We are excited to announce the 2nd Conference on Artificial Intelligence in Materials Science and Engineering (AI MSE 2025), an interdisciplinary event that brings together leading researchers and industry experts to explore the integration of artificial intelligence (AI), deep learning, and machine learning in the field of materials science.

Conference Highlights:

• Innovative Research Presentations: Discover the latest advancements in AI applications within materials science and engineering.
• Expert Panels: Engage with thought leaders discussing current trends and future directions.
• Networking Opportunities: Connect with professionals and peers to foster collaborations.

Topics:

• A: Microstructure characterization and reconstruction (image-based methods)
  Focuses on using image-based techniques to analyze and rebuild the microstructure of materials.
• B: Predicting properties/microstructures
  Involves using AI to forecast material properties and structures based on their microstructural characteristics.
  • B.01: Machine Learning in atomistic simulations
    Discusses the application of machine learning to simulate and analyze material behavior at the atomic level.
  • B.02: Machine Learning in continuum simulations
    Covers the integration of machine learning into continuum mechanics simulations for material science.
• C: Materials Discovery
  Explores how AI can accelerate the discovery of new materials with desired properties.
  • C.01: Active Learning
    Examines adaptive machine learning techniques where the algorithm actively queries information to learn more effectively.
• D: Emerging technologies
  Focuses on the introduction and potential impact of nascent data science technologies in material science and engineering.
  • D.01: Neurosymbolic approaches
    Combines symbolic reasoning with neural networks to enhance decision-making and problem-solving in material science.
  • D.02: Natural Language Processing and Large Language Models
    Involves the use of AI to process and analyze human language within the context of material science.
  • D.03: Physically informed neural networks
    Discusses neural networks that incorporate physical laws into their architecture, improving prediction accuracy for scientific problems.
  • D.04: Neural ODEs
    Focuses on the use of neural ordinary differential equations to model continuous-time dynamics in material processes.

Emerging Technologies Track:

We are also introducing a special track dedicated to emerging technologies. Submissions are encouraged on innovative data science techniques that, while not yet widely adopted in materials science and engineering, hold promise for future impact.