This talk describes opportunities for students, companies and academics to work in a Materials Informatics Skunkworks, presently located at the University of Wisconsin - Madison. For more information please contact Dane Morgan at ddmorgan@wisc.edu.
This document summarizes work using high-throughput computing on the Open Science Grid to generate large materials databases. Key points:
- The researchers used over 2.6 million CPU hours on the Open Science Grid to run thousands of ab initio calculations for materials properties like diffusion coefficients.
- This enabled the creation of the world's largest database of diffusion data from a single research group, with properties for over 350 material systems.
- The databases are publicly available online and help discover new scientific insights not possible from smaller datasets.
- The researchers are now using the same high-throughput approach on the Open Science Grid to calculate other materials properties at scale, like excess formation volumes in alloys.
Strain Effects on Defects and Diffusion in Perovskites
Dane Morgan, Tam Mayeshiba, Milind Gadre, Anh Ngo
University of Wisconsin, Madison
Yueh-Lin Lee, Yang-Shao Horn
Massachusetts Institute of Technology
Stuart Adler
University of Washington, Seattle
October 6, 2014
MMM
Berkeley, California
Presentation on machine learning and materials science at Computing in Engineering Forum 2018, Machine Ground Interaction Consortium (MaGIC) 2018, Wisconsin, Madison, December 4, 2018
Automated Generation of High-accuracy Interatomic Potentials Using Quantum Dataaimsnist
Sandia National Laboratories is developing SNAP (Spectral Neighbor Analysis Potential) potentials for molecular dynamics simulations. SNAP potentials are fitted to quantum mechanical data using bispectrum components that describe the local atomic environments. SNAP potentials have been shown to accurately reproduce properties of tantalum, including liquid structure and screw dislocation behavior not included in the training data. Work is ongoing to develop multi-element SNAP potentials, including for tungsten-beryllium alloys relevant to modeling plasma-surface interactions in nuclear fusion reactors.
Data Mining to Discovery for Inorganic Solids: Software Tools and Applicationsaimsnist
This document summarizes four projects from Lawrence Berkeley National Laboratory related to using artificial intelligence and data mining for materials science:
1) Interpretable descriptors of crystal structure that describe local environments as fingerprints to distinguish structures.
2) The matminer toolkit which connects materials data to machine learning algorithms and data visualization.
3) The atomate and Rocketsled software for running high-throughput density functional theory calculations and building a computational optimizer.
4) A text mining approach to label the content of materials science abstracts to build a revised materials search engine and identify related materials.
Polymer Genome: An Informatics Platform for Polymer Dielectrics Discovery and...aimsnist
The Ramprasad Research Group at Georgia Tech uses machine learning and high-throughput computations to screen the chemical space of polymers for materials with applications in energy storage. They have identified several high-performing polymer dielectrics with higher dielectric constants and energy densities than the current standard. The group is working to further improve materials by incorporating metals and exploring morphological complexity with the goal of autonomous polymer design.
This document summarizes research on developing autonomous experimental systems for materials characterization and phase diagram mapping. Key points discussed include:
- Using active clustering algorithms and Gaussian process classification to analyze x-ray diffraction data and autonomously map phase diagrams without human labeling or supervision.
- Developing infrastructure for autonomous experiments involving autonomous data analysis, selection of new experimental conditions based on analysis, and control of experimental equipment to acquire new data.
- Demonstrating this approach on systems like VNbO2 and VWO2 to map phase diagrams and metal-insulator transition temperatures as a function of composition and temperature.
This document summarizes work using high-throughput computing on the Open Science Grid to generate large materials databases. Key points:
- The researchers used over 2.6 million CPU hours on the Open Science Grid to run thousands of ab initio calculations for materials properties like diffusion coefficients.
- This enabled the creation of the world's largest database of diffusion data from a single research group, with properties for over 350 material systems.
- The databases are publicly available online and help discover new scientific insights not possible from smaller datasets.
- The researchers are now using the same high-throughput approach on the Open Science Grid to calculate other materials properties at scale, like excess formation volumes in alloys.
Strain Effects on Defects and Diffusion in Perovskites
Dane Morgan, Tam Mayeshiba, Milind Gadre, Anh Ngo
University of Wisconsin, Madison
Yueh-Lin Lee, Yang-Shao Horn
Massachusetts Institute of Technology
Stuart Adler
University of Washington, Seattle
October 6, 2014
MMM
Berkeley, California
Presentation on machine learning and materials science at Computing in Engineering Forum 2018, Machine Ground Interaction Consortium (MaGIC) 2018, Wisconsin, Madison, December 4, 2018
Automated Generation of High-accuracy Interatomic Potentials Using Quantum Dataaimsnist
Sandia National Laboratories is developing SNAP (Spectral Neighbor Analysis Potential) potentials for molecular dynamics simulations. SNAP potentials are fitted to quantum mechanical data using bispectrum components that describe the local atomic environments. SNAP potentials have been shown to accurately reproduce properties of tantalum, including liquid structure and screw dislocation behavior not included in the training data. Work is ongoing to develop multi-element SNAP potentials, including for tungsten-beryllium alloys relevant to modeling plasma-surface interactions in nuclear fusion reactors.
Data Mining to Discovery for Inorganic Solids: Software Tools and Applicationsaimsnist
This document summarizes four projects from Lawrence Berkeley National Laboratory related to using artificial intelligence and data mining for materials science:
1) Interpretable descriptors of crystal structure that describe local environments as fingerprints to distinguish structures.
2) The matminer toolkit which connects materials data to machine learning algorithms and data visualization.
3) The atomate and Rocketsled software for running high-throughput density functional theory calculations and building a computational optimizer.
4) A text mining approach to label the content of materials science abstracts to build a revised materials search engine and identify related materials.
Polymer Genome: An Informatics Platform for Polymer Dielectrics Discovery and...aimsnist
The Ramprasad Research Group at Georgia Tech uses machine learning and high-throughput computations to screen the chemical space of polymers for materials with applications in energy storage. They have identified several high-performing polymer dielectrics with higher dielectric constants and energy densities than the current standard. The group is working to further improve materials by incorporating metals and exploring morphological complexity with the goal of autonomous polymer design.
This document summarizes research on developing autonomous experimental systems for materials characterization and phase diagram mapping. Key points discussed include:
- Using active clustering algorithms and Gaussian process classification to analyze x-ray diffraction data and autonomously map phase diagrams without human labeling or supervision.
