Machine Guided Discovery of Novel Carbon Capture Solvents
This work addresses the problem of costly and time-consuming materials development for carbon capture technologies, offering a machine learning tool to accelerate solvent discovery, though it is incremental in applying existing methods to a specific domain.
The authors tackled the challenge of discovering new carbon capture solvents by developing an end-to-end machine learning discovery cycle, which achieved 60% accuracy for material parameters and 80% for a single parameter on an external test set, leading to the identification of several promising amines verified experimentally.
The increasing importance of carbon capture technologies for deployment in remediating CO2 emissions, and thus the necessity to improve capture materials to allow scalability and efficiency, faces the challenge of materials development, which can require substantial costs and time. Machine learning offers a promising method for reducing the time and resource burdens of materials development through efficient correlation of structure-property relationships to allow down-selection and focusing on promising candidates. Towards demonstrating this, we have developed an end-to-end "discovery cycle" to select new aqueous amines compatible with the commercially viable acid gas scrubbing carbon capture. We combine a simple, rapid laboratory assay for CO2 absorption with a machine learning based molecular fingerprinting model approach. The prediction process shows 60% accuracy against experiment for both material parameters and 80% for a single parameter on an external test set. The discovery cycle determined several promising amines that were verified experimentally, and which had not been applied to carbon capture previously. In the process we have compiled a large, single-source data set for carbon capture amines and produced an open source machine learning tool for the identification of amine molecule candidates (https://github.com/IBM/Carbon-capture-fingerprint-generation).