{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T20:13:19Z","timestamp":1772223199713,"version":"3.50.1"},"reference-count":26,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T00:00:00Z","timestamp":1707782400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/3.0"},{"start":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T00:00:00Z","timestamp":1707782400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"crossref","award":["FA-9550-22-1-0400"],"award-info":[{"award-number":["FA-9550-22-1-0400"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Department of Energy National Nuclear Security Administration","award":["DE-NA0003856"],"award-info":[{"award-number":["DE-NA0003856"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2024,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Parameter estimation using observables is a fundamental concept in the experimental sciences. Mathematical models that represent the physical processes can enable reconstructions of the experimental observables and greatly assist in parameter estimation by turning it into an optimization problem which can be solved by gradient-free or gradient-based methods. In this work, the recent rise in flexible frameworks for developing differentiable scientific computing programs is leveraged in order to dramatically accelerate data analysis of a common experimental diagnostic relevant to laser\u2013plasma and inertial fusion experiments, Thomson scattering. A differentiable Thomson-scattering data analysis tool is developed that uses reverse-mode automatic differentiation (AD) to calculate gradients. By switching from finite differencing to reverse-mode AD, three distinct outcomes are achieved. First, gradient descent is accelerated dramatically to the extent that it enables near real-time usage in laser\u2013plasma experiments. Second, qualitatively novel quantities which require <jats:inline-formula>\n                     <jats:tex-math\/>\n                     <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\">\n                        <mml:mrow>\n                           <mml:mi class=\"MJX-tex-calligraphic\">O<\/mml:mi>\n                        <\/mml:mrow>\n                        <mml:mo stretchy=\"false\">(<\/mml:mo>\n                        <mml:msup>\n                           <mml:mn>10<\/mml:mn>\n                           <mml:mn>3<\/mml:mn>\n                        <\/mml:msup>\n                        <mml:mo stretchy=\"false\">)<\/mml:mo>\n                     <\/mml:math>\n                     <jats:inline-graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"mlstad2493ieqn1.gif\" xlink:type=\"simple\"\/>\n                  <\/jats:inline-formula> parameters can now be included in the analysis of data which enables unprecedented measurements of small-scale laser\u2013plasma phenomena. Third, uncertainty estimation approaches that leverage the value of the Hessian become accurate and efficient because reverse-mode AD can be used for calculating the Hessian.<\/jats:p>","DOI":"10.1088\/2632-2153\/ad2493","type":"journal-article","created":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T07:51:56Z","timestamp":1707810716000},"page":"015026","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Qualitative and quantitative enhancement of parameter estimation for model-based diagnostics using automatic differentiation with an application to inertial fusion"],"prefix":"10.1088","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9988-6109","authenticated-orcid":true,"given":"A L","family":"Milder","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3599-5629","authenticated-orcid":true,"given":"A S","family":"Joglekar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"W","family":"Rozmus","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"D H","family":"Froula","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2024,2,13]]},"reference":[{"key":"mlstad2493bib1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.95.023306","article-title":"Quantitative shadowgraphy and proton radiography for large intensity modulations","volume":"95","author":"Kasim","year":"2017","journal-title":"Phys. Rev. E"},{"key":"mlstad2493bib2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.95.043305","article-title":"Machine learning applied to proton radiography of high-energy-density plasmas","volume":"95","author":"Chen","year":"2017","journal-title":"Phys. Rev. E"},{"key":"mlstad2493bib3","doi-asserted-by":"publisher","DOI":"10.1063\/1.5134786","article-title":"Axial proton probing of magnetic and electric fields inside laser-driven coils","volume":"27","author":"Peebles","year":"2020","journal-title":"Phys. Plasmas"},{"key":"mlstad2493bib4","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1038\/s41467-020-20387-7","article-title":"Observations of pressure anisotropy effects within semi-collisional magnetized plasma bubbles","volume":"12","author":"Tubman","year":"2021","journal-title":"Nat. Commun."},{"key":"mlstad2493bib5","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.106.225005","article-title":"Measurement of the ionization state and electron temperature of plasma during the ablation stage of a wire-array Z pinch using absorption spectroscopy","volume":"106","author":"Ivanov","year":"2011","journal-title":"Phys. Rev. Lett."},{"key":"mlstad2493bib6","author":"Froula","year":"2011","edition":"2nd edn"},{"key":"mlstad2493bib7","author":"Nocedal","year":"2006","edition":"2nd edn"},{"key":"mlstad2493bib8","doi-asserted-by":"publisher","DOI":"10.1063\/5.0083195","article-title":"Quantitative assessment of fitting errors associated with streak camera noise in Thomson scattering data analysis","volume":"93","author":"Swadling","year":"2022","journal-title":"Rev. Sci. Instrum."