- Developing infrastructure for autonomous experiments involving autonomous data analysis, selection of new experimental conditions based on analysis, and control of experimental equipment to acquire new data.
- Demonstrating this approach on systems like VNbO2 and VWO2 to map phase diagrams and metal-insulator transition temperatures as a function of composition and temperature.
Combinatorial Experimentation and Machine Learning for Materials Discoveryaimsnist
This document describes how machine learning and active learning can be used to enhance high-throughput combinatorial experimentation for materials discovery. Specifically, it discusses how active learning algorithms can direct experiments to optimally query samples and map out phase diagrams with fewer total measurements. An example is given of using these methods to autonomously map the composition-temperature phase diagram of tungsten-doped VO2 with only 10% of samples requiring direct measurement. The document concludes that machine learning has the potential to significantly reduce the number of experiments needed in combinatorial screening studies.
Applications of Machine Learning for Materials Discovery at NRELaimsnist
Machine learning and artificial intelligence techniques are being applied at NREL to accelerate materials discovery in several ways:
1) Clustering of experimental XRD patterns allows automated structure determination, replacing slow manual analysis.
2) Neural networks can predict optoelectronic properties of molecules from their structure alone, screening millions of candidates.
3) Models are being developed to predict properties not measured in experiments to augment experimental data.
4) End-to-end deep learning on molecular and crystal structures may predict properties with accuracy approaching computationally expensive DFT simulations.
Predicting local atomic structures from X-ray absorption spectroscopy using t...aimsnist
The document discusses using theory, computation, and machine learning to interpret experimental X-ray absorption spectroscopy data and determine local atomic structures. It presents examples of using density functional theory calculations of X-ray absorption near edge structure (XANES) spectra to benchmark predictions against experiments and develop machine learning models for structure classification. The models are able to classify local structures like tetrahedral, square pyramidal, and octahedral coordination with over 85% accuracy across different materials systems. This approach provides a way to solve the inverse problem of determining structures from spectroscopy measurements in real time.
Smart Metrics for High Performance Material Designaimsnist
This document discusses smart metrics for high-performance material design using density functional theory (DFT), classical force fields (FF), and machine learning (ML). It provides an overview of the JARVIS database and tools containing over 35,000 materials and classical properties calculated using DFT, FF, and ML methods. Metrics discussed include formation energy, exfoliation energy, elastic constants, surface energy, vacancy energy, grain boundary energy, bandgaps, and other electronic and optical properties important for applications like solar cells. ML models are developed to predict these properties with mean absolute errors within chemical accuracy compared to DFT benchmarks.
Failing Fastest: What an Effective HTE and ML Workflow Enables for Functional...aimsnist
This document discusses how high-throughput experimentation (HTE) and machine learning (ML) can accelerate materials discovery for functional metallic glasses (MGs). It describes a round robin experiment between NIST and NREL to synthesize and characterize composition spread samples to test data sharing standards. General trends predicted by ML models often correlate within a given synthesis method but systematic differences can occur between methods. While ML is not a replacement for physics, the combination of HTE and ML can identify promising new materials faster than traditional experimentation alone. Autonomous research platforms may enable an even greater acceleration of the materials discovery process.
Accelerated Materials Discovery & Characterization with Classical, Quantum an...KAMAL CHOUDHARY
This document summarizes Kamal Choudhary's talk on accelerated materials discovery and characterization using classical, quantum, and machine learning approaches. The talk discusses NIST's JARVIS framework which combines different computational approaches and machine learning to discover new materials and characterize their properties. Specifically, JARVIS has been used to evaluate force fields, discover low-dimensional materials, topological materials, efficient solar cell materials, high-performance thermoelectrics, and flexible/negative Poisson materials. Machine learning models have also been developed to predict formation energies and bandgaps of materials.
Machine Learning Platform for Catalyst DesignAnubhav Jain
This document provides an overview of a project to design a machine learning platform for catalyst design. The project aims to (1) design and screen new materials for water purification faster than ever before using materials theory, high-performance computing, and automated experiments, (2) demonstrate commercially viable catalysts for oxyanion reduction within one year, and (3) develop a general materials discovery platform that can discover new materials for many scenarios through leveraging supercomputing and machine learning to virtually screen over 1,000 alloys for their nitrate reduction potential and experimentally testing the most promising candidates.
From Conference Electronic Materials and Applications 2019 (EMA 2019), Abstract # 3065049, EMA-S13-013-2019 Symposium: S13: From Basic Science to Agile Design of Functional Materials: Aligned Computational and Experimental Approaches and Materials Informatics, January 24, 2019
Conducting and Enabling Data-Driven Research Through the Materials ProjectAnubhav Jain
The Materials Project provides a free database of calculated materials properties for over 150,000 materials. It aims to enable data-driven materials research by conducting high-throughput calculations and providing tools for researchers to explore the data. The presentation discusses how the Materials Project has been used to discover new functional materials, including p-type transparent conductors, thermoelectrics, and phosphors, by screening for materials with desirable predicted properties. Engaging the research community through contributions of experimental data and machine learning benchmarking helps add value to the Materials Project platform.
High-throughput discovery of low-dimensional and topologically non-trivial ma...KAMAL CHOUDHARY
This document summarizes research into using density functional theory to discover new low-dimensional and topologically non-trivial materials. Key aspects include screening over 600 2D materials and 30,000 3D bulk materials to identify promising candidates, calculating exfoliation energies to confirm stability of low-dimensional forms, and using a spillage criterion to identify over 1,800 potential topological materials by comparing wavefunctions with and without spin-orbit coupling. Ongoing work focuses on characterizing elemental contributions to topological materials and identifying other classes of topological phases like Weyl and Dirac semimetals.
Automated Machine Learning Applied to Diverse Materials Design ProblemsAnubhav Jain
Automated Machine Learning Applied to Diverse Materials Design Problems
Anubhav Jain presented on developing standardized benchmark datasets and algorithms for automated machine learning in materials science. Matbench provides a diverse set of materials design problems for evaluating ML algorithms, including classification and regression tasks of varying sizes from experiments and DFT. Automatminer is a "black box" ML algorithm that uses genetic algorithms to automatically generate features, select models, and tune hyperparameters on a given dataset, performing comparably to specialized literature methods on small datasets but less well on large datasets. Standardized evaluations can help accelerate progress in automated ML for materials design.
