Machine learning accelerated descriptor design for catalyst discovery in CO2 to methanol conversion
Problem
Achieving high methanol yields and stable catalysts for CO2 thermoreduction remains a significant challenge for closing the carbon cycle.
Why it matters
CO2-to-methanol conversion is a crucial step toward closing the carbon cycle and nearing industrial application.
What the AI did
A computational framework using machine-learned force fields and a new descriptor (adsorption energy distribution), plus unsupervised machine learning on ~160 metallic alloys, to accelerate catalyst discovery.
Results
Proposed new promising catalyst candidates ZnRh and ZnPt3 from analysis of nearly 160 metallic alloys.
Impact
ML accelerated computational screening and produced candidate catalysts; no experimental validation is stated.
Record
| Venue | npj Computational Materials |
|---|---|
| Published | 2025 |
| Work type | article |
| Authors | Prajwal Sanjay Pisal, Ondřej Krejčí, Patrick Rinke |
| Citations | 25 (OpenAlex, at import time) |
| References | 67 |
| Model or method | machine-learned force fields; unsupervised machine learning (no named model) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1038/s41524-025-01664-9 |
| Open access | gold |
| Keywords | CO2 conversion, methanol, catalyst discovery, machine-learned force fields, unsupervised learning, alloys |
Importance rating
significant — thousands to millions affected
Abstract calls CO2-to-methanol conversion a crucial step toward closing the carbon cycle, with technology nearing industrial application; major climate/industrial relevance, though study is computational screening without experimental validation.
More in Climate & Environment
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Learning skillful medium-range global weather forecasting | 2023 | 1,416 |
8
|
| 2 | Accurate medium-range global weather forecasting with 3D neural networks | 2023 | 1,631 |
8
|
| 3 | FuXi: a cascade machine learning forecasting system for 15-day global weather forecast | 2023 | 355 |
8
|
| 4 | Skilful nowcasting of extreme precipitation with NowcastNet | 2023 | 451 |
8
|
| 5 | Forecasting Renewable Energy Generation with Machine Learning and Deep Learning: Current Advances and Future Prospects | 2023 | 378 |
8
|