TORAX: A Fast and Differentiable Tokamak Transport Simulator in JAX
We present TORAX, a new, open-source, differentiable tokamak core transport simulator implemented in Python using the JAX framework. TORAX solves the coupled equations for ion heat transport, electron heat transport, particle transport, and current diffusion, incorporating modular physics-based and...
Gespeichert in:
| Veröffentlicht in: | arXiv.org 2024-12 |
|---|---|
| Hauptverfasser: | , , , , , , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | arXiv.org |
| container_volume | |
| creator | Citrin, Jonathan Goodfellow, Ian Raju, Akhil Chen, Jeremy Degrave, Jonas Donner, Craig Felici, Federico Hamel, Philippe Huber, Andrea Nikulin, Dmitry Pfau, David Tracey, Brendan Riedmiller, Martin Kohli, Pushmeet |
| description | We present TORAX, a new, open-source, differentiable tokamak core transport simulator implemented in Python using the JAX framework. TORAX solves the coupled equations for ion heat transport, electron heat transport, particle transport, and current diffusion, incorporating modular physics-based and ML models. JAX's just-in-time compilation ensures fast runtimes, while its automatic differentiation capability enables gradient-based optimization workflows and simplifies the use of Jacobian-based PDE solvers. Coupling to ML-surrogates of physics models is greatly facilitated by JAX's intrinsic support for neural network development and inference. TORAX is verified against the established RAPTOR code, demonstrating agreement in simulated plasma profiles. TORAX provides a powerful and versatile tool for accelerating research in tokamak scenario modeling, pulse design, and control. |
| format | Article |
| fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3067539238</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3067539238</sourcerecordid><originalsourceid>FETCH-proquest_journals_30675392383</originalsourceid><addsrcrecordid>eNqNyr0KwjAUQOEgCBbtO1xwLsTEtNWtVIu4CJqhW7liCulPUpP0_XXwAZzO8J0FiRjnuyTfM7YisfcdpZSlGROCR6SUt3tRH6GACn0ANC846bZVTpmg8TkokLbHEXuQDo2frAvw0OM8YLAOtIFrUW_IssXBq_jXNdlWZ1leksnZ96x8aDo7O_OlhtM0E_zAeM7_uz4lRjix</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3067539238</pqid></control><display><type>article</type><title>TORAX: A Fast and Differentiable Tokamak Transport Simulator in JAX</title><source>Free E- Journals</source><creator>Citrin, Jonathan ; Goodfellow, Ian ; Raju, Akhil ; Chen, Jeremy ; Degrave, Jonas ; Donner, Craig ; Felici, Federico ; Hamel, Philippe ; Huber, Andrea ; Nikulin, Dmitry ; Pfau, David ; Tracey, Brendan ; Riedmiller, Martin ; Kohli, Pushmeet</creator><creatorcontrib>Citrin, Jonathan ; Goodfellow, Ian ; Raju, Akhil ; Chen, Jeremy ; Degrave, Jonas ; Donner, Craig ; Felici, Federico ; Hamel, Philippe ; Huber, Andrea ; Nikulin, Dmitry ; Pfau, David ; Tracey, Brendan ; Riedmiller, Martin ; Kohli, Pushmeet</creatorcontrib><description>We present TORAX, a new, open-source, differentiable tokamak core transport simulator implemented in Python using the JAX framework. TORAX solves the coupled equations for ion heat transport, electron heat transport, particle transport, and current diffusion, incorporating modular physics-based and ML models. JAX's just-in-time compilation ensures fast runtimes, while its automatic differentiation capability enables gradient-based optimization workflows and simplifies the use of Jacobian-based PDE solvers. Coupling to ML-surrogates of physics models is greatly facilitated by JAX's intrinsic support for neural network development and inference. TORAX is verified against the established RAPTOR code, demonstrating agreement in simulated plasma profiles. TORAX provides a powerful and versatile tool for accelerating research in tokamak scenario modeling, pulse design, and control.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Diffusion rate ; Neural networks ; Tokamak devices</subject><ispartof>arXiv.org, 2024-12</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</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>780,784</link.rule.ids></links><search><creatorcontrib>Citrin, Jonathan</creatorcontrib><creatorcontrib>Goodfellow, Ian</creatorcontrib><creatorcontrib>Raju, Akhil</creatorcontrib><creatorcontrib>Chen, Jeremy</creatorcontrib><creatorcontrib>Degrave, Jonas</creatorcontrib><creatorcontrib>Donner, Craig</creatorcontrib><creatorcontrib>Felici, Federico</creatorcontrib><creatorcontrib>Hamel, Philippe</creatorcontrib><creatorcontrib>Huber, Andrea</creatorcontrib><creatorcontrib>Nikulin, Dmitry</creatorcontrib><creatorcontrib>Pfau, David</creatorcontrib><creatorcontrib>Tracey, Brendan</creatorcontrib><creatorcontrib>Riedmiller, Martin</creatorcontrib><creatorcontrib>Kohli, Pushmeet</creatorcontrib><title>TORAX: A Fast and Differentiable Tokamak Transport Simulator in JAX</title><title>arXiv.org</title><description>We present TORAX, a new, open-source, differentiable tokamak core transport simulator implemented in Python using the JAX framework. TORAX solves the coupled equations for ion heat transport, electron heat transport, particle transport, and current diffusion, incorporating modular physics-based and ML models. JAX's just-in-time compilation ensures fast runtimes, while its automatic differentiation capability enables gradient-based optimization workflows and simplifies the use of Jacobian-based PDE solvers. Coupling to ML-surrogates of physics models is greatly facilitated by JAX's intrinsic support for neural network development and inference. TORAX is verified against the established RAPTOR code, demonstrating agreement in simulated plasma profiles. TORAX provides a powerful and versatile tool for accelerating research in tokamak scenario modeling, pulse design, and control.