Augmented signal processing in Liquid Argon Time Projection Chambers with a deep neural network
The Liquid Argon Time Projection Chamber (LArTPC) is an advanced neutrino detector technology widely used in recent and upcoming accelerator neutrino experiments. It features a low energy threshold and high spatial resolution that allow for comprehensive reconstruction of event topologies. In curren...
Gespeichert in:
| Veröffentlicht in: | Journal of instrumentation 2021-01, Vol.16 (1), p.P01036-P01036 |
|---|---|
| Hauptverfasser: | , , , , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | P01036 |
|---|---|
| container_issue | 1 |
| container_start_page | P01036 |
| container_title | Journal of instrumentation |
| container_volume | 16 |
| creator | Yu, H.W. Bishai, M. Gu, W.Q. Lin, M.F. Qian, X. Ren, Y.H. Scarpelli, A. Viren, B. Wei, H.Y. Yu, H.Z. Yu, K. Zhang, C. |
| description | The Liquid Argon Time Projection Chamber (LArTPC) is an advanced neutrino detector technology widely used in recent and upcoming accelerator neutrino experiments. It features a low energy threshold and high spatial resolution that allow for comprehensive reconstruction of event topologies. In current-generation LArTPCs, the recorded data consist of digitized waveforms on wires produced by induced signal on wires of drifting ionization electrons, which can also be viewed as two-dimensional (2D) (time versus wire) projection images of charged-particle trajectories. For such an imaging detector, one critical step is the signal processing that reconstructs the original charge projections from the recorded 2D images. For the first time, we introduce a deep neural network in LArTPC signal processing to improve the signal region of interest detection. By combining domain knowledge (e.g., matching information from multiple wire planes) and deep learning, this method shows significant improvements over traditional methods. This work details the method, software tools, and performance evaluated with realistic detector simulations. |
| doi_str_mv | 10.1088/1748-0221/16/01/P01036 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_osti_</sourceid><recordid>TN_cdi_osti_scitechconnect_1732142</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2485096647</sourcerecordid><originalsourceid>FETCH-LOGICAL-c358t-346996e97fa5b9c79580920bf706229716fe0e27e9395bb9d5ff6307b79337853</originalsourceid><addsrcrecordid>eNpNkE1rwzAMhsPYYF23vzDMds4i27EdH0vZFxTWQ3c2-VBSd43T2gll_34pGWMnSehB6H2i6J7CE4UsS6hKsxgYowmVCdBkDRS4vIhmf4vLf_11dBPCDkBokcIsMouhadH1WJFgG5fvycF3JYZgXUOsIyt7HGxFFr7pHNnYFsnadzssezvOy23eFugDOdl-S3JSIR6Iw8GPZxz2p85_3UZXdb4PePdb59Hny_Nm-RavPl7fl4tVXHKR9TFPpdYStapzUehSaZGBZlDUCiRjWlFZIyBTqLkWRaErUdeSgyqU5lxlgs-jh-luF3prQml7LLdl59z4qqGKM5qyEXqcoDHjccDQm103-DF0MCzNBGgpUzVScqJK34XgsTYHb9vcfxsK5mzcnGWas0xDpQFqJuP8B3h_cns</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2485096647</pqid></control><display><type>article</type><title>Augmented signal processing in Liquid Argon Time Projection Chambers with a deep neural network</title><source>IOP Publishing Journals</source><source>Institute of Physics (IOP) Journals - HEAL-Link</source><creator>Yu, H.W. ; Bishai, M. ; Gu, W.Q. ; Lin, M.F. ; Qian, X. ; Ren, Y.H. ; Scarpelli, A. ; Viren, B. ; Wei, H.Y. ; Yu, H.Z. ; Yu, K. ; Zhang, C.