Inverse Design of Potential Singlet Fission Molecules using a Transfer Learning Based Approach
This work addresses the need for more efficient solar cell materials for optoelectronic applications, but it is incremental as it applies an existing method to a new domain.
The researchers tackled the limited availability of singlet fission molecules by using a transfer learning approach to predict new candidates, leveraging a larger ChEMBL dataset to overcome small dataset constraints in material science.
Singlet fission has emerged as one of the most exciting phenomena known to improve the efficiencies of different types of solar cells and has found uses in diverse optoelectronic applications. The range of available singlet fission molecules is, however, limited as to undergo singlet fission, molecules have to satisfy certain energy conditions. Recent advances in material search using inverse design has enabled the prediction of materials for a wide range of applications and has emerged as one of the most efficient methods in the discovery of suitable materials. It is particularly helpful in manipulating large datasets, uncovering hidden information from the molecular dataset and generating new structures. However, we seldom encounter large datasets in structure prediction problems in material science. In our work, we put forward inverse design of possible singlet fission molecules using a transfer learning based approach where we make use of a much larger ChEMBL dataset of structurally similar molecules to transfer the learned characteristics to the singlet fission dataset.