[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126288-en":3,"doc-seo-126288-105":31,"detail-sidebar-cat-0-en-105":93},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126288,2336475104736,"Quinn","https://ap-avatar.wpscdn.com/avatar/22000c4c5e0e5b17e70?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786591360781797222",8,"Research & Report","Discovering and Designing Novel Perovskite Photovoltaic Materials via Machine Learning - Overview","Focuses on data-driven materials discovery for novel perovskite photovoltaics using machine learning. Breaks down “Perovskite Photovoltaics” by defining ABX3 perovskite chemistry and connecting light-to-electricity operation to solar cells and band-gap concepts. Presents an end-to-end workflow: generating hypothetical ABX3 compounds in a selected chemical space, constructing compositional property descriptors with domain-expertise filters, then predicting decomposition energy and electronic band gap using RGF regression.","Purdue University  \nPurdue e-Pubs  \n\n| Discovery Undergraduate Interdisciplinary Research Internship | Discovery Park District |\n| --- | --- |\n| 7-30-2025\u003Cbr>Discovering and Designing Novel Perovskite Photovoltaic Materials via Machine Learning\u003Cbr>Junyeong Ahn\u003Cbr>Purdue University, [ahn111@purdue.edu](ahn111@purdue.edu)\u003Cbr>Follow this and additional works at: [https://docs.lib.purdue.edu/duri](https://docs.lib.purdue.edu/duri)\u003Cbr> Part of the Chemical Engineering Commons, Data Science Commons, and the Semiconductor and Optical Materials Commons |  |\n\nRecommended Citation  \nAhn, Junyeong, \"Discovering and Designing Novel Perovskite Photovoltaic Materials via Machine Learning\" (2025) . Discovery Undergraduate Interdisciplinary Research Internship. Paper 64. [https://docs.lib.purdue.edu/duri/64](https://docs.lib.purdue.edu/duri/64)  \nThis document has been made available through Purdue e-Pubs, a service of the Purdue University Libraries. [Please contact epubs@purdue.edu](Please contact epubs@purdue.edu) for additional information.  \nDiscovering and Designing Novel Perovskite Photovoltaic Materials via Machine Learning  \nDiscovery Undergraduate Interdisciplinary Research Internship (DUIRI)  \nJunyeongAhn, MSE  \nPI : Arun Kumar Mannodi Kanakkithodi / Graduate mentor : Rushik Desai (MSE)  \nBreakdown of the Keyword : “Perovskite Photovoltaics”  \n• Perovskite : A type of ceramic compound with atomic composition of A – B – X3  \n􀂾 A & B: positive cations (Org / Inorg)  \n􀂾 X3 : negative anion × 3 (Halogen / Chalcogen)  \n• Photovoltaics : Light (photon) → electricity  \n􀂾 Solar cells  \n􀂾 Electron excitation into the conduction state – overcoming Band Gap  \n􀂾 Perovskite materials show outstanding PV efficiency  \nCallister, W. D., & Rethwisch, D. G. (2020) . Materials science and engineering: An introduction (10th ed. ) . Wiley.  \nA  \nBX  \nHalogens  \nChalcogens  \nTao, Q.; Xu, P.; Li, M.; Lu, W. Machine Learning for Perovskite Materials Design and Discovery. npj Comput Mater  \n2021, 7 (1), 1–18. [https://doi.org/10.1038/s41524-021-00495-8](https://doi.org/10.1038/s41524-021-00495-8. 3)[.](https://doi.org/10.1038/s41524-021-00495-8. 3)[ 3](https://doi.org/10.1038/s41524-021-00495-8. 3)  \nData-Driven Materials Discovery in Practice  \n\n| 1. Generate Hypothetical ABX 3 Compounds |\n| --- |\n| 2. ML Material Properties Prediction |\n| 3. ML Synthesizability Prediction |\n|  |\n\n1. Compound Generation  \nWhat do we want to make?  \nBa Zr S 3  \n2 + + 4 + + [3 × 2 − ]􀫙  \n=  \n􀂃 Charge neutral ABX3 perovskite compounds (Ex . BaZrS 3 )  \n􀂃 Cations (+) at A, B site with varying oxidation states from 1+ to 5+  \n􀂃 Anions (-) at X site with oxidation states of 1-to 3- (much narrower)  \n􀂃 12 physicochemical properties associated with each site elements  \n􀂃 12 × 3 sites = 36-dim property descriptors  \n􀂃 “Compositional property descriptors”  \nProperty descriptors: BP, MP, Density, At_wt, Elec_Aff, Heat_fusion, Heat_vap, Electronegativity, At_num, Period, ion_rad, ion_energy  \n􀂃 Apply filters to reduce the size of the generated data point  \n􀂃 Domain expertise : Goldschmidt tolerance factor (t, geometry indicator)Δ Electronegativity (Δχ, Chemical bond stability)  \nCompound Generation  \n• From the chemical space of 162 cations and 9 anions ...  \n􀂾  1,152,176 compounds generated (without filters) We absolutely can predict properties for all Do we REALLY need all of these?  \n􀂾 Let the experimentalist choose the chemical space!  \n􀀹 Choice of site elements / ions  \n􀀹 Generate compounds within the chosen chemical space  \nHalide Perovskites  \n\n| A | B | X |\n| --- | --- | --- |\n| MA | Pb | I |\n| FA | Sn | Br |\n| Cs | Ge | Cl |\n| Rb | Ba |  |\n| K | Sr |  |\n|  | Ca |  |\n\nChalcogenide Perovskites  \n\n| A | B | X |\n| --- | --- | --- |\n| Ba | Ti | S |\n| Sr | Zr | Se |\n| Ca | Hf | Te |\n|  | Sn |  |\n|  | Ge |  |\n|  |  |  |\n| La | Al | S |\n| Y | Sc | Se |\n| Ce | Sb | Te |\n\n2. Decomposition Energy / Electronic Band Gap Prediction with Regularized Greedy Forest (RGF) Regression","cbCaiuReyN53d3gq","https://ap.wps.com/l/cbCaiuReyN53d3gq","pdf",1929322,6,1,24,"English","en",105,"# Data-Driven Materials Discovery in Practice\n## Generate Hypothetical ABX3 Compounds\n## ML Material Properties Prediction\n## ML Synthesizability Prediction","[{\"question\":\"What does ABX3 mean in perovskite photovoltaics as described in the document?\",\"answer\":\"ABX3 refers to an atomic composition where A and B are cations at two cation sites and X is a negative anion multiplied three times at the anion site.\"},{\"question\":\"How are candidate perovskite compounds generated in the workflow?\",\"answer\":\"The workflow generates hypothetical ABX3 compositions by choosing site elements/ions within a defined chemical space, then filtering using domain expertise such as the Goldschmidt tolerance factor and electronegativity differences.\"},{\"question\":\"Which machine-learning task is used for decomposition energy and electronic band gap prediction?\",\"answer\":\"The document states the use of Regularized Greedy Forest (RGF) regression for predicting decomposition energy and electronic band gap.\"}]","Discovering and Designing Novel Perovskite Photovoltaic Materials via Machine Learning - Overview | PDF",1785904275,60,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"discovering-and-designing-novel-perovskite-photovoltaic-materials-via-machine-learning-overview","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/discovering-and-designing-novel-perovskite-photovoltaic-materials-via-machine-learning-overview/126288/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"What does ABX3 mean in perovskite photovoltaics as described in the document?","Question",{"text":77,"@type":78},"ABX3 refers to an atomic composition where A and B are cations at two cation sites and X is a negative anion multiplied three times at the anion site.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"How are candidate perovskite compounds generated in the workflow?",{"text":82,"@type":78},"The workflow generates hypothetical ABX3 compositions by choosing site elements/ions within a defined chemical space, then filtering using domain expertise such as the Goldschmidt tolerance factor and electronegativity differences.",{"name":84,"@type":75,"acceptedAnswer":85},"Which machine-learning task is used for decomposition energy and electronic band gap prediction?",{"text":86,"@type":78},"The document states the use of Regularized Greedy Forest (RGF) regression for predicting decomposition energy and electronic band gap.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,111,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":30,"slug":110},5,"Comic","comic",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":112,"show_sort_weight":113,"slug":114},"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":47,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":47,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":47,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":47,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":47,"category_name":137,"show_sort_weight":108,"slug":138},19,"General","general"]