Computational Discovery of Two-Dimensional Materials, Evaluation of Force-Fie...KAMAL CHOUDHARY
JARVIS (Joint Automated Repository for Various Integrated Simulations) is a repository designed to automate materials discovery using classical force-field, density functional theory, machine learning calculations and experiments.
The Force-field section of JARVIS (JARVIS-FF) consists of thousands of automated LAMMPS based force-field calculations on DFT geometries. Some of the properties included in JARVIS-FF are energetics, elastic constants, surface energies, defect formations energies and phonon frequencies of materials.
The Density functional theory section of JARVIS (JARVIS-DFT) consists of thousands of VASP based calculations for 3D-bulk, single layer (2D), nanowire (1D) and molecular (0D) systems. Most of the calculations are carried out with optB88vDW functional. JARVIS-DFT includes materials data such as: energetics, diffraction pattern, radial distribution function, band-structure, density of states, carrier effective mass, temperature and carrier concentration dependent thermoelectric properties, elastic constants and gamma-point phonons.
The Machine-learning section of JARVIS (JARVIS-ML) consists of machine learning prediction tools, trained on JARVIS-DFT data. Some of the ML-predictions focus on energetics, heat of formation, GGA/METAGGA bandgaps, bulk and shear modulus. The ML webpage is visible to NIST employees only right now, but will be available publicly soon.
Software tools, crystal descriptors, and machine learning applied to material...Anubhav Jain
1. The document discusses using density functional theory (DFT) and high-throughput computing to screen large numbers of materials for promising thermoelectric properties.
2. Early high-throughput studies screened tens of thousands of materials for applications like scintillators, topological insulators, and high temperature superconductors, finding candidates with a hit rate of around 1 in 1000.
3. Predictions from high-throughput DFT have been experimentally confirmed for new thermoelectric, battery cathode, and CO2 capture materials. However, accurately predicting all thermoelectric properties like the figure of merit remains challenging.
Database of Topological Materials and Spin-orbit SpillageKAMAL CHOUDHARY
We present the results of a high-throughput, first principles search for topological materials based on identifying materials with band inversion induced by spin-orbit coupling. Out of the currently available 30000 materials in our database, we investigate more than 4507 non-magnetic materials having heavy atoms and low bandgaps. We compute the spillage between the spin-orbit and non-spin-orbit wave functions, resulting in more than 1699 high-spillage candidate materials. We demonstrate that in addition to Z2 topological insulators, this screening method successfully identifies many semimetals and topological crystalline insulators. Our approach is applicable to the investigation of disordered or distorted materials, because it is not based on symmetry considerations, and it can be extended to magnetic materials. After our first screening step, we use Wannier-interpolation to calculate the topological invariants and to search for band crossings in our candidate materials. We discuss some individual example materials, as well as trends throughout our dataset, that is available at JARVIS-DFT website: http://jarvis.nist.gov
Combining density functional theory calculations, supercomputing, and data-dr...Anubhav Jain
Combining density functional theory calculations, supercomputing, and data-driven methods, the speaker aims to understand and design new thermoelectric materials for waste heat recovery. He discusses using high-throughput computations and large databases like the Materials Project to efficiently search for promising thermoelectric materials candidates among thousands of potential compositions. Experimental validation is then needed to confirm computational predictions.
Targeted Band Structure Design and Thermoelectric Materials Discovery Using H...Anubhav Jain
This work was supported by funding from the U.S. Department of Energy and involved collaborations with researchers from Northwestern University, Universite Catholique de Louvain, Dalhousie University, and UC Berkeley/LBNL. Using high-throughput computational methods, over 50,000 compounds were screened to discover new thermoelectric materials, identifying YCuTe2 as a promising candidate with a calculated zT of 0.75. Experimental synthesis and testing achieved a maximum zT of 0.75 for this material. Future work will involve developing more accurate electronic transport models, expanding the materials library through substitutional predictions, and applying machine learning to discover new structure-property relationships.
Software tools for data-driven research and their application to thermoelectr...Anubhav Jain
This document summarizes several software tools for materials data science and their application to thermoelectrics materials discovery. It discusses Atomate for high-throughput calculations, Matminer for materials feature extraction and machine learning, AMSET for electron transport modeling, and integration with the Materials Project database. Example applications are described like using order parameters for structure characterization and a computational screening identifying new thermoelectric materials like YCuTe2.
Data Mining to Discovery for Inorganic Solids: Software Tools and ApplicationsAnubhav Jain
This document summarizes several projects from Anubhav Jain at Lawrence Berkeley National Laboratory related to using artificial intelligence and data mining for materials science. It discusses (1) developing interpretable descriptors of crystal structure based on local environments, (2) the matminer toolkit for connecting materials data to machine learning algorithms, and (3) the atomate/Rocketsled software for running high-throughput density functional theory calculations on supercomputers. It also briefly outlines a project to develop a text mining database for materials science literature.
Overview of accelerated materials design efforts in the Hacking Materials res...Anubhav Jain
This document provides an overview of accelerated materials design efforts in the Hacking Materials research group. It discusses using high-throughput computing and simulations like density functional theory to generate large datasets for materials screening. Machine learning techniques like matminer are used to represent materials as feature vectors to enable predictive modeling. Text mining of scientific literature is also discussed as a way to automatically extract knowledge from millions of published articles to inform new materials discoveries. The goal is to develop automated methods that can suggest the next best computational experiments to optimize properties of interest.
This talk describes opportunities for companies and academics to work with undergraduates at University of Wisconsin to engage in the exciting new field of Materials Informatics. It was originally given in slightly altered form at the UW AMIC meeting on 2015-09-11.
2016 09-06v3 skunkworks q&a information session publicddm314
This document summarizes an information session for the Informatics Skunkworks group at the University of Wisconsin-Madison. The group is dedicated to applying informatics to science and engineering problems. Students can join projects with mentors to gain experience. Projects use large datasets and tools like machine learning. An example project used density functional theory calculations and machine learning to predict diffusion barriers for alloy systems, which could save significant computation costs. Students are encouraged to join for opportunities to work on projects, build skills, and participate in a community of colleagues.
Combinatorial Experimentation and Machine Learning for Materials Discoveryaimsnist
This document describes how machine learning and active learning can be used to enhance high-throughput combinatorial experimentation for materials discovery. Specifically, it discusses how active learning algorithms can direct experiments to optimally query samples and map out phase diagrams with fewer total measurements. An example is given of using these methods to autonomously map the composition-temperature phase diagram of tungsten-doped VO2 with only 10% of samples requiring direct measurement. The document concludes that machine learning has the potential to significantly reduce the number of experiments needed in combinatorial screening studies.
