of the analytical model, which values are difficult or impossible to estimate. Setting these parameters incorrectly may induce a dataset shift even when applied to synthetic data. To overcome this problem, we train the ML-model on a dataset with randomly varied latent parameters of the analythical model to force the ML-model to concentrate on more general patterns that depend weakly on the latent parameters. We applied this approach to the problem of tight focusing of a laser pulse with the complex structure of the wavefront. We observed good accuracy of reconstructing of the tilt parameters when training and testing the ML-model on datasets generated for different values of the latent parameters. This confirms that the ML-model was able to select relevant information without over-fitting for specific features inherent in certain values of the latent parameters. We believe that this approach will enrich possible applications of ML-methods to an experimental diagnostics of laser pulses.
doi_str_mv 10.48550/arxiv.2209.09959
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2209_09959</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2209_09959</sourcerecordid><originalsourceid>FETCH-LOGICAL-a679-46f5b86271c37e047ef5eee242ba46a0df61b45561f8cbeb8423c747997f5b463</originalsourceid><addsrcrecordid>eNotjruOwjAURN1QIOADqNY_kODY13ZcIrQ8pKBt0kfXjr2KxBJkL6-_JzyqI81oRoeQecFyKKVkC4y37pJzzkzOjJFmTETdXzG2ie6rzGLyLW07_D326b9zifaBht6dn_FhKCM9nQ_JT8ko4MDZhxNSr7_r1Tarfja71bLKUGmTgQrSlorrwgntGWgfpPeeA7cIClkbVGFBSlWE0llvS-DCadDG6GEISkzI1_v2Zd2cYveH8d487ZuXvXgA8tY-vw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Towards ML-based diagnostics of focused laser pulse</title><source>arXiv.org</source><creator>Rodimkov, Y. R ; Volokitin, V. D ; Meyerov, I. B ; Efimenko, E. S</creator><creatorcontrib>Rodimkov, Y. R ; Volokitin, V. D ; Meyerov, I. B ; Efimenko, E. S</creatorcontrib><description>Currently, machine learning (ML) methods are widely used to process the results of physical experiments. In some cases, due to the limited amount of experimental data, ML-models can be pre-trained on synthetic data simulated based on the analytical theory and then fine-tuned using experimental data. A limitation of this approach is the presence of the latent parameters of the analytical model, which values are difficult or impossible to estimate. Setting these parameters incorrectly may induce a dataset shift even when applied to synthetic data. To overcome this problem, we train the ML-model on a dataset with randomly varied latent parameters of the analythical model to force the ML-model to concentrate on more general patterns that depend weakly on the latent parameters. We applied this approach to the problem of tight focusing of a laser pulse with the complex structure of the wavefront. We observed good accuracy of reconstructing of the tilt parameters when training and testing the ML-model on datasets generated for different values of the latent parameters. This confirms that the ML-model was able to select relevant information without over-fitting for specific features inherent in certain values of the latent parameters. We believe that this approach will enrich possible applications of ML-methods to an experimental diagnostics of laser pulses.</description><identifier>DOI: 10.48550/arxiv.2209.09959</identifier><language>eng</language><subject>Physics - Computational Physics</subject><creationdate>2022-09</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2209.09959$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2209.09959$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Rodimkov, Y. R</creatorcontrib><creatorcontrib>Volokitin, V. D</creatorcontrib><creatorcontrib>Meyerov, I. B</creatorcontrib><creatorcontrib>Efimenko, E. S</creatorcontrib><title>Towards ML-based diagnostics of focused laser pulse</title><description>Currently, machine learning (ML) methods are widely used to process the results of physical experiments. In some cases, due to the limited amount of experimental data, ML-models can be pre-trained on synthetic data simulated based on the analytical theory and then fine-tuned using experimental data. A limitation of this approach is the presence of the latent parameters of the analytical model, which values are difficult or impossible to estimate. Setting these parameters incorrectly may induce a dataset shift even