AI/ML for Energy & Semiconductor Materials
AI/ML for Energy & Semiconductor Materials
The discovery of high-performance quantum materials is critical for advancing sustainable energy systems and next-generation semiconductor technologies. This work presents an integrated materials discovery framework that combines density functional theory (DFT), high-throughput screening, and artificial intelligence/machine learning (AI/ML) to efficiently identify promising candidates across diverse applications, including batteries, fuel cells, quantum devices, and semiconductor systems.
The approach enables systematic exploration of complex materials spaces, with a particular focus on low-dimensional structures. By integrating first-principles modeling with data-driven prediction, the framework accelerates the evaluation of key properties—such as catalytic activity, electronic structure, and stability—thereby significantly reducing experimental effort.
The project establishes a comprehensive ecosystem comprising a curated library of candidate materials, open-access datasets, and predictive machine learning models. Together, these components define robust design principles for targeted materials innovation.
This integrated platform provides a scalable pathway for rapid materials discovery, supporting the development of efficient energy conversion technologies and advanced semiconductor devices.
#DFT #HighThroughput #AI #MachineLearning #QuantumMaterials #Semiconductors #EnergyMaterials #MaterialsDiscovery
Selected Publications
1.Nguyet N. T. Pham†, So-Yeon Song†, Sae-In Suh, Jaemin Choi, Yong-Yoon Ahn, Kitae Kim, Yudong Xue*,Seung-Geol Lee,*, Jaesang Lee,*.Unveiling the Unforeseen Role of Manganese Constituent in Creating a Carbon-based Composite as a High-Efficiency Persulfate Activator: Catalyzing Carbon Phase Graphitization and Promoting Persulfate Binding Affinity. Applied Catalysis B: Environment and Energy 378 (2025): 125598
2.Tan Phat Pham†, Minh Tam Le†, Minh Dang Le†, Hoang Anh Nguyen, Hengquan Guo, Seung Goel Lee, Hsueh-Shih Chen, Nguyet N. T. Pham*. Single – atom Fe/N-embedded Graphdiyne as Catalysts for Hydrogen Evolution Reaction: A DFT Approach. International Journal of Hydrogen Energy 130(2025): 402-410.