How machine learning can help select capping layers to suppress perovskite degradation
Environmental stability of perovskite solar cells (PSCs) has been improved by trial-and-error exploration of thin low-dimensional (LD) perovskite deposited on top of the perovskite absorber, called the capping layer. In this study, a machine-learning framework is presented to optimize this layer. We...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Springer Science and Business Media LLC
2021
|
| Online Access: | https://hdl.handle.net/1721.1/129799 |
| _version_ | 1826197576886517760 |
|---|---|
| author | Hartono, Noor Titan Putri Thapa, Janak Tiihonen, Armi Oviedo, Felipe Batali, Clio Yoo, Jason J.(Jason Jungwan) Liu, Zhe Li, Ruipeng Marrón, David Fuertes Bawendi, Moungi G Buonassisi, Tonio Sun, Shijing |
| author2 | Massachusetts Institute of Technology. Department of Mechanical Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Mechanical Engineering Hartono, Noor Titan Putri Thapa, Janak Tiihonen, Armi Oviedo, Felipe Batali, Clio Yoo, Jason J.(Jason Jungwan) Liu, Zhe Li, Ruipeng Marrón, David Fuertes Bawendi, Moungi G Buonassisi, Tonio Sun, Shijing |
| author_sort | Hartono, Noor Titan Putri |
| collection | MIT |
| description | Environmental stability of perovskite solar cells (PSCs) has been improved by trial-and-error exploration of thin low-dimensional (LD) perovskite deposited on top of the perovskite absorber, called the capping layer. In this study, a machine-learning framework is presented to optimize this layer. We featurize 21 organic halide salts, apply them as capping layers onto methylammonium lead iodide (MAPbI₃) films, age them under accelerated conditions, and determine features governing stability using supervised machine learning and Shapley values. We find that organic molecules’ low number of hydrogen-bonding donors and small topological polar surface area correlate with increased MAPbI₃ film stability. The top performing organic halide, phenyltriethylammonium iodide (PTEAI), successfully extends the MAPbI₃ stability lifetime by 4 ± 2 times over bare MAPbI₃ and 1.3 ± 0.3 times over state-of-the-art octylammonium bromide (OABr). Through characterization, we find that this capping layer stabilizes the photoactive layer by changing the surface chemistry and suppressing methylammonium loss. |
| first_indexed | 2024-09-23T10:49:46Z |
| format | Article |
| id | mit-1721.1/129799 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T10:49:46Z |
| publishDate | 2021 |
| publisher | Springer Science and Business Media LLC |
| record_format | dspace |
| spelling | mit-1721.1/1297992022-09-30T23:19:51Z How machine learning can help select capping layers to suppress perovskite degradation Hartono, Noor Titan Putri Thapa, Janak Tiihonen, Armi Oviedo, Felipe Batali, Clio Yoo, Jason J.(Jason Jungwan) Liu, Zhe Li, Ruipeng Marrón, David Fuertes Bawendi, Moungi G Buonassisi, Tonio Sun, Shijing Massachusetts Institute of Technology. Department of Mechanical Engineering Environmental stability of perovskite solar cells (PSCs) has been improved by trial-and-error exploration of thin low-dimensional (LD) perovskite deposited on top of the perovskite absorber, called the capping layer. In this study, a machine-learning framework is presented to optimize this layer. We featurize 21 organic halide salts, apply them as capping layers onto methylammonium lead iodide (MAPbI₃) films, age them under accelerated conditions, and determine features governing stability using supervised machine learning and Shapley values. We find that organic molecules’ low number of hydrogen-bonding donors and small topological polar surface area correlate with increased MAPbI₃ film stability. The top performing organic halide, phenyltriethylammonium iodide (PTEAI), successfully extends the MAPbI₃ stability lifetime by 4 ± 2 times over bare MAPbI₃ and 1.3 ± 0.3 times over state-of-the-art octylammonium bromide (OABr). Through characterization, we find that this capping layer stabilizes the photoactive layer by changing the surface chemistry and suppressing methylammonium loss. NSF (Award DMR-1419807) NSF (Grant CBET-1605547) Skoltech (Grant 1913/R) DOE (Award DE-EE0007535) ISN (Grant W911NF-13-D-0001) NASA (Grant NNX16AM70H) 2021-02-17T21:04:56Z 2021-02-17T21:04:56Z 2020-08 2020-01 2020-09-14T17:28:51Z Article http://purl.org/eprint/type/JournalArticle 2041-1723 https://hdl.handle.net/1721.1/129799 Hartono, Noor Titan Putri et al. "How machine learning can help select capping layers to suppress perovskite degradation." Nature Communications 11, 1 (August 2020): 4172. en 10.1038/s41467-020-17945-4 Nature Communications Creative Commons Attribution 4.0 International license https://creativecommons.org/licenses/by/4.0/ application/pdf Springer Science and Business Media LLC Nature |
| spellingShingle | Hartono, Noor Titan Putri Thapa, Janak Tiihonen, Armi Oviedo, Felipe Batali, Clio Yoo, Jason J.(Jason Jungwan) Liu, Zhe Li, Ruipeng Marrón, David Fuertes Bawendi, Moungi G Buonassisi, Tonio Sun, Shijing How machine learning can help select capping layers to suppress perovskite degradation |
| title | How machine learning can help select capping layers to suppress perovskite degradation |
| title_full | How machine learning can help select capping layers to suppress perovskite degradation |
| title_fullStr | How machine learning can help select capping layers to suppress perovskite degradation |
| title_full_unstemmed | How machine learning can help select capping layers to suppress perovskite degradation |
| title_short | How machine learning can help select capping layers to suppress perovskite degradation |
| title_sort | how machine learning can help select capping layers to suppress perovskite degradation |
| url | https://hdl.handle.net/1721.1/129799 |
| work_keys_str_mv | AT hartononoortitanputri howmachinelearningcanhelpselectcappinglayerstosuppressperovskitedegradation AT thapajanak howmachinelearningcanhelpselectcappinglayerstosuppressperovskitedegradation AT tiihonenarmi howmachinelearningcanhelpselectcappinglayerstosuppressperovskitedegradation AT oviedofelipe howmachinelearningcanhelpselectcappinglayerstosuppressperovskitedegradation AT bataliclio howmachinelearningcanhelpselectcappinglayerstosuppressperovskitedegradation AT yoojasonjjasonjungwan howmachinelearningcanhelpselectcappinglayerstosuppressperovskitedegradation AT liuzhe howmachinelearningcanhelpselectcappinglayerstosuppressperovskitedegradation AT liruipeng howmachinelearningcanhelpselectcappinglayerstosuppressperovskitedegradation AT marrondavidfuertes howmachinelearningcanhelpselectcappinglayerstosuppressperovskitedegradation AT bawendimoungig howmachinelearningcanhelpselectcappinglayerstosuppressperovskitedegradation AT buonassisitonio howmachinelearningcanhelpselectcappinglayerstosuppressperovskitedegradation AT sunshijing howmachinelearningcanhelpselectcappinglayerstosuppressperovskitedegradation |