Applications of Machine Learning for Materials Discovery at NRELaimsnist
Machine learning and artificial intelligence techniques are being applied at NREL to accelerate materials discovery in several ways:
1) Clustering of experimental XRD patterns allows automated structure determination, replacing slow manual analysis.
2) Neural networks can predict optoelectronic properties of molecules from their structure alone, screening millions of candidates.
3) Models are being developed to predict properties not measured in experiments to augment experimental data.
4) End-to-end deep learning on molecular and crystal structures may predict properties with accuracy approaching computationally expensive DFT simulations.
Predicting local atomic structures from X-ray absorption spectroscopy using t...aimsnist
The document discusses using theory, computation, and machine learning to interpret experimental X-ray absorption spectroscopy data and determine local atomic structures. It presents examples of using density functional theory calculations of X-ray absorption near edge structure (XANES) spectra to benchmark predictions against experiments and develop machine learning models for structure classification. The models are able to classify local structures like tetrahedral, square pyramidal, and octahedral coordination with over 85% accuracy across different materials systems. This approach provides a way to solve the inverse problem of determining structures from spectroscopy measurements in real time.
Smart Metrics for High Performance Material Designaimsnist
This document discusses smart metrics for high-performance material design using density functional theory (DFT), classical force fields (FF), and machine learning (ML). It provides an overview of the JARVIS database and tools containing over 35,000 materials and classical properties calculated using DFT, FF, and ML methods. Metrics discussed include formation energy, exfoliation energy, elastic constants, surface energy, vacancy energy, grain boundary energy, bandgaps, and other electronic and optical properties important for applications like solar cells. ML models are developed to predict these properties with mean absolute errors within chemical accuracy compared to DFT benchmarks.
Failing Fastest: What an Effective HTE and ML Workflow Enables for Functional...aimsnist
This document discusses how high-throughput experimentation (HTE) and machine learning (ML) can accelerate materials discovery for functional metallic glasses (MGs). It describes a round robin experiment between NIST and NREL to synthesize and characterize composition spread samples to test data sharing standards. General trends predicted by ML models often correlate within a given synthesis method but systematic differences can occur between methods. While ML is not a replacement for physics, the combination of HTE and ML can identify promising new materials faster than traditional experimentation alone. Autonomous research platforms may enable an even greater acceleration of the materials discovery process.
Accelerated Materials Discovery & Characterization with Classical, Quantum an...KAMAL CHOUDHARY
This document summarizes Kamal Choudhary's talk on accelerated materials discovery and characterization using classical, quantum, and machine learning approaches. The talk discusses NIST's JARVIS framework which combines different computational approaches and machine learning to discover new materials and characterize their properties. Specifically, JARVIS has been used to evaluate force fields, discover low-dimensional materials, topological materials, efficient solar cell materials, high-performance thermoelectrics, and flexible/negative Poisson materials. Machine learning models have also been developed to predict formation energies and bandgaps of materials.
Machine Learning Platform for Catalyst DesignAnubhav Jain
This document provides an overview of a project to design a machine learning platform for catalyst design. The project aims to (1) design and screen new materials for water purification faster than ever before using materials theory, high-performance computing, and automated experiments, (2) demonstrate commercially viable catalysts for oxyanion reduction within one year, and (3) develop a general materials discovery platform that can discover new materials for many scenarios through leveraging supercomputing and machine learning to virtually screen over 1,000 alloys for their nitrate reduction potential and experimentally testing the most promising candidates.
From Conference Electronic Materials and Applications 2019 (EMA 2019), Abstract # 3065049, EMA-S13-013-2019 Symposium: S13: From Basic Science to Agile Design of Functional Materials: Aligned Computational and Experimental Approaches and Materials Informatics, January 24, 2019
Conducting and Enabling Data-Driven Research Through the Materials ProjectAnubhav Jain
The Materials Project provides a free database of calculated materials properties for over 150,000 materials. It aims to enable data-driven materials research by conducting high-throughput calculations and providing tools for researchers to explore the data. The presentation discusses how the Materials Project has been used to discover new functional materials, including p-type transparent conductors, thermoelectrics, and phosphors, by screening for materials with desirable predicted properties. Engaging the research community through contributions of experimental data and machine learning benchmarking helps add value to the Materials Project platform.
High-throughput discovery of low-dimensional and topologically non-trivial ma...KAMAL CHOUDHARY
This document summarizes research into using density functional theory to discover new low-dimensional and topologically non-trivial materials. Key aspects include screening over 600 2D materials and 30,000 3D bulk materials to identify promising candidates, calculating exfoliation energies to confirm stability of low-dimensional forms, and using a spillage criterion to identify over 1,800 potential topological materials by comparing wavefunctions with and without spin-orbit coupling. Ongoing work focuses on characterizing elemental contributions to topological materials and identifying other classes of topological phases like Weyl and Dirac semimetals.
Automated Machine Learning Applied to Diverse Materials Design ProblemsAnubhav Jain
Automated Machine Learning Applied to Diverse Materials Design Problems
Anubhav Jain presented on developing standardized benchmark datasets and algorithms for automated machine learning in materials science. Matbench provides a diverse set of materials design problems for evaluating ML algorithms, including classification and regression tasks of varying sizes from experiments and DFT. Automatminer is a "black box" ML algorithm that uses genetic algorithms to automatically generate features, select models, and tune hyperparameters on a given dataset, performing comparably to specialized literature methods on small datasets but less well on large datasets. Standardized evaluations can help accelerate progress in automated ML for materials design.
Computational Discovery of Two-Dimensional Materials, Evaluation of Force-Fie...KAMAL CHOUDHARY
JARVIS (Joint Automated Repository for Various Integrated Simulations) is a repository designed to automate materials discovery using classical force-field, density functional theory, machine learning calculations and experiments.
The Force-field section of JARVIS (JARVIS-FF) consists of thousands of automated LAMMPS based force-field calculations on DFT geometries. Some of the properties included in JARVIS-FF are energetics, elastic constants, surface energies, defect formations energies and phonon frequencies of materials.
The Density functional theory section of JARVIS (JARVIS-DFT) consists of thousands of VASP based calculations for 3D-bulk, single layer (2D), nanowire (1D) and molecular (0D) systems. Most of the calculations are carried out with optB88vDW functional. JARVIS-DFT includes materials data such as: energetics, diffraction pattern, radial distribution function, band-structure, density of states, carrier effective mass, temperature and carrier concentration dependent thermoelectric properties, elastic constants and gamma-point phonons.
