Show simple item record

dc.contributor.authorRen, Zekun
dc.contributor.authorOviedo, Felipe
dc.contributor.authorThway, Maung
dc.contributor.authorTian, Siyu IP
dc.contributor.authorWang, Yue
dc.contributor.authorXue, Hansong
dc.contributor.authorDario Perea, Jose
dc.contributor.authorLayurova, Mariya
dc.contributor.authorHeumueller, Thomas
dc.contributor.authorBirgersson, Erik
dc.contributor.authorAberle, Armin G
dc.contributor.authorBrabec, Christoph J
dc.contributor.authorStangl, Rolf
dc.contributor.authorLi, Qianxiao
dc.contributor.authorSun, Shijing
dc.contributor.authorLin, Fen
dc.contributor.authorPeters, Ian Marius
dc.contributor.authorBuonassisi, Tonio
dc.date.accessioned2021-12-14T18:58:43Z
dc.date.available2021-12-14T18:58:43Z
dc.date.issued2020
dc.identifier.urihttps://hdl.handle.net/1721.1/138474
dc.description.abstract© 2020, The Author(s). Process optimization of photovoltaic devices is a time-intensive, trial-and-error endeavor, which lacks full transparency of the underlying physics and relies on user-imposed constraints that may or may not lead to a global optimum. Herein, we demonstrate that embedding physics domain knowledge into a Bayesian network enables an optimization approach for gallium arsenide (GaAs) solar cells that identifies the root cause(s) of underperformance with layer-by-layer resolution and reveals alternative optimal process windows beyond traditional black-box optimization. Our Bayesian network approach links a key GaAs process variable (growth temperature) to material descriptors (bulk and interface properties, e.g., bulk lifetime, doping, and surface recombination) and device performance parameters (e.g., cell efficiency). For this purpose, we combine a Bayesian inference framework with a neural network surrogate device-physics model that is 100× faster than numerical solvers. With the trained surrogate model and only a small number of experimental samples, our approach reduces significantly the time-consuming intervention and characterization required by the experimentalist. As a demonstration of our method, in only five metal organic chemical vapor depositions, we identify a superior growth temperature profile for the window, bulk, and back surface field layer of a GaAs solar cell, without any secondary measurements, and demonstrate a 6.5% relative AM1.5G efficiency improvement above traditional grid search methods.en_US
dc.language.isoen
dc.publisherSpringer Science and Business Media LLCen_US
dc.relation.isversionof10.1038/S41524-020-0277-Xen_US
dc.rightsCreative Commons Attribution 4.0 International licenseen_US
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/en_US
dc.sourceNatureen_US
dc.titleEmbedding physics domain knowledge into a Bayesian network enables layer-by-layer process innovation for photovoltaicsen_US
dc.typeArticleen_US
dc.identifier.citationRen, Zekun, Oviedo, Felipe, Thway, Maung, Tian, Siyu IP, Wang, Yue et al. 2020. "Embedding physics domain knowledge into a Bayesian network enables layer-by-layer process innovation for photovoltaics." npj Computational Materials, 6 (1).
dc.contributor.departmentSingapore-MIT Alliance in Research and Technology (SMART)
dc.contributor.departmentMassachusetts Institute of Technology. Department of Mechanical Engineering
dc.relation.journalnpj Computational Materialsen_US
dc.eprint.versionFinal published versionen_US
dc.type.urihttp://purl.org/eprint/type/JournalArticleen_US
eprint.statushttp://purl.org/eprint/status/PeerRevieweden_US
dc.date.updated2021-12-14T18:55:50Z
dspace.orderedauthorsRen, Z; Oviedo, F; Thway, M; Tian, SIP; Wang, Y; Xue, H; Dario Perea, J; Layurova, M; Heumueller, T; Birgersson, E; Aberle, AG; Brabec, CJ; Stangl, R; Li, Q; Sun, S; Lin, F; Peters, IM; Buonassisi, Ten_US
dspace.date.submission2021-12-14T18:55:52Z
mit.journal.volume6en_US
mit.journal.issue1en_US
mit.licensePUBLISHER_CC
mit.metadata.statusAuthority Work and Publication Information Neededen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record