ProgramMaster Logo
Conference Tools for MS&T21: Materials Science & Technology
Login
Register as a New User
Help
Submit An Abstract
Propose A Symposium
Presenter/Author Tools
Organizer/Editor Tools
About this Abstract
Meeting MS&T21: Materials Science & Technology
Symposium Ceramics and Glasses Modeling by Simulations and Machine Learning
Presentation Title Fusing Experimental and Simulation Datasets in Machine Learning for Predicting Glass Properties
Author(s) Mathieu Bauchy
On-Site Speaker (Planned) Mathieu Bauchy
Abstract Scope Machine learning models require as a prerequisite the existence of data that are available, complete, consistent, accurate, and numerous. Although experimental data are usually accurate, they are often not numerous enough to enable meaningful deep learning approaches. As an alternative path, synthetic data generated by high-throughput molecular dynamics simulations can offer large, consistent datasets. However, their limited accuracy does not always yield a perfect agreement with experiments—which makes it challenging to directly combine experimental and simulation data within universal, unifying datasets. Here, we present a new “data fusion” approach that can simultaneously leverage the advantages of experimental and simulation data—wherein experimental and simulation data mutually inform, augment, and advance each other. We demonstrate that our fused model systematically outperforms models that are solely trained based on experimental (or simulation) data.
Proceedings Inclusion? Undecided

OTHER PAPERS PLANNED FOR THIS SYMPOSIUM

A Machine-learning Based Hierarchical Framework to Discover Novel Scintillator Chemistries
Bayesian Optimization of Silicon Nitride Empirical Potentials
Ceramics from Polymers –– Results of Ab Initio Molecular Dynamic Simulations
Deciphering the Viscosity of Glass Materials with Machine Learning
Decomposing the Strength of Hydrated Cement Compositions by Machine Learning
Development of a Reactive Force Field (ReaxFF) for Simulation of Polymer-derived Ceramics
Development of a Transferable Inter-atomic Potential for Boroaluminosilicate Glasses
Effect of Polydispersity on the Fracture Properties of Calcium–Silicate–Hydrate Gel
Elucidating Compositional Governance of Optical Properties of Oxide Glasses Using Interpretable Machine Learning
Fusing Experimental and Simulation Datasets in Machine Learning for Predicting Glass Properties
Graph ODE for Learning Dynamic Systems
Impact of Irradiation on the Properties of Gel Layer Formed After Aqueous Corrosion of Borosilicate Glasses
Kinetic Monte Carlo Simulation of Glasses Aided by Machine Learning
Looking for Order in Disorder: Topological Data Analysis of Glass Structure
Machine Learning as a Tool to Accelerate the Design of Nuclear Waste Glasses with Enhanced Sulfur Loadings
Modeling Polaron Hopping in Ternary Spinel Oxides
Now On-Demand Only: Information Extraction Pipeline for Glasses: An NLP Based Approach
P1-3: Molecular Dynamic Characteristic Temperatures for Predicting Metallic Glass Forming Ability
The Energy Landscape Governs Ductility in Disordered Materials
Toward Revealing Full Atomic Picture of Nanoindentation Deformation Mechanisms in Li2O-2SiO2 Glass-ceramics

Questions about ProgramMaster? Contact programming@programmaster.org