The Machine-learning section of JARVIS (JARVIS-ML) consists of machine learning prediction tools, trained on JARVIS-DFT data. Some of the ML-predictions focus on energetics, heat of formation, GGA/METAGGA bandgaps, bulk and shear modulus. The ML webpage is visible to NIST employees only right now, but will be available publicly soon.
Software tools, crystal descriptors, and machine learning applied to material...Anubhav Jain
1. The document discusses using density functional theory (DFT) and high-throughput computing to screen large numbers of materials for promising thermoelectric properties.
2. Early high-throughput studies screened tens of thousands of materials for applications like scintillators, topological insulators, and high temperature superconductors, finding candidates with a hit rate of around 1 in 1000.
3. Predictions from high-throughput DFT have been experimentally confirmed for new thermoelectric, battery cathode, and CO2 capture materials. However, accurately predicting all thermoelectric properties like the figure of merit remains challenging.
Database of Topological Materials and Spin-orbit SpillageKAMAL CHOUDHARY
We present the results of a high-throughput, first principles search for topological materials based on identifying materials with band inversion induced by spin-orbit coupling. Out of the currently available 30000 materials in our database, we investigate more than 4507 non-magnetic materials having heavy atoms and low bandgaps. We compute the spillage between the spin-orbit and non-spin-orbit wave functions, resulting in more than 1699 high-spillage candidate materials. We demonstrate that in addition to Z2 topological insulators, this screening method successfully identifies many semimetals and topological crystalline insulators. Our approach is applicable to the investigation of disordered or distorted materials, because it is not based on symmetry considerations, and it can be extended to magnetic materials. After our first screening step, we use Wannier-interpolation to calculate the topological invariants and to search for band crossings in our candidate materials. We discuss some individual example materials, as well as trends throughout our dataset, that is available at JARVIS-DFT website: http://jarvis.nist.gov
Combining density functional theory calculations, supercomputing, and data-dr...Anubhav Jain
Combining density functional theory calculations, supercomputing, and data-driven methods, the speaker aims to understand and design new thermoelectric materials for waste heat recovery. He discusses using high-throughput computations and large databases like the Materials Project to efficiently search for promising thermoelectric materials candidates among thousands of potential compositions. Experimental validation is then needed to confirm computational predictions.
Targeted Band Structure Design and Thermoelectric Materials Discovery Using H...Anubhav Jain
This work was supported by funding from the U.S. Department of Energy and involved collaborations with researchers from Northwestern University, Universite Catholique de Louvain, Dalhousie University, and UC Berkeley/LBNL. Using high-throughput computational methods, over 50,000 compounds were screened to discover new thermoelectric materials, identifying YCuTe2 as a promising candidate with a calculated zT of 0.75. Experimental synthesis and testing achieved a maximum zT of 0.75 for this material. Future work will involve developing more accurate electronic transport models, expanding the materials library through substitutional predictions, and applying machine learning to discover new structure-property relationships.
Software tools for data-driven research and their application to thermoelectr...Anubhav Jain
This document summarizes several software tools for materials data science and their application to thermoelectrics materials discovery. It discusses Atomate for high-throughput calculations, Matminer for materials feature extraction and machine learning, AMSET for electron transport modeling, and integration with the Materials Project database. Example applications are described like using order parameters for structure characterization and a computational screening identifying new thermoelectric materials like YCuTe2.
Data Mining to Discovery for Inorganic Solids: Software Tools and ApplicationsAnubhav Jain
This document summarizes several projects from Anubhav Jain at Lawrence Berkeley National Laboratory related to using artificial intelligence and data mining for materials science. It discusses (1) developing interpretable descriptors of crystal structure based on local environments, (2) the matminer toolkit for connecting materials data to machine learning algorithms, and (3) the atomate/Rocketsled software for running high-throughput density functional theory calculations on supercomputers. It also briefly outlines a project to develop a text mining database for materials science literature.
Overview of accelerated materials design efforts in the Hacking Materials res...Anubhav Jain
This document provides an overview of accelerated materials design efforts in the Hacking Materials research group. It discusses using high-throughput computing and simulations like density functional theory to generate large datasets for materials screening. Machine learning techniques like matminer are used to represent materials as feature vectors to enable predictive modeling. Text mining of scientific literature is also discussed as a way to automatically extract knowledge from millions of published articles to inform new materials discoveries. The goal is to develop automated methods that can suggest the next best computational experiments to optimize properties of interest.
This talk describes opportunities for companies and academics to work with undergraduates at University of Wisconsin to engage in the exciting new field of Materials Informatics. It was originally given in slightly altered form at the UW AMIC meeting on 2015-09-11.
2016 09-06v3 skunkworks q&a information session publicddm314
This document summarizes an information session for the Informatics Skunkworks group at the University of Wisconsin-Madison. The group is dedicated to applying informatics to science and engineering problems. Students can join projects with mentors to gain experience. Projects use large datasets and tools like machine learning. An example project used density functional theory calculations and machine learning to predict diffusion barriers for alloy systems, which could save significant computation costs. Students are encouraged to join for opportunities to work on projects, build skills, and participate in a community of colleagues.
This document describes an experimental investigation of a quaternary nitrate/nitrite molten salt as an advanced heat transfer fluid and energy storage material for concentrated solar power plants. The author synthesized a salt mixture containing lithium nitrate, potassium nitrate, potassium nitrite and sodium nitrate, doped with 1% silicon dioxide nanoparticles. Differential scanning calorimetry showed the doped salt had up to 25% higher specific heat capacity compared to the base salt. Scanning electron microscopy and energy dispersive X-ray spectroscopy characterized the salt mixtures and identified the elements present. The enhanced salt properties could improve concentrated solar power plant efficiency and lower the cost of electricity generation.
RMG at the Flame Chemistry Workshop 2014Richard West
Presentation to the 2nd International Workshop on Flame Chemistry, preceding the 35th International Symposium on Combustion, in San Francisco, CA, in August 2014.
Describes recent progress in two projects related to our Reaction Mechanism Generator software.
