CarbNN: A Novel Active Transfer Learning Neural Network To Build De Novo Metal Organic Frameworks (MOFs) for Carbon Capture
This work addresses the need for better carbon capture materials to combat climate change, offering a computational method that could accelerate discovery in materials science, though it is incremental as it builds on transfer learning with limited data.
The researchers tackled the problem of designing efficient and cost-effective Metal Organic Frameworks (MOFs) for carbon capture by developing an active transfer learning neural network, which successfully generated a novel Selenium MOF (C18MgO25Se11Sn20Zn5) that is predicted to be more effective and synthetically accessible than existing MOFs.
Over the past decade, climate change has become an increasing problem with one of the major contributing factors being carbon dioxide (CO2) emissions; almost 51% of total US carbon emissions are from factories. Current materials used in CO2 capture are lacking either in efficiency, sustainability, or cost. Electrocatalysis of CO2 is a new approach where CO2 can be reduced and the components used industrially as fuel, saving transportation costs, creating financial incentives. Metal Organic Frameworks (MOFs) are crystals made of organo-metals that adsorb, filter, and electrocatalyze CO2. The current available MOFs for capture & electrocatalysis are expensive to manufacture and inefficient at capture. The goal therefore is to computationally design a MOF that can adsorb CO2 and catalyze carbon monoxide & oxygen with low cost. A novel active transfer learning neural network was developed, utilizing transfer learning due to limited available data on 15 MOFs. Using the Cambridge Structural Database with 10,000 MOFs, the model used incremental mutations to fit a trained fitness hyper-heuristic function. Eventually, a Selenium MOF (C18MgO25Se11Sn20Zn5) was converged on. Through analysis of predictions & literature, the converged MOF was shown to be more effective & more synthetically accessible than existing MOFs, showing the model had an understanding of effective electrocatalytic structures in the material space. This novel network can be implemented for other gas separations and catalysis applications that have limited training accessible datasets.