</creator><creatorcontrib>Yu, H.W. ; Bishai, M. ; Gu, W.Q. ; Lin, M.F. ; Qian, X. ; Ren, Y.H. ; Scarpelli, A. ; Viren, B. ; Wei, H.Y. ; Yu, H.Z. ; Yu, K. ; Zhang, C. ; Brookhaven National Laboratory (BNL), Upton, NY (United States)</creatorcontrib><description>The Liquid Argon Time Projection Chamber (LArTPC) is an advanced neutrino detector technology widely used in recent and upcoming accelerator neutrino experiments. It features a low energy threshold and high spatial resolution that allow for comprehensive reconstruction of event topologies. In current-generation LArTPCs, the recorded data consist of digitized waveforms on wires produced by induced signal on wires of drifting ionization electrons, which can also be viewed as two-dimensional (2D) (time versus wire) projection images of charged-particle trajectories. For such an imaging detector, one critical step is the signal processing that reconstructs the original charge projections from the recorded 2D images. For the first time, we introduce a deep neural network in LArTPC signal processing to improve the signal region of interest detection. By combining domain knowledge (e.g., matching information from multiple wire planes) and deep learning, this method shows significant improvements over traditional methods. This work details the method, software tools, and performance evaluated with realistic detector simulations.</description><identifier>ISSN: 1748-0221</identifier><identifier>EISSN: 1748-0221</identifier><identifier>DOI: 10.1088/1748-0221/16/01/P01036</identifier><language>eng</language><publisher>Bristol: IOP Publishing</publisher><subject>Argon ; Artificial neural networks ; Deep Neural Network ; Image reconstruction ; LArTPC ; Machine learning ; Neural networks ; Neutrinos ; Particle trajectories ; PHYSICS OF ELEMENTARY PARTICLES AND FIELDS ; Projection ; Radiation counters ; Sensors ; Signal Processing ; Software ; Software development tools ; Spatial resolution ; Topology ; Waveforms ; Wire ; Wire-Cell</subject><ispartof>Journal of instrumentation, 2021-01, Vol.16 (1), p.P01036-P01036</ispartof><rights>Copyright IOP Publishing Jan 2021</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c358t-346996e97fa5b9c79580920bf706229716fe0e27e9395bb9d5ff6307b79337853</citedby><orcidid>0000000229734580</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>230,314,778,782,883,27907,27908</link.rule.ids><backlink>$$Uhttps://www.osti.gov/servlets/purl/1732142$$D View this record in Osti.gov$$Hfree_for_read</backlink></links><search><creatorcontrib>Yu, H.W.</creatorcontrib><creatorcontrib>Bishai, M.</creatorcontrib><creatorcontrib>Gu, W.Q.</creatorcontrib><creatorcontrib>Lin, M.F.</creatorcontrib><creatorcontrib>Qian, X.</creatorcontrib><creatorcontrib>Ren, Y.H.</creatorcontrib><creatorcontrib>Scarpelli, A.</creatorcontrib><creatorcontrib>Viren, B.</creatorcontrib><creatorcontrib>Wei, H.Y.</creatorcontrib><creatorcontrib>Yu, H.Z.</creatorcontrib><creatorcontrib>Yu, K.</creatorcontrib><creatorcontrib>Zhang, C.</creatorcontrib><creatorcontrib>Brookhaven National Laboratory (BNL), Upton, NY (United States)</creatorcontrib><title>Augmented signal processing in Liquid Argon Time Projection Chambers with a deep neural network</title><title>Journal of instrumentation</title><description>The Liquid Argon Time Projection Chamber (LArTPC) is an advanced neutrino detector technology widely used in recent and upcoming accelerator neutrino experiments. It features a low energy threshold and high spatial resolution that allow for comprehensive reconstruction of event topologies. In current-generation LArTPCs, the recorded data consist of digitized waveforms on wires produced by induced signal on wires of drifting ionization electrons, which can also be viewed as two-dimensional (2D) (time versus wire) projection images of charged-particle trajectories. For such an imaging detector, one critical step is the signal processing that reconstructs the original charge projections from the recorded 2D images. For the first time, we introduce a deep neural network in LArTPC signal processing to improve the signal region of interest detection. By combining domain knowledge (e.g., matching information from multiple wire planes) and deep learning, this method shows significant improvements over traditional methods. This work details the method, software tools, and performance evaluated with realistic detector simulations.