Serendipity based recommender system for perovskites material discovery: balancing exploration and exploitation across multiple models
Machine learning is a useful tool for accelerating materials discovery, however it is a challenge to develop accurate methods that successfully transfer between domains while also broadening the scope of reaction conditions considered. In this paper, we consider how active- and transfer-learning methods can be used as building blocks for predicting reaction outcomes of metal halide perovskite synthesis. We then introduce a serendipity-based recommendation system that guides these methods to balance novelty and accuracy. The model-agnostic recommendation system is tested across active- and transfer-learning algorithms, using laboratory experiments for training and testing and a time-separated hold out that includes four different chemical systems. The serendipity recommendation system achieves high accuracy while increasing the scope of the synthesis conditions explored..
Medienart: |
Preprint |
---|
Erscheinungsjahr: |
2022 |
---|---|
Erschienen: |
2022 |
Enthalten in: |
chemRxiv.org - (2022) vom: 20. Juli Zur Gesamtaufnahme - year:2022 |
---|
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Shekar, Venkateswaran [VerfasserIn] |
---|
Links: |
Volltext [kostenfrei] |
---|
Themen: |
---|
doi: |
10.26434/chemrxiv-2022-l1wpf-v2 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
XCH03669004X |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | XCH03669004X | ||
003 | DE-627 | ||
005 | 20230429142419.0 | ||
007 | cr uuu---uuuuu | ||
008 | 220728s2022 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.26434/chemrxiv-2022-l1wpf-v2 |2 doi | |
035 | |a (DE-627)XCH03669004X | ||
035 | |a (chemrXiv)10.26434/chemrxiv-2022-l1wpf-v2 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Shekar, Venkateswaran |e verfasserin |4 aut | |
245 | 1 | 0 | |a Serendipity based recommender system for perovskites material discovery: balancing exploration and exploitation across multiple models |
264 | 1 | |c 2022 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a Computermedien |b c |2 rdamedia | ||
338 | |a Online-Ressource |b cr |2 rdacarrier | ||
520 | |a Machine learning is a useful tool for accelerating materials discovery, however it is a challenge to develop accurate methods that successfully transfer between domains while also broadening the scope of reaction conditions considered. In this paper, we consider how active- and transfer-learning methods can be used as building blocks for predicting reaction outcomes of metal halide perovskite synthesis. We then introduce a serendipity-based recommendation system that guides these methods to balance novelty and accuracy. The model-agnostic recommendation system is tested across active- and transfer-learning algorithms, using laboratory experiments for training and testing and a time-separated hold out that includes four different chemical systems. The serendipity recommendation system achieves high accuracy while increasing the scope of the synthesis conditions explored. | ||
650 | 4 | |a Chemistry |7 (dpeaa)DE-84 | |
650 | 4 | |a 540 |7 (dpeaa)DE-84 | |
700 | 1 | |a Yu, Vincent |e verfasserin |4 aut | |
700 | 1 | |a Garcia, Benjamin J. |e verfasserin |4 aut | |
700 | 1 | |a Gordon, David Benjamin |e verfasserin |4 aut | |
700 | 1 | |a Moran, Gemma E. |e verfasserin |4 aut | |
700 | 1 | |a Blei, David M. |e verfasserin |4 aut | |
700 | 1 | |a Roch, Loïc M. |e verfasserin |4 aut | |
700 | 1 | |a García-Durán, Alberto |e verfasserin |4 aut | |
700 | 1 | |a Ani Najeeb, Mansoor |e verfasserin |4 aut | |
700 | 1 | |a Zeile, Margaret |e verfasserin |4 aut | |
700 | 1 | |a Nega, Philip W. |e verfasserin |4 aut | |
700 | 1 | |a Li, Zhi |e verfasserin |4 aut | |
700 | 1 | |a Kim, Mina A. |e verfasserin |4 aut | |
700 | 1 | |a Chan, Emory M. |e verfasserin |4 aut | |
700 | 1 | |a Norquist, Alexander J. |e verfasserin |4 aut | |
700 | 1 | |a Friedler, Sorelle |e verfasserin |4 aut | |
700 | 1 | |a Schrier, Joshua |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t chemRxiv.org |g (2022) vom: 20. Juli |
773 | 1 | 8 | |g year:2022 |g day:20 |g month:07 |
856 | 4 | 0 | |u http://dx.doi.org/10.26434/chemrxiv-2022-l1wpf-v2 |z kostenfrei |3 Volltext |
912 | |a GBV_XCH | ||
912 | |a SSG-OLC-PHA | ||
951 | |a AR | ||
952 | |j 2022 |b 20 |c 07 |