A label free and enzyme-free aptasensor for visual cd2+ detection based on sp...Vincent Paul Schmitz
The document describes a label-free and enzyme-free aptasensor for visual detection of Cd2+ based on split G-quadruplex DNAzyme fragments. The sensing system utilizes a three-way junction structure constructed from three hairpin molecules. In the presence of Cd2+, the aptamer binds Cd2+ and initiates branch migration of the hairpins, forming the junction. This brings the split G-quadruplex fragments into proximity to form an intact G-quadruplex upon addition of hemin. The formed G-quadruplex DNAzymes catalyze a color change reaction, providing naked-eye visual detection of Cd2+ with high sensitivity down to 10 pM concentration. The biosensor
One of the most important, yet often overlooked, aspects of predictive modeling is the transformation of data to create model inputs, better known as feature engineering (FE). This talk will go into the theoretical background behind FE, showing how it leverages existing data to produce better modeling results. It will then detail some important FE techniques that should be in every data scientist’s tool kit.
nanotechnology. INTRODUCTION TO BIONANOTECHNOLOGY
Group : L01-B01 (LAB)
Class Date & Time : 02-Apr-2024, 08:00 - 10:00 AM
All students will be tagged as ABSENT until student scanned QR code OR lecturer manually update attendance status
Cis Vs. Trans: Squaraine Molecules as Potential Sensitizers for Dye Sensitize...danielmorales91
This document summarizes research on synthesizing and testing a new cis-like symmetrical squaraine dye as a potential sensitizer for dye-sensitized solar cells. The synthesized squaraine molecule has absorption bands in the high-energy visible light region and reversible redox behavior that could improve photovoltaic performance. Testing of the dye's electrochemical and optical properties showed a red-shifted absorption and energy levels that may positively impact solar cell efficiency compared to other squaraine dyes. Future work will involve incorporating the dye into solar cells to evaluate its photovoltaic response.
An introduction to usage of AI in Pharmaceutical industry. Machine Learning algorithms and use cases for Pharma Industry have been discussed in this PPT during the FDP for Andhra University
AI for automated materials discovery via learning to represent, predict, gene...Deakin University
A brief overview of how our AI can help automate the materials discovery process, covering a wide range of problems, from drug design to crystal plasticity.
The document provides an overview of the state of nanotechnology, including major accomplishments and tools/techniques. In the past 15-20 years, measurements and imaging have improved to picometer precision (1), modeling can successfully simulate molecular interactions (2), and some nanostructure fabrication processes exist (3). A variety of microscopy, metrology, simulation and synthesis tools form the foundation for nanotechnology research. Recent progress includes new microscopy arrays, molecular modeling software, nanomaterials, electronics, and biochip applications. Grand challenges include developing stronger lightweight materials and improving computer and solar cell efficiency.
This document discusses high-throughput screening (HTS) workflows for identifying biologically active small molecules. It describes how robots are used to rapidly screen large libraries of compounds in assays and generate large datasets. Statistical and machine learning methods in R can then be used to build predictive models from these datasets to identify promising leads and guide the screening of additional compounds. Caveats regarding the applicability of models to new chemical spaces are also discussed.
The document proposes the development of piezoresistive transistors using layered dichalcogenide materials to overcome limitations in silicon-based devices. It outlines a 3-phase technical approach to optimize materials, demonstrate a large-scale functional prototype, and develop a full-scale prototype. A project timeline, budget, and potential economic and social impacts are also presented.
This document provides an overview of the Georgia Tech Packaging Research Center (PRC). It includes the PRC organizational structure, listing directors, departments, research groups, and staff. It also outlines PRC funding sources and needs, global partnerships, and core technologies including 3D integrated circuits and systems. The PRC pursues open innovation through collaborations between industry and academia to enable globally competitive technologies.
Skoltech at a glance. What is the new type of university? What do we do? What differs us from traditional universities?
And - what it takes to become a Skoltech student?
Skoltech is a new university in Russia aimed at accelerating innovation. It offers master's programs in fields like energy, IT, and biomedical science. Students take intensive courses and engage in research with a focus on practical applications. The university works with industry and has 15 research centers in areas such as biomedicine, energy, IT, and space. It aims to produce global leaders by giving students skills in both research and entrepreneurship.
Combining density functional theory calculations, supercomputing, and data-dr...Anubhav Jain
The document summarizes how computational materials science using density functional theory (DFT) calculations, supercomputing, and data-driven methods can help design new materials faster than traditional experimental approaches. It describes how high-throughput DFT calculations are run on supercomputers to screen large numbers of potential materials. The results are compiled in open databases like the Materials Project to be shared and reused by researchers. While computational limitations remain, combining computation and data is helping accelerate the discovery of new materials with improved properties for applications like batteries, thermoelectrics, and carbon capture.
The importance of data curation on QSAR Modeling: PHYSPROP open data as a cas...Kamel Mansouri
This presentation highlighted how data curation impacts the reliability of QSAR models. We examined key datasets related to environmental endpoints to validate across chemical structure representations (e.g., mol file and SMILES) and identifiers (chemical names and registry numbers), and approaches to standardize data into QSAR-ready formats prior to modeling procedures. This allowed us to quantify and segregate data into quality categories. This improved our ability to evaluate the resulting models that can be developed from these data slices, and to quantify to what extent efforts developing high-quality datasets have the expected pay-off in terms of predicting performance. The most accurate models that we build will be accessible via our public-facing platform and will be used for screening and prioritizing chemicals for further testing.
Similar to Materials informatics skunkworks overview 2015-11-18 1.1 (20)
The document provides advice on what a PhD student should learn during their degree. It discusses that the answer may vary between individuals. Some key learnings suggested include:
1. Learning how to learn quickly and effectively, and having a growth mindset.
2. Gaining skills to solve open-ended, unstructured problems by setting goals, leveraging technology, and drawing on interests/passions.
3. Developing technical knowledge in their field while also learning about science/technology broadly.
4. Improving self-awareness of strengths/weaknesses and professional skills like time management, presenting, and teamwork.
2019 09-06 skunkworks q&a information session v2.1 distddm314
This document summarizes an information session about the Informatics Skunkworks group at the University of Wisconsin-Madison. The group uses informatics tools like machine learning, big data, and high-performance computing to solve problems in science and engineering. Example projects include using machine learning to predict material properties and detect defects in images. Students can get course credit or pay for working on projects with mentors. The group has had success publishing papers and winning fellowships. Students are encouraged to email the contact to learn about open projects.
