Unified physio-thermodynamic descriptors via learned CO2 adsorption properties in metal-organic frameworks
Abstract The large design space of metal-organic frameworks (MOFs) has prompted the utilization of deep learning to drive material design. Nonetheless, the prediction of key thermodynamic properties, such as heat of adsorption ( $$\Delta {H}_{{\rm{ads}}}$$ Δ H ads ), remains largely unexplored for C...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | npj Computational Materials |
| Online Access: | https://doi.org/10.1038/s41524-025-01700-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849331871564955648 |
|---|---|
| author | Emily Lin Yang Zhong Gang Chen Sili Deng |
| author_facet | Emily Lin Yang Zhong Gang Chen Sili Deng |
| author_sort | Emily Lin |
| collection | DOAJ |
| description | Abstract The large design space of metal-organic frameworks (MOFs) has prompted the utilization of deep learning to drive material design. Nonetheless, the prediction of key thermodynamic properties, such as heat of adsorption ( $$\Delta {H}_{{\rm{ads}}}$$ Δ H ads ), remains largely unexplored for CO2 adsorption in MOFs. Herein, we present IsothermNet, a high-throughput graph neural network designed to estimate uptake and $$\Delta {H}_{{\rm{ads}}}$$ Δ H ads over 0–50 bars, enabling high-quality full isotherm reconstruction (PCC: 0.73–0.95 [uptake], 0.76–0.88 [ $$\Delta {H}_{{\rm{ads}}}$$ Δ H ads ]). We further bridged these adsorption properties to uptake behaviors (i.e., isotherm shapes/types) and structural information by performing detailed ablation studies to investigate the relative importance of local and global features in relation to predictive performance. This comparative analysis facilitated the discovery of a (1) physically-interpretable and (2) analytically-derived universal descriptor set capable of illustrating interdependencies between easily-computed, accessible textural information and extrinsic adsorption properties. When used cooperatively with IsothermNet, these descriptors enable efficient material screening, accelerating high-performance MOF discovery for CO2 capture. |
| format | Article |
| id | doaj-art-20a0389f96ea4f5da53ba66067e4d7d4 |
| institution | Kabale University |
| issn | 2057-3960 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Computational Materials |
| spelling | doaj-art-20a0389f96ea4f5da53ba66067e4d7d42025-08-20T03:46:23ZengNature Portfolionpj Computational Materials2057-39602025-07-0111111110.1038/s41524-025-01700-8Unified physio-thermodynamic descriptors via learned CO2 adsorption properties in metal-organic frameworksEmily Lin0Yang Zhong1Gang Chen2Sili Deng3Massachusetts Institute of TechnologyMassachusetts Institute of TechnologyMassachusetts Institute of TechnologyMassachusetts Institute of TechnologyAbstract The large design space of metal-organic frameworks (MOFs) has prompted the utilization of deep learning to drive material design. Nonetheless, the prediction of key thermodynamic properties, such as heat of adsorption ( $$\Delta {H}_{{\rm{ads}}}$$ Δ H ads ), remains largely unexplored for CO2 adsorption in MOFs. Herein, we present IsothermNet, a high-throughput graph neural network designed to estimate uptake and $$\Delta {H}_{{\rm{ads}}}$$ Δ H ads over 0–50 bars, enabling high-quality full isotherm reconstruction (PCC: 0.73–0.95 [uptake], 0.76–0.88 [ $$\Delta {H}_{{\rm{ads}}}$$ Δ H ads ]). We further bridged these adsorption properties to uptake behaviors (i.e., isotherm shapes/types) and structural information by performing detailed ablation studies to investigate the relative importance of local and global features in relation to predictive performance. This comparative analysis facilitated the discovery of a (1) physically-interpretable and (2) analytically-derived universal descriptor set capable of illustrating interdependencies between easily-computed, accessible textural information and extrinsic adsorption properties. When used cooperatively with IsothermNet, these descriptors enable efficient material screening, accelerating high-performance MOF discovery for CO2 capture.https://doi.org/10.1038/s41524-025-01700-8 |
| spellingShingle | Emily Lin Yang Zhong Gang Chen Sili Deng Unified physio-thermodynamic descriptors via learned CO2 adsorption properties in metal-organic frameworks npj Computational Materials |
| title | Unified physio-thermodynamic descriptors via learned CO2 adsorption properties in metal-organic frameworks |
| title_full | Unified physio-thermodynamic descriptors via learned CO2 adsorption properties in metal-organic frameworks |
| title_fullStr | Unified physio-thermodynamic descriptors via learned CO2 adsorption properties in metal-organic frameworks |
| title_full_unstemmed | Unified physio-thermodynamic descriptors via learned CO2 adsorption properties in metal-organic frameworks |
| title_short | Unified physio-thermodynamic descriptors via learned CO2 adsorption properties in metal-organic frameworks |
| title_sort | unified physio thermodynamic descriptors via learned co2 adsorption properties in metal organic frameworks |
| url | https://doi.org/10.1038/s41524-025-01700-8 |
| work_keys_str_mv | AT emilylin unifiedphysiothermodynamicdescriptorsvialearnedco2adsorptionpropertiesinmetalorganicframeworks AT yangzhong unifiedphysiothermodynamicdescriptorsvialearnedco2adsorptionpropertiesinmetalorganicframeworks AT gangchen unifiedphysiothermodynamicdescriptorsvialearnedco2adsorptionpropertiesinmetalorganicframeworks AT silideng unifiedphysiothermodynamicdescriptorsvialearnedco2adsorptionpropertiesinmetalorganicframeworks |