Conference Tools for MS&T24: Materials Science & Technology

Help

About this Abstract
Meeting	MS&T24: Materials Science & Technology
Symposium	Frontiers of Machine Learning on Materials Discovery
Presentation Title	Physics-Aware Recurrent Convolutional Neural Networks for Modeling Hotspot Formation and Growth in Energetic Materials
Author(s)	Stephen Baek
On-Site Speaker (Planned)	Stephen Baek
Abstract Scope	In this presentation, our recent work on physics-aware recurrent convolutional neural networks (PARC) will be discussed. PARC is a deep neural network that embodies a network architecture mirroring how traditional numerical simulation packages solve physics-governing differential equations. PARC was found to be capable of predicting the intricate, extreme thermomechanics of energetic materials such as explosives and propellants, with high resolution of details and accuracy comparable to those of traditional direct numerical solvers. Yet, PARC presented multiple orders of magnitude acceleration in computing speed from hours on high-performance clusters for traditional solvers to a few seconds on a laptop for PARC. This presentation will delve into the innovations and potential that PARC presents to the energetic materials community, as well as its scientific contribution in comparison to other existing physics-informed machine learning models. Current limitations and research opportunities of PARC for EM research will also be discussed.

OTHER PAPERS PLANNED FOR THIS SYMPOSIUM

A Hierarchical Machine Learning Scheme to Identify Promising New Scintillators

abICS Framework for ab initio Statistical Thermodynamics of Complex Oxides Accelerated by Machine Learning

Accelerating Defect Predictions in Semiconductors Using Crystal Graphs

Accelerating Electron Microscopy and Experimentation through Acceptance of ML/AI

Autonomous Materials Synthesis System for Inorganic Thin Films Utilizing AI and Robotics

Bayesian optimization of CG topologies: Applications to common polymers

Data-Driven Accelerated Discovery of Novel Battery Materials

Delocalized, Asynchronous, Closed-Loop Discovery of Organic Laser Emitters

Exploring New Frontiers in Inverse Materials Design through Graph Neural Networks and Large Language Models

Inverse Design of Quantum Materials by High-Throughput Calculations and Optimization Techniques

Machine-Learning-Aided Discovery of Metal-Organic Frameworks for Water Harvesting

Machine Learning in Chemistry: Reactive Force Fields and Beyond

Machine Learning Materials Properties with Accurate Predictions, Uncertainty Estimates, Domain Guidance, and Persistent Online Accessibility

MAXIMA: A High-Throughput Instrument for XRD and XRF Characterization of Materials

Physics-Aware Recurrent Convolutional Neural Networks for Modeling Hotspot Formation and Growth in Energetic Materials

Physics-Informed Machine Learning of Thermodynamic Properties

Physics-Infused Causal and Hypothesis-Driven AI for Advanced Functional Materials

Reinforcement Learning for Materials Science: Algorithms, Challenges and Applications to Improve Understanding of System Dynamics

Role of Domain Knowledge Injection in Data-Driven Methods Towards Accelerating Material Discovery

The Space of Phase Diagrams: Visualization Strategies for Advanced Materials

Towards Automatic Alloy Design via Large Language Model Powered Multi-Agent Collaborations

Using UNET Architecture for Microstructural Image Analysis in Hypoeutectoid Steel

Variable Selection for Small-Scale Chemical Experimental Data Based on Bayesian Inference

Questions about ProgramMaster? Contact programming@programmaster.org