Program


Conference Tracks

Track 1: Multiscale Materials and Engineered Systems

Description TBD

Mini-Symposium 1-1: Machine Learning for Material Characterization and Design

Organizing Team:

  • Ajit Achuthan, Department of Mechanical & Aerospace Engineering, Clarkson University
  • Natasha Banerjee, Department of Computer Science, Clarkson University
  • Sean Banerjee, Department of Computer Science, Clarkson University
  • John G. Michopoulos, Naval Research Laboratory
  • Amit Bagchi, Naval Research Laboratory
  • Steve M. Arnold, NASA Glenn

With the recent advancements in Additive Manufacturing (AM) technologies, tailoring a material’s microstructure to obtain superior mechanical properties is no longer a distant dream. Studies to develop materials with hierarchical microstructures, compositional gradients, and high entropy alloying have picked up momentum all over the world. Consequently, the future of part design is poised for a paradigm shift: manufacturing processes, geometric considerations, and open-ended material domains tightly integrated to form a complex, but rich design space with abundant solutions. A major challenge to the realization of this promise is the lack of a thorough understanding of the material deformation mechanism at the microstructural length scale. This understanding is critical to the development of rigorous mathematical models for the accurate prediction of material behavior and the invention of methods to manipulate these deformation mechanisms desirably. However, at the microstructural length scale, most materials are highly heterogeneous with many microstructural features. Although the presence of these features that have individual and collective influence on local deformation potentially provide ample options to tailor local properties, the severe heterogeneity they introduce makes gaining the fundamental understanding of local deformation an arduous endeavor. Unsurprisingly, Machine Learning that deals with large, complex data is emerging as a promising tool to address many of these challenges.

In this track, we invite papers that discuss research pertaining to the development and utilization of Machine Learning principles and tools to gain fundamental understanding of material deformation at small length scales, develop mathematical prediction models, and invent new design paradigms. Contributions on supervised learning methods for predicting structure property relationships, developing Hamiltonians, predicting crystal structures and other microstructural morphologies, classification of microstructures and descriptors identification as well as unsupervised learning methods for compositional analysis spreads from combinatorial experiments, micrograph analysis, data noise reduction or data post-processing are example topics for this track.

Track 2: Multi-Modal Generation of Big Data for Machine Learning

Description TBD

Track 3: Scientific and Engineering Digital Twins

Description TBD

Track 4: Advanced Manufacturing and Design Optimization

Description TBD

Track 5: Biomedical Systems, Medical Devices, and Mechanistic Machine Learning Enhanced Diagnostics

Description TBD

Track 6: Reduced-order Modeling for Fluids, Solids, and Structures

Description TBD

Track 7: Injection of Mechanistic Machine Learning on Co-Design in High-Performance Computing

Description TBD

Track 8: Geosystem, Geostatistics, and Petroleum Engineering

Description TBD

Track 9: Data Centric Earthquake Engineering and Performance-based Design

Track Chairs: Joel Conte (UC San Diego), Gilberto Mosqueda (UC San Diego), and Michael Todd (UC San Diego)

Description TBD

Track 10: Infrastructure and Cyberinfrastructure Systems

Track Chairs: Joel Conte (UC San Diego), Gilberto Mosqueda (UC San Diego), and Michael Todd (UC San Diego)

Description TBD

Track 11: Technology Transfer for Innovative Scientific and Engineering Applications

Description TBD

Track 12: Mechanistic Machine Learning for the Ecosystem: Environment, Smart City, and Healthcare

Description TBD

Track 13: Education, Outreach, and Funding Opportunities

Description TBD

UC San Diego, Department of Structural Engineering, 9500 Gilman Dr MC 0085, La Jolla, CA 92093-0085
Copyright (C) Regents of the University of CaliforniaAll Rights Reserved