Organic semiconductors have gained attention recently due to their potential applications in flexible, low-cost, lightweight electronics and solar cells. However, developing new organic semiconductors with improved performance remains a significant challenge due to the vast space of possible molecular structures. Furthermore, the high cost and time-consuming nature of experimental synthesis and characterization hinder the rapid discovery of new materials. To overcome these challenges, this dissertation presents a novel data-driven approach. The primary focus of this work is the development of data-driven tools, namely machine learning models, to predict critical electronic and structural properties of molecular organic semiconductors. These models are trained on a large dataset of quantum chemical calculations, enabling the efficient screening of thousands of candidate molecules. In addition to developing the predictive models, this work includes creating a user-friendly web platform. The platform enables scientists and engineers to access the models and rapidly explore the chemical space to design new materials. The platform also includes visualization and analysis tools to guide the design process and facilitate collaboration between researchers. The data-driven tools developed in this research have the potential to significantly accelerate the discovery and development of new molecular organic semiconductors, paving the way for the next generation of flexible electronics and renewable energy technologies. Overall, this dissertation offers a practical and innovative framework for designing organic semiconductors, leveraging data-driven approaches to overcome the challenges of the traditional experimental trial-and-error process.
Speaker(s) / Presenter(s):
Type of Event (for grouping events):