CarbNN: A Novel Active Transfer Learning Neural Network To Build De Novo Metal Organic Frameworks (MOFs) for Carbon Capture

TL;DR

This paper introduces CarbNN, a transfer learning neural network that designs cost-effective, efficient MOFs for CO2 capture and electrocatalysis, addressing climate change by improving materials used in carbon reduction.

Contribution

A novel active transfer learning neural network for designing MOFs with limited data, demonstrating effective prediction and synthesis of new materials for carbon capture.

Findings

Converged on a Selenium MOF with improved effectiveness.

Model outperforms existing MOFs in predicted efficiency.

Demonstrated applicability to other gas separation tasks.

Abstract

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.