소재 인공지능 플랫폼 연구실

In particular, our research spans machine learning and generative models for materials design, autonomous AI systems for scientific discovery, experimental data–driven modeling, and molecular simulation methods such as density functional theory, molecular dynamics, and Monte Carlo simulations. Through the integration of these approaches, MAPL seeks to build intelligent computational frameworks that bridge data, theory, and experimentation to accelerate next-generation materials discovery. We develop machine learning methods to understand and design organic molecules and inoragnic materials. Our research focuses on learning structure–property relationships from large chemical and materials datasets using modern AI architectures such as graph neural networks, transformer-based models, and emerging foundation models for chemistry. These approaches enable the representation of complex molecular and materials structures and allow models to capture subtle chemical interactions that determine functional properties. Welcome to the Material AI Platform Laboratory (MAPL). Our research focuses on developing artificial intelligence and computational methods to accelerate the discovery and design of molecules and materials. By combining machine learning, data-driven approaches, and molecular simulations, we aim to understand complex chemical systems and enable the rational design of functional materials. At MAPL, we are particularly interested in machine learning for materials prediction, generative models for inverse materials design, autonomous AI systems for scientific discovery, and data-driven integration of experimental and computational chemistry. Our goal is to build intelligent research frameworks that bridge artificial intelligence, chemical knowledge, and physical simulat