when applied to synthetic data. To overcome this problem, we train the ML-model on a dataset with randomly varied latent parameters of the analythical model to force the ML-model to concentrate on more general patterns that depend weakly on the latent parameters. We applied this approach to the problem of tight focusing of a laser pulse with the complex structure of the wavefront. We observed good accuracy of reconstructing of the tilt parameters when training and testing the ML-model on datasets generated for different values of the latent parameters. This confirms that the ML-model was able to select relevant information without over-fitting for specific features inherent in certain values of the latent parameters. We believe that this approach will enrich possible applications of ML-methods to an experimental diagnostics of laser pulses.</description><subject>Physics - Computational Physics</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotjruOwjAURN1QIOADqNY_kODY13ZcIrQ8pKBt0kfXjr2KxBJkL6-_JzyqI81oRoeQecFyKKVkC4y37pJzzkzOjJFmTETdXzG2ie6rzGLyLW07_D326b9zifaBht6dn_FhKCM9nQ_JT8ko4MDZhxNSr7_r1Tarfja71bLKUGmTgQrSlorrwgntGWgfpPeeA7cIClkbVGFBSlWE0llvS-DCadDG6GEISkzI1_v2Zd2cYveH8d487ZuXvXgA8tY-vw</recordid><startdate>20220920</startdate><enddate>20220920</enddate><creator>Rodimkov, Y. R</creator><creator>Volokitin, V. D</creator><creator>Meyerov, I. B</creator><creator>Efimenko, E. S</creator><scope>GOX</scope></search><sort><creationdate>20220920</creationdate><title>Towards ML-based diagnostics of focused laser pulse</title><author>Rodimkov, Y. R ; Volokitin, V. D ; Meyerov, I. B ; Efimenko, E. S</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a679-46f5b86271c37e047ef5eee242ba46a0df61b45561f8cbeb8423c747997f5b463</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Physics - Computational Physics</topic><toplevel>online_resources</toplevel><creatorcontrib>Rodimkov, Y. R</creatorcontrib><creatorcontrib>Volokitin, V. D</creatorcontrib><creatorcontrib>Meyerov, I. B</creatorcontrib><creatorcontrib>Efimenko, E. S</creatorcontrib><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Rodimkov, Y. R</au><au>Volokitin, V. D</au><au>Meyerov, I. B</au><au>Efimenko, E. S</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Towards ML-based diagnostics of focused laser pulse</atitle><date>2022-09-20</date><risdate>2022</risdate><abstract>Currently, machine learning (ML) methods are widely used to process the results of physical experiments. In some cases, due to the limited amount of experimental data, ML-models can be pre-trained on synthetic data simulated based on the analytical theory and then fine-tuned using experimental data. A limitation of this approach is the presence of the latent parameters of the analytical model, which values are difficult or impossible to estimate. Setting these parameters incorrectly may induce a dataset shift even when applied to synthetic data. To overcome this problem, we train the ML-model on a dataset with randomly varied latent parameters of the analythical model to force the ML-model to concentrate on more general patterns that depend weakly on the latent parameters. We applied this approach to the problem of tight focusing of a laser pulse with the complex structure of the wavefront. We observed good accuracy of reconstructing of the tilt parameters when training and testing the ML-model on datasets generated for different values of the latent parameters. This confirms that the ML-model was able to select relevant information without over-fitting for specific features inherent in certain values of the latent parameters. We believe that this approach will enrich possible applications of ML-methods to an experimental diagnostics of laser pulses.</abstract><doi>10.48550/arxiv.2209.09959</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2209.09959
ispartof
issn
language eng
recordid cdi_arxiv_primary_2209_09959
source arXiv.org
subjects Physics - Computational Physics
title Towards ML-based diagnostics of focused laser pulse
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-03T02%3A14%3A30IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Towards%20ML-based%20diagnostics%20of%20focused%20laser%20pulse&rft.au=Rodimkov,%20Y.%20R&rft.date=2022-09-20&rft_id=info:doi/10.48550/arxiv.2209.09959&rft_dat=%3Carxiv_GOX%3E2209_09959%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true