Attention-based solubility prediction of polysulfide and electrolyte analysis for lithium–sulfur batteries
Abstract During the continuous charge and discharge process in lithium-sulfur batteries, one of the next-generation batteries, polysulfides are generated in the battery’s electrolyte, and impact its performance in terms of power and capacity by involving the process. The amount of polysulfides in th...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-11-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-47154-0 |
| _version_ | 1797415210340843520 |
|---|---|
| author | Jaewan Lee Hongjun Yang Changyoung Park Seong-Hyo Park Eunji Jang Hobeom Kwack Chang Hoon Lee Chang-ik Song Young Cheol Choi Sehui Han Honglak Lee |
| author_facet | Jaewan Lee Hongjun Yang Changyoung Park Seong-Hyo Park Eunji Jang Hobeom Kwack Chang Hoon Lee Chang-ik Song Young Cheol Choi Sehui Han Honglak Lee |
| author_sort | Jaewan Lee |
| collection | DOAJ |
| description | Abstract During the continuous charge and discharge process in lithium-sulfur batteries, one of the next-generation batteries, polysulfides are generated in the battery’s electrolyte, and impact its performance in terms of power and capacity by involving the process. The amount of polysulfides in the electrolyte could be estimated by the change of the Gibbs free energy of the electrolyte, $$\Delta _{mix}\textrm{G}$$ Δ mix G in the presence of polysulfide. However, obtaining $$\Delta _{mix}\textrm{G}$$ Δ mix G of the diverse mixtures of components in the electrolyte is a complex and expensive task that shows itself as a bottleneck in optimization of electrolytes. In this work, we present a machine-learning approach for predicting $$\Delta _{mix}\textrm{G}$$ Δ mix G of electrolytes. The proposed architecture utilizes (1) an attention-based model (Attentive FP), a contrastive learning model (MolCLR) or morgan fingerprints to represent chemical components, and (2) transformers to account for the interactions between chemicals in the electrolyte. This architecture was not only capable of predicting electrolyte properties, including those of chemicals not used during training, but also providing insights into chemical interactions within electrolytes. It revealed that interactions with other chemicals relate to the logP and molecular weight of the chemicals. |
| first_indexed | 2024-03-09T05:44:33Z |
| format | Article |
| id | doaj.art-ce5cdee094f54dd6b70e68d4fc0260e9 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-09T05:44:33Z |
| publishDate | 2023-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-ce5cdee094f54dd6b70e68d4fc0260e92023-12-03T12:22:14ZengNature PortfolioScientific Reports2045-23222023-11-011311910.1038/s41598-023-47154-0Attention-based solubility prediction of polysulfide and electrolyte analysis for lithium–sulfur batteriesJaewan Lee0Hongjun Yang1Changyoung Park2Seong-Hyo Park3Eunji Jang4Hobeom Kwack5Chang Hoon Lee6Chang-ik Song7Young Cheol Choi8Sehui Han9Honglak Lee10LG AI Research, ISCLG AI Research, ISCLG AI Research, ISCLG Energy Solution, LTD.LG Energy Solution, LTD.LG Energy Solution, LTD.LG Energy Solution, LTD.LG Energy Solution, LTD.LG Energy Solution, LTD.LG AI Research, ISCLG AI Research, ISCAbstract During the continuous charge and discharge process in lithium-sulfur batteries, one of the next-generation batteries, polysulfides are generated in the battery’s electrolyte, and impact its performance in terms of power and capacity by involving the process. The amount of polysulfides in the electrolyte could be estimated by the change of the Gibbs free energy of the electrolyte, $$\Delta _{mix}\textrm{G}$$ Δ mix G in the presence of polysulfide. However, obtaining $$\Delta _{mix}\textrm{G}$$ Δ mix G of the diverse mixtures of components in the electrolyte is a complex and expensive task that shows itself as a bottleneck in optimization of electrolytes. In this work, we present a machine-learning approach for predicting $$\Delta _{mix}\textrm{G}$$ Δ mix G of electrolytes. The proposed architecture utilizes (1) an attention-based model (Attentive FP), a contrastive learning model (MolCLR) or morgan fingerprints to represent chemical components, and (2) transformers to account for the interactions between chemicals in the electrolyte. This architecture was not only capable of predicting electrolyte properties, including those of chemicals not used during training, but also providing insights into chemical interactions within electrolytes. It revealed that interactions with other chemicals relate to the logP and molecular weight of the chemicals.https://doi.org/10.1038/s41598-023-47154-0 |
| spellingShingle | Jaewan Lee Hongjun Yang Changyoung Park Seong-Hyo Park Eunji Jang Hobeom Kwack Chang Hoon Lee Chang-ik Song Young Cheol Choi Sehui Han Honglak Lee Attention-based solubility prediction of polysulfide and electrolyte analysis for lithium–sulfur batteries Scientific Reports |
| title | Attention-based solubility prediction of polysulfide and electrolyte analysis for lithium–sulfur batteries |
| title_full | Attention-based solubility prediction of polysulfide and electrolyte analysis for lithium–sulfur batteries |
| title_fullStr | Attention-based solubility prediction of polysulfide and electrolyte analysis for lithium–sulfur batteries |
| title_full_unstemmed | Attention-based solubility prediction of polysulfide and electrolyte analysis for lithium–sulfur batteries |
| title_short | Attention-based solubility prediction of polysulfide and electrolyte analysis for lithium–sulfur batteries |
| title_sort | attention based solubility prediction of polysulfide and electrolyte analysis for lithium sulfur batteries |
| url | https://doi.org/10.1038/s41598-023-47154-0 |
| work_keys_str_mv | AT jaewanlee attentionbasedsolubilitypredictionofpolysulfideandelectrolyteanalysisforlithiumsulfurbatteries AT hongjunyang attentionbasedsolubilitypredictionofpolysulfideandelectrolyteanalysisforlithiumsulfurbatteries AT changyoungpark attentionbasedsolubilitypredictionofpolysulfideandelectrolyteanalysisforlithiumsulfurbatteries AT seonghyopark attentionbasedsolubilitypredictionofpolysulfideandelectrolyteanalysisforlithiumsulfurbatteries AT eunjijang attentionbasedsolubilitypredictionofpolysulfideandelectrolyteanalysisforlithiumsulfurbatteries AT hobeomkwack attentionbasedsolubilitypredictionofpolysulfideandelectrolyteanalysisforlithiumsulfurbatteries AT changhoonlee attentionbasedsolubilitypredictionofpolysulfideandelectrolyteanalysisforlithiumsulfurbatteries AT changiksong attentionbasedsolubilitypredictionofpolysulfideandelectrolyteanalysisforlithiumsulfurbatteries AT youngcheolchoi attentionbasedsolubilitypredictionofpolysulfideandelectrolyteanalysisforlithiumsulfurbatteries AT sehuihan attentionbasedsolubilitypredictionofpolysulfideandelectrolyteanalysisforlithiumsulfurbatteries AT honglaklee attentionbasedsolubilitypredictionofpolysulfideandelectrolyteanalysisforlithiumsulfurbatteries |