Conference Logo ProgramMaster Logo
Conference Tools for 2026 TMS Annual Meeting & Exhibition
Login
Register as a New User
Help
Submit An Abstract
Propose A Symposium
Presenter/Author Tools
Organizer/Editor Tools

About this Abstract

Meeting 2026 TMS Annual Meeting & Exhibition
Symposium Accelerated Discovery and Insertion of Next Generation Structural Materials
Presentation Title Leveraging Domain Knowledge for Optimal Initialization in Materials Optimization Frameworks
Author(s) Trevor Hastings, James Paramore, Brady Butler, Raymundo Arróyave
On-Site Speaker (Planned) Trevor Hastings
Abstract Scope Machine learning-based optimization strategies have emerged as an effective means to accelerate the discovery of new materials by efficiently exploring complex and high-dimensional design spaces. However, the success of optimization frameworks greatly depends on how well the campaign is initialized---the selection of seed data points from which the optimization starts. In this study, we focus on improving these initial datasets by incorporating materials science expertise into the selection process. Using Bayesian Optimization as a prototypical framework with real-world design criteria, we demonstrate that incorporating domain knowledge leads to more diverse initial datasets. These enhanced starting points significantly improve the efficiency of subsequent optimization efforts. We also introduce clear metrics for assessing the quality and diversity of initial datasets, providing a straightforward way to compare different initialization strategies. This approach acts as a widely applicable enhancement to various materials discovery scenarios.
Proceedings Inclusion? Planned:
Keywords Modeling and Simulation, Computational Materials Science & Engineering, Machine Learning

OTHER PAPERS PLANNED FOR THIS SYMPOSIUM

A Combinatorial Approach for the Development of Ternary Alloys
Accelerated Discovery of Additively Manufacturable Al-Zr-Er-Ni Alloys with Enhanced Strength and Ductility Via CALPHAD-Based ICME Technique
Accelerated Mapping of Metallurgical Impact Bonding of GRX 810 Nickel ODS AM Alloys Using Laser Induced Particle Impact Testing (LIPIT)
Accelerating W-Alloy Design with Physics-Guided Machine Learning
AlloyBot: An Automatic Arc-Melting System for High-Throughput Alloy Synthesis
Automated High-Throughput Characterization of Structural Materials for Extreme Environments
CALPHAD Based Screening for Rapid Training of Alloy Design Models
Coupled Design and Characterization Tools to Enable Components with Spatially Varying Materials and Properties
DARPA METALS: Introducing New Material Test Methods and Design Optimization Paradigms for Future Multi-Material Structures
E-44: Evaluating Elemental Powder-Based Direct Energy Deposition for High-Throughput Synthesis of Alloys
Generative Design of Compositionally Graded Turbine Rotors
Hydrogen Embrittlement Behavior of Ni-Based Alloy Fabricated by Laser-Powder Bed Fusion
Leveraging Domain Knowledge for Optimal Initialization in Materials Optimization Frameworks
Machine-Learning Prediction of Yield Strength for W-Ta-Nb Alloy from Room Temperature to 2000°C
Machine Learning Domain Knowledge-Based Design of Alloys with High Strength
Microstructural Evolution During Processing and Creep of Re-Free Single Crystal Superalloy ERBO/15
Multimaterial Structures: Materials, Test Methods, Models and Data Enabled Topology Optimized Design
New Insights into the Evolution of Powder Metallurgy (PM) Ni-Based Superalloys During Consolidation and Thermomechanical Processing
Novel Approach to Rapid Material Characterization and Multi-Material Design Optimization
On the Effect of Temperature Cycling and Stress on the Formation of σ-Phase in Single Crystal Superalloys
RADICAL: Rapid Array DImple-Based Co-Design of Gradient MateriaL and Geometry
Rapid and Flexible Design of Alloys Using The Alloy Optimization Software (TAOS)
Rapid Exploration of Al-Ti-Fe-Si Alloys Via Automated High-Throughput Laboratory X-Ray Diffraction (XRD) and Fluorescence Analysis (XRF)
Simultaneous Design and Discovery of Functionally-Graded Alloys, Supported by Material Informatics and Rapid Testing
SMART: Novel Material Library Synthesis to Accelerate Structural Alloy Discovery
Success and Challenges with Qualifying 6061-RAM2 and 7050-RAM2 Aluminum Alloys for LBPF Additive Manufacturing
"Old-Fashioned" Cast & Wrought Ni-Base Superalloys - Some Remaining Challenges for Alloy and Process Design

Questions about ProgramMaster? Contact programming@programmaster.org | TMS Privacy Policy | Accessibility Statement