</description><subject>Argon</subject><subject>Artificial neural networks</subject><subject>Deep Neural Network</subject><subject>Image reconstruction</subject><subject>LArTPC</subject><subject>Machine learning</subject><subject>Neural networks</subject><subject>Neutrinos</subject><subject>Particle trajectories</subject><subject>PHYSICS OF ELEMENTARY PARTICLES AND FIELDS</subject><subject>Projection</subject><subject>Radiation counters</subject><subject>Sensors</subject><subject>Signal Processing</subject><subject>Software</subject><subject>Software development tools</subject><subject>Spatial resolution</subject><subject>Topology</subject><subject>Waveforms</subject><subject>Wire</subject><subject>Wire-Cell</subject><issn>1748-0221</issn><issn>1748-0221</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNpNkE1rwzAMhsPYYF23vzDMds4i27EdH0vZFxTWQ3c2-VBSd43T2gll_34pGWMnSehB6H2i6J7CE4UsS6hKsxgYowmVCdBkDRS4vIhmf4vLf_11dBPCDkBokcIsMouhadH1WJFgG5fvycF3JYZgXUOsIyt7HGxFFr7pHNnYFsnadzssezvOy23eFugDOdl-S3JSIR6Iw8GPZxz2p85_3UZXdb4PePdb59Hny_Nm-RavPl7fl4tVXHKR9TFPpdYStapzUehSaZGBZlDUCiRjWlFZIyBTqLkWRaErUdeSgyqU5lxlgs-jh-luF3prQml7LLdl59z4qqGKM5qyEXqcoDHjccDQm103-DF0MCzNBGgpUzVScqJK34XgsTYHb9vcfxsK5mzcnGWas0xDpQFqJuP8B3h_cns</recordid><startdate>20210129</startdate><enddate>20210129</enddate><creator>Yu, H.W.</creator><creator>Bishai, M.</creator><creator>Gu, W.Q.</creator><creator>Lin, M.F.</creator><creator>Qian, X.</creator><creator>Ren, Y.H.</creator><creator>Scarpelli, A.</creator><creator>Viren, B.</creator><creator>Wei, H.Y.</creator><creator>Yu, H.Z.</creator><creator>Yu, K.</creator><creator>Zhang, C.</creator><general>IOP Publishing</general><general>Institute of Physics (IOP)</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7U5</scope><scope>8FD</scope><scope>L7M</scope><scope>OIOZB</scope><scope>OTOTI</scope><orcidid>https://orcid.org/0000000229734580</orcidid></search><sort><creationdate>20210129</creationdate><title>Augmented signal processing in Liquid Argon Time Projection Chambers with a deep neural network</title><author>Yu, H.W. ; Bishai, M. ; Gu, W.Q. ; Lin, M.F. ; Qian, X. ; Ren, Y.H. ; Scarpelli, A. ; Viren, B. ; Wei, H.Y. ; Yu, H.Z. ; Yu, K. ; Zhang, C.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c358t-346996e97fa5b9c79580920bf706229716fe0e27e9395bb9d5ff6307b79337853</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Argon</topic><topic>Artificial neural networks</topic><topic>Deep Neural Network</topic><topic>Image reconstruction</topic><topic>LArTPC</topic><topic>Machine learning</topic><topic>Neural networks</topic><topic>Neutrinos</topic><topic>Particle trajectories</topic><topic>PHYSICS OF ELEMENTARY PARTICLES AND FIELDS</topic><topic>Projection</topic><topic>Radiation counters</topic><topic>Sensors</topic><topic>Signal Processing</topic><topic>Software</topic><topic>Software development tools</topic><topic>Spatial resolution</topic><topic>Topology</topic><topic>Waveforms</topic><topic>Wire</topic><topic>Wire-Cell</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yu, H.W.</creatorcontrib><creatorcontrib>Bishai, M.</creatorcontrib><creatorcontrib>Gu, W.Q.</creatorcontrib><creatorcontrib>Lin, M.F.</creatorcontrib><creatorcontrib>Qian, X.</creatorcontrib><creatorcontrib>Ren, Y.H.</creatorcontrib><creatorcontrib>Scarpelli, A.</creatorcontrib><creatorcontrib>Viren, B.</creatorcontrib><creatorcontrib>Wei, H.Y.</creatorcontrib><creatorcontrib>Yu, H.Z.</creatorcontrib><creatorcontrib>Yu, K.</creatorcontrib><creatorcontrib>Zhang, C.