Machine Learning Approach on Degree-Sum Based Topological Indices of Bottom-Up-Synthesized Graphene Nanoribbons

Graphene nanoribbons (GNRs) have drawn a lot of interest because of their tunable electronic characteristics, which make them interesting materials for optoelectronic and nanoelectronic applications. In this study, we use a machine learning (ML) approach to examine the topological indices (TIs) of bottom-up synthesized GNRs that are based on neighborhood degree sums. Key physicochemical and electrical features of GNRs can be predicted using these indices, which capture crucial structural characteristics of molecular graphs, as descriptors. Our findings show that ML models may accurately forecast GNR characteristics based on TIs, providing a quick and dependable substitute for conventional computational chemistry techniques. This work contributes to the development of nanomaterials studies by illustrating the potential of ML-driven methods in the logical design and property optimization of GNRs.