},{"key":"mlstad2493bib9","article-title":"Automatic differentiation in machine learning: a survey","author":"Baydin","year":"2018"},{"key":"mlstad2493bib10","article-title":"Automatic differentiation in PyTorch","author":"Paszke","year":"2017"},{"key":"mlstad2493bib11","article-title":"TensorFlow: large-scale machine learning on heterogeneous systems","author":"Abadi","year":"2015"},{"key":"mlstad2493bib12","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1002\/pamm.200310012","article-title":"Introduction to automatic differentiation","volume":"2","author":"Griewank","year":"2003","journal-title":"PAMM"},{"key":"mlstad2493bib13","doi-asserted-by":"publisher","first-page":"552","DOI":"10.1038\/s43017-023-00450-9","article-title":"Differentiable modelling to unify machine learning and physical models for geosciences","volume":"4","author":"Shen","year":"2023","journal-title":"Nat. Rev. Earth Environ."},{"key":"mlstad2493bib14","doi-asserted-by":"publisher","first-page":"15344","DOI":"10.1073\/pnas.1814058116","article-title":"Learning data-driven discretizations for partial differential equations","volume":"116","author":"Bar-Sinai","year":"2019","journal-title":"Proc. Natl Acad. Sci."},{"key":"mlstad2493bib15","article-title":"Learning to control PDEs with differentiable physics","author":"Holl","year":"2020"},{"key":"mlstad2493bib16","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2022.108527","article-title":"JAX-fluids: a fully-differentiable high-order computational fluid dynamics solver for compressible two-phase flows","volume":"282","author":"Bezgin","year":"2023","journal-title":"Comput. Phys. Commun."},{"key":"mlstad2493bib17","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/acb19c","article-title":"Differentiable physics-enabled closure modeling for Burgers\u2019 turbulence","volume":"4","author":"Shankar","year":"2023","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstad2493bib18","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.128.204801","article-title":"Differentiable Preisach modeling for characterization and optimization of particle accelerator systems with hysteresis","volume":"128","author":"Roussel","year":"2022","journal-title":"Phys. Rev. Lett."},{"key":"mlstad2493bib19","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.130.145001","article-title":"Phase space reconstruction from accelerator beam measurements using neural networks and differentiable simulations","volume":"130","author":"Roussel","year":"2023","journal-title":"Phys. Rev. Lett."},{"key":"mlstad2493bib20","doi-asserted-by":"publisher","DOI":"10.1017\/S0022377822000939","article-title":"Unsupervised discovery of nonlinear plasma physics using differentiable kinetic simulations","volume":"88","author":"Joglekar","year":"2022","journal-title":"J. Plasma Phys."},{"key":"mlstad2493bib21","doi-asserted-by":"crossref","DOI":"10.1088\/2632-2153\/acf81a","article-title":"Machine learning of hidden variables in multiscale fluid simulation","author":"Joglekar","year":"2023"},{"key":"mlstad2493bib22","article-title":"JAX: composable transformations of Python+NumPy programs","author":"Bradbury","year":"2018"},{"key":"mlstad2493bib23","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1145\/279232.279236","article-title":"Algorithm 778: L-BFGS-B: Fortran subroutines for large-scale bound-constrained optimization","volume":"23","author":"Zhu","year":"1997","journal-title":"ACM Trans. Math. Softw."},{"key":"mlstad2493bib24","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.124.025001","article-title":"Evolution of the electron distribution function in the presence of inverse bremsstrahlung heating and collisional ionization","volume":"124","author":"Milder","year":"2020","journal-title":"Phys. Rev. Lett."},{"key":"mlstad2493bib25","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.127.015001","article-title":"Measurements of non-Maxwellian electron distribution functions and their effect on laser heating","volume":"127","author":"Milder","year":"2021","journal-title":"Phys. Rev. Lett."},{"key":"mlstad2493bib26","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: fundamental algorithms for scientific computing in python","volume":"17","author":"(SciPy 1.0 Contributors)","year":"2020","journal-title":"Nat. Methods"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad2493","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad2493\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad2493\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad2493\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T07:52:02Z","timestamp":1707810722000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad2493"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,13]]},"references-count":26,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,2,13]]},"published-print":{"date-parts":[[2024,3,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad2493","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,13]]},"assertion":[{"value":"Qualitative and quantitative enhancement of parameter estimation for model-based diagnostics using automatic differentiation with an application to inertial fusion","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2024 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2023-10-04","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-01-31","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-02-13","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}