2018 09-07 skunkworks q&a information session v1.2ddm314
This document summarizes an information session about forming an "Informatics Skunkworks" group at the University of Wisconsin-Madison dedicated to realizing the potential of informatics in science and engineering. The group works on projects using tools like machine learning, provides a community for students, and has had successes publishing papers and winning awards. Example projects described include using machine learning to predict material properties and detect defects in images. Students are encouraged to email the organizer if interested in joining projects on materials informatics topics.
2017-09-08 skunkworks q&a information session v1.0 distrddm314
This document summarizes an information session for the Informatics Skunkworks group at the University of Wisconsin-Madison. The Skunkworks is dedicated to applying informatics to science and engineering problems. Students can join projects with mentors to gain skills and work on transformative tools using large datasets and new fields. Typical commitments involve 10 hours per week of work on a project, along with regular meetings and presentations. Benefits of joining include access to resources, networking opportunities, experience with teamwork and publication. Examples of past projects demonstrated machine learning applications for materials problems like improving diffusion data prediction.
Zach and Aren talk on Materials Informatics at UW WIMSEA 2016-02-12ddm314
Presentation at WIsconsin Materials Science and Engineering Industrial Affiliates (WIMSEA) meeting at University of Wisconsin - Madison on 2016-02-12. Undergraduates Zach and Aren presented on informatics skunkworks activities in materials informatics.
Skunworks Final poster 2015-09-21_eau_claireddm314
Poster presentation from Skunkworks members at the Regional Materials and Manufacturing Network (RM2N) meeting in Eau Claire, WI. The focus is on machine learning applications for materials impurity diffusion data.
Morgan mgi meeting 2015 01-11 v2.0 distributionddm314
This document discusses the importance of collaborative networks for achieving the goals of the Materials Genome Initiative (MGI). It provides examples of several collaborative networks, including the Materials Accelerator Network, the Wisconsin Materials Institute, and MAterials Simulation Toolkit (MAST). These networks aim to strengthen integration between theory, modeling, experimentation, academia, and industry. They also promote sharing of resources, data, and tools to accelerate materials development. The document emphasizes that collaborative networks are critical for achieving the MGI's goals of developing new materials twice as fast at half the cost.
The document discusses nanostructured ferritic alloys which are steels strengthened with nanoscale oxide precipitates. Density functional theory calculations were performed to determine the stable structures of Ti-O, Y-O, and Ti-Y-O clusters within the ferritic matrix. The calculations found that clusters resembling the structures of bulk metal oxides like TiO2 and Y2O3 were the most stable, with mixed termination and hyperstoichiometric compositions. The interfaces between oxide precipitates and the ferritic matrix were also examined using density functional theory, finding reconstructions occurred to accommodate lattice mismatches.
Walmart Business+ and Spark Good for Nonprofits.pdfTechSoup
"Learn about all the ways Walmart supports nonprofit organizations.
You will hear from Liz Willett, the Head of Nonprofits, and hear about what Walmart is doing to help nonprofits, including Walmart Business and Spark Good. Walmart Business+ is a new offer for nonprofits that offers discounts and also streamlines nonprofits order and expense tracking, saving time and money.
The webinar may also give some examples on how nonprofits can best leverage Walmart Business+.
The event will cover the following::
Walmart Business + (https://business.walmart.com/plus) is a new shopping experience for nonprofits, schools, and local business customers that connects an exclusive online shopping experience to stores. Benefits include free delivery and shipping, a 'Spend Analytics” feature, special discounts, deals and tax-exempt shopping.
Special TechSoup offer for a free 180 days membership, and up to $150 in discounts on eligible orders.
Spark Good (walmart.com/sparkgood) is a charitable platform that enables nonprofits to receive donations directly from customers and associates.
Answers about how you can do more with Walmart!"
Level 3 NCEA - NZ: A Nation In the Making 1872 - 1900 SML.pptHenry Hollis
The History of NZ 1870-1900.
Making of a Nation.
From the NZ Wars to Liberals,
Richard Seddon, George Grey,
Social Laboratory, New Zealand,
Confiscations, Kotahitanga, Kingitanga, Parliament, Suffrage, Repudiation, Economic Change, Agriculture, Gold Mining, Timber, Flax, Sheep, Dairying,
Philippine Edukasyong Pantahanan at Pangkabuhayan (EPP) CurriculumMJDuyan
(𝐓𝐋𝐄 𝟏𝟎𝟎) (𝐋𝐞𝐬𝐬𝐨𝐧 𝟏)-𝐏𝐫𝐞𝐥𝐢𝐦𝐬
𝐃𝐢𝐬𝐜𝐮𝐬𝐬 𝐭𝐡𝐞 𝐄𝐏𝐏 𝐂𝐮𝐫𝐫𝐢𝐜𝐮𝐥𝐮𝐦 𝐢𝐧 𝐭𝐡𝐞 𝐏𝐡𝐢𝐥𝐢𝐩𝐩𝐢𝐧𝐞𝐬:
- Understand the goals and objectives of the Edukasyong Pantahanan at Pangkabuhayan (EPP) curriculum, recognizing its importance in fostering practical life skills and values among students. Students will also be able to identify the key components and subjects covered, such as agriculture, home economics, industrial arts, and information and communication technology.
𝐄𝐱𝐩𝐥𝐚𝐢𝐧 𝐭𝐡𝐞 𝐍𝐚𝐭𝐮𝐫𝐞 𝐚𝐧𝐝 𝐒𝐜𝐨𝐩𝐞 𝐨𝐟 𝐚𝐧 𝐄𝐧𝐭𝐫𝐞𝐩𝐫𝐞𝐧𝐞𝐮𝐫:
-Define entrepreneurship, distinguishing it from general business activities by emphasizing its focus on innovation, risk-taking, and value creation. Students will describe the characteristics and traits of successful entrepreneurs, including their roles and responsibilities, and discuss the broader economic and social impacts of entrepreneurial activities on both local and global scales.
The chapter Lifelines of National Economy in Class 10 Geography focuses on the various modes of transportation and communication that play a vital role in the economic development of a country. These lifelines are crucial for the movement of goods, services, and people, thereby connecting different regions and promoting economic activities.
This presentation was provided by Rebecca Benner, Ph.D., of the American Society of Anesthesiologists, for the second session of NISO's 2024 Training Series "DEIA in the Scholarly Landscape." Session Two: 'Expanding Pathways to Publishing Careers,' was held June 13, 2024.