</creatorcontrib><creatorcontrib>Brookhaven National Laboratory (BNL), Upton, NY (United States)</creatorcontrib><collection>CrossRef</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>Technology Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>OSTI.GOV - Hybrid</collection><collection>OSTI.GOV</collection><jtitle>Journal of instrumentation</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yu, H.W.</au><au>Bishai, M.</au><au>Gu, W.Q.</au><au>Lin, M.F.</au><au>Qian, X.</au><au>Ren, Y.H.</au><au>Scarpelli, A.</au><au>Viren, B.</au><au>Wei, H.Y.</au><au>Yu, H.Z.</au><au>Yu, K.</au><au>Zhang, C.</au><aucorp>Brookhaven National Laboratory (BNL), Upton, NY (United States)</aucorp><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Augmented signal processing in Liquid Argon Time Projection Chambers with a deep neural network</atitle><jtitle>Journal of instrumentation</jtitle><date>2021-01-29</date><risdate>2021</risdate><volume>16</volume><issue>1</issue><spage>P01036</spage><epage>P01036</epage><pages>P01036-P01036</pages><issn>1748-0221</issn><eissn>1748-0221</eissn><abstract>The Liquid Argon Time Projection Chamber (LArTPC) is an advanced neutrino detector technology widely used in recent and upcoming accelerator neutrino experiments. It features a low energy threshold and high spatial resolution that allow for comprehensive reconstruction of event topologies. In current-generation LArTPCs, the recorded data consist of digitized waveforms on wires produced by induced signal on wires of drifting ionization electrons, which can also be viewed as two-dimensional (2D) (time versus wire) projection images of charged-particle trajectories. For such an imaging detector, one critical step is the signal processing that reconstructs the original charge projections from the recorded 2D images. For the first time, we introduce a deep neural network in LArTPC signal processing to improve the signal region of interest detection. By combining domain knowledge (e.g., matching information from multiple wire planes) and deep learning, this method shows significant improvements over traditional methods. This work details the method, software tools, and performance evaluated with realistic detector simulations.</abstract><cop>Bristol</cop><pub>IOP Publishing</pub><doi>10.1088/1748-0221/16/01/P01036</doi><orcidid>https://orcid.org/0000000229734580</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1748-0221 |
| ispartof | Journal of instrumentation, 2021-01, Vol.16 (1), p.P01036-P01036 |
| issn | 1748-0221 1748-0221 |
| language | eng |
| recordid | cdi_osti_scitechconnect_1732142 |
| source | IOP Publishing Journals; Institute of Physics (IOP) Journals - HEAL-Link |
| subjects | Argon Artificial neural networks Deep Neural Network Image reconstruction LArTPC Machine learning Neural networks Neutrinos Particle trajectories PHYSICS OF ELEMENTARY PARTICLES AND FIELDS Projection Radiation counters Sensors Signal Processing Software Software development tools Spatial resolution Topology Waveforms Wire Wire-Cell |
| title | Augmented signal processing in Liquid Argon Time Projection Chambers with a deep neural network |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-17T01%3A05%3A52IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_osti_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Augmented%20signal%20processing%20in%20Liquid%20Argon%20Time%20Projection%20Chambers%20with%20a%20deep%20neural%20network&rft.jtitle=Journal%20of%20instrumentation&rft.au=Yu,%20H.W.&rft.aucorp=Brookhaven%20National%20Laboratory%20(BNL),%20Upton,%20NY%20(United%20States)&rft.date=2021-01-29&rft.volume=16&rft.issue=1&rft.spage=P01036&rft.epage=P01036&rft.pages=P01036-P01036&rft.issn=1748-0221&rft.eissn=1748-0221&rft_id=info:doi/10.1088/1748-0221/16/01/P01036&rft_dat=%3Cproquest_osti_%3E2485096647%3C/proquest_osti_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2485096647&rft_id=info:pmid/&rfr_iscdi=true |