ProgramMaster Logo
Conference Tools for 2018 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 2018 TMS Annual Meeting & Exhibition
Symposium Computational Materials Discovery and Optimization
Presentation Title Machine Learning for Materials
Author(s) Matthias Rupp
On-Site Speaker (Planned) Matthias Rupp
Abstract Scope Computational discovery and optimization of novel materials requires accurate treatment on the atomic scale. While numerical approximations to the electronic structure problem accommodate this, their applicability is severely limited by their high computational cost. In high-throughput settings, machine learning can reduce these costs significantly by interpolating between reference calculations. For this, a numerical representation of atomistic systems that supports interpolation is crucial. Using our recently introduced many-body tensor representation, we demonstrate empirical evidence for predictions of ab initio formation enthalpies with errors in the single digit eV/atom range on benchmark datasets of crystal structures, as well as application to phase diagrams of Pt-group / transition-metal binary systems.
Proceedings Inclusion? Planned: Supplemental Proceedings volume

OTHER PAPERS PLANNED FOR THIS SYMPOSIUM

A Combined Experimental-computational Approach to Determining Nanoscale Structures
A Materials-informatics Approach for Finding New Hard-magnetic Phases
Computational Design of Fatigue-resistant NiTi-based Shape Memory Alloys
Computational Screening of Novel Two-dimensional Topological Insulators and Layer-dependent properties
Data-driven Discovery of Photocathodes for CO2 Reduction
Design Concepts of Optimized MRI Magnet by COMSOL Multiphysics Simulation
Determination of Thermal Transport in Solids and Liquids by Non-equilibrium Molecular Dynamics Simulations
Dual Band Metamaterial Perfect Absorber Based on Mie Resonances
Economic Analysis of National Needs for Technology Infrastructure to Support the Materials Genome Initiative
Fabricating Optimized Crystallographic Textures through Heterogeneous Templated Grain Growth
First-principles Calculations on the Multiferroic Properties of Two-dimensional Oxides
First Principle Prediction of Magnetic Topological Phase in Thin Films of Bi2XY4 (X = Mn, Cr; Y = Se, Te)
High-throughput Investigation of the Electronic Properties of 2D and Bulk Materials in the MaterialsWeb Database
Holistic Computational Structure Screening of More than 12 000 Candidates for Solid Lithium-ion Conductor Materials
Improving the Ductility of Boron Carbide from Computational Design
Learning Grain Boundary Properties from Macroscopic and Microscopic Structural Descriptors
Light-metal Complex Hydrides: Computational Structure Prediction and Interaction with Functionalized Nanoporous Hosts
Machine Learning for Materials
Machine Learning for Prediction of Electronic Structures of Multi-component Alloys
Minimal Addition of Cerium for Stability of Critical Phases in Hard Magnetic AlNiCo Alloys: Combined Machine Learning and CALPHAD
Predicting Ferroelectric Properties from Microstructures with Deep Learning
Quantum-accurate Force Fields from Machine Learning of Large Materials Data
Reentrant Melting of Sodium, Magnesium and Aluminum and Possible Universal Trend
Search for Rare-Earth Free Permanent Magnets in Fe and Co Based Compounds by Adaptive Genetic Algorithm
Software Tools for High-throughput Materials Data Generation and Data Mining
Structure-property Linkages for Porous Membranes Using the Materials Knowledge Systems Framework
Tailoring Properties in Multi-component Alloys through Heuristic Optimization
The Use of Cluster Expansions to Predict the Structure and Properties of Catalysts

Questions about ProgramMaster? Contact programming@programmaster.org