Mr. Ning Wang is a Master’s student in Materials Physics and Chemistry at Peking University, Shenzhen Graduate School. His research focuses on AI-driven advancements in materials science, including machine learning applications in molecular simulations and atomic interaction modeling. He has conducted research at the Matter Lab, University of Toronto, and has multiple publications in computational materials science. His work includes the development of the Egsmole model for molecular orbital learning, machine learning-accelerated crystal growth simulations, and AI-driven material discovery tools. He has received several academic awards and actively contributes to open-source projects in computational chemistry.

Profile

Scopus

Early Academic Pursuits 🎓

Ning Wang’s academic journey began with a strong foundation in materials science and engineering. His undergraduate studies at Northeastern University (2018–2022) were marked by excellence, earning him prestigious awards such as the National Scholarship (2020) and the First-Class University Scholarship. His early exposure to materials research set the stage for his specialization in computational materials science and AI-driven simulations. His research at the Key Lab of Electromagnetic Processing of Materials, where he investigated 5A90 Al-Li alloys, demonstrated his keen analytical skills and commitment to advancing materials science.

Building on this foundation, he pursued a Master’s degree in Materials Physics and Chemistry at Peking University, Shenzhen Graduate School. His summer research stint at the Matter Lab, University of Toronto (2024), under Prof. Alan Aspuru-Guzik, further refined his expertise in AI applications for materials science. His dedication to the field was evident in his research on molecular orbital learning using machine learning, where he introduced groundbreaking methodologies for enhanced computational simulations.

Professional Endeavors 🏗️

Ning Wang’s professional trajectory has been characterized by a blend of theoretical research and practical application. His work at Peking University’s Pan Group focused on machine learning-accelerated simulations of silver single crystal growth. He developed a robust dataset comprising over 70,000 data points using density functional theory (DFT) calculations and trained machine learning models to predict material behaviors accurately.

Additionally, his involvement with DP Technology in 2023 saw him enhancing the DeepPot model with Transformer-M architecture, achieving significant improvements in energy prediction. His participation in the AI4S Cup further demonstrated his ability to apply AI-driven techniques to real-world material challenges, such as predicting attributes of OLED materials.

Contributions and Research Focus 🔬

Ning Wang’s research is at the intersection of artificial intelligence, computational chemistry, and materials science. His key contributions include:

• Egsmole Model: A novel equivariant graph neural network designed for molecular orbital learning, ensuring symmetry adherence in molecular simulations.
• GDGen Methodology & Pygdgen: A gradient descent-based approach for generating optimized atomic configurations, significantly improving computational simulations.
• Machine Learning-Accelerated Crystal Growth: Developing AI-driven force fields to predict and optimize silver single crystal growth, bridging experimental and theoretical insights.
• DeepPot Enhancement: Integrating Transformer-M architecture to improve atomic interaction modeling, reducing prediction errors and enhancing computational efficiency.
• XMaterial Plugin: Connecting ChatGPT with the Materials Project database, enabling seamless AI-driven material searches without requiring coding expertise.

His ability to merge AI with materials science has resulted in impactful publications, including works in the Journal of Alloys and Compounds and Computer Physics Communications. His research papers focus on novel AI methodologies for predicting molecular properties, optimizing atomic interactions, and accelerating material discovery.

Accolades and Recognition 🏆

Ning Wang’s contributions have earned him significant recognition in the scientific community:

• National Scholarship (2020): Awarded to the top 1% of students, recognizing academic excellence.
• First-Class University Scholarship (2020): Honoring outstanding research contributions during his undergraduate studies.
• 3rd Prize in DP Technology Hackathon (2023): Acknowledging his innovative approach to enhancing DeepPot models with AI.
• Acceptance at Prestigious Conferences: His research on AI-driven atomic interactions and molecular simulations has been presented at the International Conference on Electronic Information Engineering and Computer Science.
• Publication in High-Impact Journals: His papers in Journal of Alloys and Compounds and Computer Physics Communications highlight his thought leadership in AI-driven materials research.

Publishing Top Notes

Journal: Nano Energy

Year:  2025

Journal: Nanomaterials

Year: 2024

Journal: Construction and Building Materials

Year: 2024