</description><subject>Diffusion rate</subject><subject>Neural networks</subject><subject>Tokamak devices</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNyr0KwjAUQOEgCBbtO1xwLsTEtNWtVIu4CJqhW7liCulPUpP0_XXwAZzO8J0FiRjnuyTfM7YisfcdpZSlGROCR6SUt3tRH6GACn0ANC846bZVTpmg8TkokLbHEXuQDo2frAvw0OM8YLAOtIFrUW_IssXBq_jXNdlWZ1leksnZ96x8aDo7O_OlhtM0E_zAeM7_uz4lRjix</recordid><startdate>20241207</startdate><enddate>20241207</enddate><creator>Citrin, Jonathan</creator><creator>Goodfellow, Ian</creator><creator>Raju, Akhil</creator><creator>Chen, Jeremy</creator><creator>Degrave, Jonas</creator><creator>Donner, Craig</creator><creator>Felici, Federico</creator><creator>Hamel, Philippe</creator><creator>Huber, Andrea</creator><creator>Nikulin, Dmitry</creator><creator>Pfau, David</creator><creator>Tracey, Brendan</creator><creator>Riedmiller, Martin</creator><creator>Kohli, Pushmeet</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20241207</creationdate><title>TORAX: A Fast and Differentiable Tokamak Transport Simulator in JAX</title><author>Citrin, Jonathan ; Goodfellow, Ian ; Raju, Akhil ; Chen, Jeremy ; Degrave, Jonas ; Donner, Craig ; Felici, Federico ; Hamel, Philippe ; Huber, Andrea ; Nikulin, Dmitry ; Pfau, David ; Tracey, Brendan ; Riedmiller, Martin ; Kohli, Pushmeet</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_30675392383</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Diffusion rate</topic><topic>Neural networks</topic><topic>Tokamak devices</topic><toplevel>online_resources</toplevel><creatorcontrib>Citrin, Jonathan</creatorcontrib><creatorcontrib>Goodfellow, Ian</creatorcontrib><creatorcontrib>Raju, Akhil</creatorcontrib><creatorcontrib>Chen, Jeremy</creatorcontrib><creatorcontrib>Degrave, Jonas</creatorcontrib><creatorcontrib>Donner, Craig</creatorcontrib><creatorcontrib>Felici, Federico</creatorcontrib><creatorcontrib>Hamel, Philippe</creatorcontrib><creatorcontrib>Huber, Andrea</creatorcontrib><creatorcontrib>Nikulin, Dmitry</creatorcontrib><creatorcontrib>Pfau, David</creatorcontrib><creatorcontrib>Tracey, Brendan</creatorcontrib><creatorcontrib>Riedmiller, Martin</creatorcontrib><creatorcontrib>Kohli, Pushmeet</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Citrin, Jonathan</au><au>Goodfellow, Ian</au><au>Raju, Akhil</au><au>Chen, Jeremy</au><au>Degrave, Jonas</au><au>Donner, Craig</au><au>Felici, Federico</au><au>Hamel, Philippe</au><au>Huber, Andrea</au><au>Nikulin, Dmitry</au><au>Pfau, David</au><au>Tracey, Brendan</au><au>Riedmiller, Martin</au><au>Kohli, Pushmeet</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>TORAX: A Fast and Differentiable Tokamak Transport Simulator in JAX</atitle><jtitle>arXiv.org</jtitle><date>2024-12-07</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>We present TORAX, a new, open-source, differentiable tokamak core transport simulator implemented in Python using the JAX framework. TORAX solves the coupled equations for ion heat transport, electron heat transport, particle transport, and current diffusion, incorporating modular physics-based and ML models. JAX's just-in-time compilation ensures fast runtimes, while its automatic differentiation capability enables gradient-based optimization workflows and simplifies the use of Jacobian-based PDE solvers. Coupling to ML-surrogates of physics models is greatly facilitated by JAX's intrinsic support for neural network development and inference. TORAX is verified against the established RAPTOR code, demonstrating agreement in simulated plasma profiles. TORAX provides a powerful and versatile tool for accelerating research in tokamak scenario modeling, pulse design, and control.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | EISSN: 2331-8422 |
| ispartof | arXiv.org, 2024-12 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_proquest_journals_3067539238 |
| source | Free E- Journals |
| subjects | Diffusion rate Neural networks Tokamak devices |
| title | TORAX: A Fast and Differentiable Tokamak Transport Simulator in JAX |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-30T14%3A42%3A50IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=TORAX:%20A%20Fast%20and%20Differentiable%20Tokamak%20Transport%20Simulator%20in%20JAX&rft.jtitle=arXiv.org&rft.au=Citrin,%20Jonathan&rft.date=2024-12-07&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3067539238%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3067539238&rft_id=info:pmid/&rfr_iscdi=true |