Polymer design for solvent separations by integrating simulations, experiments and known physics via machine learning
Abstract This study guides the discovery of sustainable high-performance polymer membranes for organic binary solvent separations. We focus on solvent diffusivity in polymers, a key factor in quantifying solvent transport. Traditional experimental and computational methods for determining diffusivit...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-06-01
|
| Series: | npj Computational Materials |
| Online Access: | https://doi.org/10.1038/s41524-025-01681-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850207449231917056 |
|---|---|
| author | Janhavi Nistane Rohan Datta Young Joo Lee Harikrishna Sahu Seung Soon Jang Ryan Lively Rampi Ramprasad |
| author_facet | Janhavi Nistane Rohan Datta Young Joo Lee Harikrishna Sahu Seung Soon Jang Ryan Lively Rampi Ramprasad |
| author_sort | Janhavi Nistane |
| collection | DOAJ |
| description | Abstract This study guides the discovery of sustainable high-performance polymer membranes for organic binary solvent separations. We focus on solvent diffusivity in polymers, a key factor in quantifying solvent transport. Traditional experimental and computational methods for determining diffusivity are time- and resource-intensive, while current machine learning (ML) models often lack accuracy outside their training domains. To overcome this, we fuse experimental and simulated diffusivity data to train physics-enforced multi-task ML models, achieving more robust predictions in unseen chemical spaces and outperforming single-task models in data-limited scenarios. Next, we address the challenge of identifying optimal membranes for a model toluene-heptane separation, identifying polyvinyl chloride (PVC) as the optimal membrane among 13,000 polymers, consistent with literature findings, thereby validating our methodology. Expanding our search, we screen 1 million publicly available and 7 million chemically recyclable polymers, identifying greener halogen-free alternatives to PVC. This capability is expected to advance membrane design for solvent separations. |
| format | Article |
| id | doaj-art-ab7df909c4e34668a989affc97fb405d |
| institution | OA Journals |
| issn | 2057-3960 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Computational Materials |
| spelling | doaj-art-ab7df909c4e34668a989affc97fb405d2025-08-20T02:10:31ZengNature Portfolionpj Computational Materials2057-39602025-06-0111111210.1038/s41524-025-01681-8Polymer design for solvent separations by integrating simulations, experiments and known physics via machine learningJanhavi Nistane0Rohan Datta1Young Joo Lee2Harikrishna Sahu3Seung Soon Jang4Ryan Lively5Rampi Ramprasad6School of Materials Science and Engineering, Georgia Institute of TechnologySchool of Chemical and Biomolecular Engineering, Georgia Institute of TechnologySchool of Chemical and Biomolecular Engineering, Georgia Institute of TechnologySchool of Materials Science and Engineering, Georgia Institute of TechnologySchool of Materials Science and Engineering, Georgia Institute of TechnologySchool of Chemical and Biomolecular Engineering, Georgia Institute of TechnologySchool of Materials Science and Engineering, Georgia Institute of TechnologyAbstract This study guides the discovery of sustainable high-performance polymer membranes for organic binary solvent separations. We focus on solvent diffusivity in polymers, a key factor in quantifying solvent transport. Traditional experimental and computational methods for determining diffusivity are time- and resource-intensive, while current machine learning (ML) models often lack accuracy outside their training domains. To overcome this, we fuse experimental and simulated diffusivity data to train physics-enforced multi-task ML models, achieving more robust predictions in unseen chemical spaces and outperforming single-task models in data-limited scenarios. Next, we address the challenge of identifying optimal membranes for a model toluene-heptane separation, identifying polyvinyl chloride (PVC) as the optimal membrane among 13,000 polymers, consistent with literature findings, thereby validating our methodology. Expanding our search, we screen 1 million publicly available and 7 million chemically recyclable polymers, identifying greener halogen-free alternatives to PVC. This capability is expected to advance membrane design for solvent separations.https://doi.org/10.1038/s41524-025-01681-8 |
| spellingShingle | Janhavi Nistane Rohan Datta Young Joo Lee Harikrishna Sahu Seung Soon Jang Ryan Lively Rampi Ramprasad Polymer design for solvent separations by integrating simulations, experiments and known physics via machine learning npj Computational Materials |
| title | Polymer design for solvent separations by integrating simulations, experiments and known physics via machine learning |
| title_full | Polymer design for solvent separations by integrating simulations, experiments and known physics via machine learning |
| title_fullStr | Polymer design for solvent separations by integrating simulations, experiments and known physics via machine learning |
| title_full_unstemmed | Polymer design for solvent separations by integrating simulations, experiments and known physics via machine learning |
| title_short | Polymer design for solvent separations by integrating simulations, experiments and known physics via machine learning |
| title_sort | polymer design for solvent separations by integrating simulations experiments and known physics via machine learning |
| url | https://doi.org/10.1038/s41524-025-01681-8 |
| work_keys_str_mv | AT janhavinistane polymerdesignforsolventseparationsbyintegratingsimulationsexperimentsandknownphysicsviamachinelearning AT rohandatta polymerdesignforsolventseparationsbyintegratingsimulationsexperimentsandknownphysicsviamachinelearning AT youngjoolee polymerdesignforsolventseparationsbyintegratingsimulationsexperimentsandknownphysicsviamachinelearning AT harikrishnasahu polymerdesignforsolventseparationsbyintegratingsimulationsexperimentsandknownphysicsviamachinelearning AT seungsoonjang polymerdesignforsolventseparationsbyintegratingsimulationsexperimentsandknownphysicsviamachinelearning AT ryanlively polymerdesignforsolventseparationsbyintegratingsimulationsexperimentsandknownphysicsviamachinelearning AT rampiramprasad polymerdesignforsolventseparationsbyintegratingsimulationsexperimentsandknownphysicsviamachinelearning |