Research Interests

My research interests lie in the areas of machine learning, deep learning, with a strong focus on their applications in cross-disciplines, such as materials informatics, recommender systems, tourism and hospitality. Recently, my work focused on using state-of-the-art deep neural network models (such as generative adversarial networks, graph neural networks, transformer language models, etc) combined with density functional theory (DFT) simulation to generate crystal structures or predict their properties. This interdisciplinary approach has shown great promise in advancing our understanding of materials and holds significant potential for real-world applications.

Research Projects

Deep learning based material crystal structure prediction

Artificial intelligence and deep learning are revolutionizing all scientific disciplines with their superior capability to learn to detect patterns from large amounts of data and build predictive models from data without relying upon prior theory or understanding. My research focuses on using these techniques to uncover relationships between structures and properties in materials. By utilizing deep learning algorithms, I designed several models to predict crystal structures and discover novel 2D materials, as well as predict material properties. Considering that the number of inorganic materials discovered so far (~250,000) by humanity is only a tiny portion of the almost infinite chemical design space, our AI based data-driven computational materials discovery has the potential to transform the conventional trial-and-error approaches in materials discovery.

Applied ML/DL in tourism and hospitality

Machine learning and deep learning technolgies are increasingly being utilized in the tourism and hospitality industry to enhance various aspects of the customer experience, operational efficiency, and decision-making processes. These technologies leverage data-driven insights to personalize services, optimize operations, and improve overall satisfaction for both travelers and businesses in the sector. Recently, we are focuing on develop a user-friendly website that integrates advanced and powerful machine learning algorithms to anticipating employee turnover, while offering intuitive and informative data visualization features.