Of all greenhouse gases, carbon dioxide is the greatest contributor to global warming. According to the Intergovernmental Panel on Climate Change, by 2100, if no action is taken, the average global temperature will rise by around 34 degrees Fahrenheit. Finding effective ways to capture and store CO2 is a challenge for researchers and industry focused on combating global warming, and Amir Barati Farimani has worked to change that.
“Machine learning models have the potential to discover new compounds or materials to combat global warming,” explains Barati Farimani, assistant professor of mechanical engineering at Carnegie Mellon University. “Machine learning models can achieve accurate and efficient virtual screening of CO2 They may even be conserved candidates and generate favorable compounds that did not exist before. ”
Barati Farimani made a breakthrough in identifying ionic liquid molecules using machine learning. Ionic liquids (ILs) are a family of molten salts that remain liquid at room temperature, have high chemical stability, and high CO.2 Highly soluble, making it an ideal candidate for CO2 Storage. Combinations of ions primarily determine the properties of ILs. However, the possibility of such combinations of cations and anions makes it very difficult to exhaust the design space of efficient CO ILs.2 Conventional experimental storage.
Machine learning is commonly used in drug discovery to create so-called molecular fingerprints, along with graph neural networks (GNNs), which treat molecules as graphs and use matrices to identify molecular bonds and related properties. Barati Farimani was the first to develop both his fingerprint-based ML model and GNNs that can predict CO.2 Absorption of ionic liquids.
“Our GNN method achieves excellent accuracy in CO prediction.2 Barati Farimani said: “Unlike his previous ML methods, which rely on hand-crafted features, GNNs learn features directly from the molecular graph.”
Understanding how machine learning models make decisions is just as important as the molecular properties they identify. This description provides researchers with further insight into how the structure of molecules affects the properties of ionic liquids from a data-driven perspective. For example, Barati Farmimani’s team discovered a molecular fragment that physically interacts with CO.2 Not as important as those with chemical interactions.Moreover, those with fewer hydrogens attached to nitrogen may be more favorable to formalize stable chemical interactions with CO2.
These findings are ACS Sustainable Chemistry and Engineeringallows researchers to advise on the design of novel and efficient ionic liquids of CO.2 future storage.
For more information:
Yue Jian et al., Prediction of CO2 Uptake in Ionic Liquids Using Molecular Descriptors and Explainable Graph Neural Networks, ACS Sustainable Chemistry and Engineering (2022). DOI: 10.1021/acssuschemeng.2c05985