1. Opportunities with the UW
Materials Informatics Skunkworks
Information about who we are, what we do, how to work
with us, how to join us
Dane Morgan
University of Wisconsin, Madison
Department of Materials Science and Engineering
ddmorgan@wisc.edu
W: 608-265-5879
C: 608-234-2906
November 18, 2015 1
2. What is Materials Informatics?
Materials informatics is a field of study that
applies the tools and principles of information
extraction from data (informatics) to materials
science and engineering to better understand
the use, selection, development, and discovery
of materials.
– Mining for materials information in large data sets
– Applying new information technologies to enable
new materials science
2
4. Turning Point for Materials Informatics
Data availabilityData Production Informatics Tools
-6
-5.5
-5
-4.5
-4
-3.5
-3
0 10 20 30 40
PredictedLogk*(cm/s)
E above hull (meV/atom)
LaBO3
YBO3
PrBO3
(Sr,Ba)BO3
4
5. The Undergraduate “Materials
Informatics Skunkworks”
We are establishing ~10-20 undergraduates working together
to provide materials informatics research for companies
• Help researchers in academia and industry develop and
utilize this new field
• Provide training in rapidly growing field of informatics to
undergraduates to enhance employment opportunities and
key workforce development
• Be supported financially/academically through credits,
internships, senior design/capstone projects, funded
projects from industry
• Be supported intellectually through group culture of
teamwork and knowledge continuity (more senior train
more junior members) with limited faculty involvement for
advanced issues
5
6. Focus Area: Machine Learning for
Knowledge Discovery in Large Data Sets
Use machine learning techniques to
• Organize your data by putting all relevant,
cleaned input and output into one place
• Understand your data by finding the most
important factors controlling output values
• Expand your data by interpolating and
extrapolating
• Optimize your data by finding correlations
between input and output data to optimize
desired output
6
7. Example
• Organize: Build a database of all the relevant factors (impurity
concentrations, processing conditions, testing conditions, …)
and output performance.
• Understand: Which impurities matter most. Size of impurity
effects vs. other contributions.
• Expand: Interpolate/extrapolate to other impurity
concentrations to assess performance under conditions we
have not yet explored.
• Optimize: Determine impurity concentrations that lead to
optimal performance.
I know impurities impact my device lifetime, so …
7
8. Example: Predicting Impurity Diffusion in
FCC Alloys
• 15 FCC hosts x 100
impurities = 1500
systems, ~15m core-
hours (~$500k to
produce, ~2 years).
• We have computed
values for ~10%
• How can we quickly
(and cheaply) get to
~100% coverage?
8
M Al Ca Ni Cu Sr Rh Pd Ag Yb Ir Pt Au Pb Ac Th
X 13 20 28 29 38 45 46 47 70 77 78 79 82 89 90
H 1
He 2
Li 3
Be 4
B 5
C 6
N 7
O 8
F 9
Ne 10
Na 11
Mg 12
Al 13
Si 14
P 15
S 16
Cl 17
Ar 18
K 19
Ca 20
Sc 21
Ti 22
V 23
Cr 24
Mn 25
Fe 26
Co 27
Ni 28
Cu 29
Zn 30
Ga 31
Ge 32
As 33
Se 34
Br 35
Kr 36
Rb 37
Sr 38
Y 39 N/A N/A
Zr 40
Nb 41
Mo 42 N/A
Tc 43 N/A N/A
Ru 44 N/A N/A
Rh 45 N/A N/A
Pd 46 N/A
Ag 47
Cd 48
In 49
Sn 50
Sb 51
Te 52
I 53
Xe 54
Cs 55
Ba 56
La 57 N/A N/A
Ce 58
Pr 59
Nd 60
Pm 61
Sm 62
Eu 63
Gd 64
Tb 65
Dy 66
Ho 67
Er 68
Tm 69
Yb 70
Lu 71
Hf 72
Ta 73
W 74
Re 75
Os 76
Ir 77
Pt 78
Au 79
Hg 80
Tl 81
Pb 82
Bi 83
Po 84
At 85
Rn 86
Fr 87
Ra 88
Ac 89
Th 90
Pa 91
U 92
Np 93
Pu 94
UNPUBLISHED DATA – CONFIDENTIAL – DO NOT DISSEMINATE
9. Materials Informatics Approach –
Regression and Prediction
• Assume Activation energy = F(elemental properties)
• Elemental properties = melting temperature, bulk modulus,
electronegativity, …
• F is determined using a one of many possible methods: linear
regression, neural network, decision tree, kernel ridge
regression, …
• Fit F with calculated data, test it with cross-validation, then
predict new data.
M Al Ca Ni Cu Sr Rh Pd Ag Yb Ir Pt Au Pb Ac Th
X 13 20 28 29 38 45 46 47 70 77 78 79 82 89 90
H 1
He 2
Li 3
Be 4
B 5
C 6
N 7
O 8
F 9
Ne 10
Na 11
Mg 12
Al 13
Si 14
P 15
S 16
Cl 17
Ar 18
K 19
Ca 20
Sc 21
Ti 22
V 23
Cr 24
Mn 25
Fe 26
Co 27
Ni 28
Cu 29
Zn 30
Ga 31
Ge 32
As 33
Se 34
Br 35
Kr 36
Rb 37
Sr 38
Y 39 N/A N/A
Zr 40
Nb 41
Mo 42 N/A
Tc 43 N/A N/A
Ru 44 N/A N/A
Rh 45 N/A N/A
Pd 46 N/A
Ag 47
Cd 48
In 49
Sn 50
Sb 51
Te 52
I 53
Xe 54
Cs 55
Ba 56
La 57 N/A N/A
Ce 58
Pr 59
Nd 60
Pm 61
Sm 62
Eu 63
Gd 64
Tb 65
Dy 66
Ho 67
Er 68
Tm 69
Yb 70
Lu 71
Hf 72
Ta 73
W 74
Re 75
Os 76
Ir 77
Pt 78
Au 79
Hg 80
Tl 81
Pb 82
Bi 83
Po 84
At 85
Rn 86
Fr 87
Ra 88
Ac 89
Th 90
Pa 91
U 92
Np 93
Pu 94
Train F(properties)
M Al Ca Ni Cu Sr Rh Pd Ag Yb Ir Pt Au Pb Ac Th
X 13 20 28 29 38 45 46 47 70 77 78 79 82 89 90
H 1
He 2
Li 3
Be 4
B 5
C 6
N 7
O 8
F 9
Ne 10
Na 11
Mg 12
Al 13
Si 14
P 15
S 16
Cl 17
Ar 18
K 19
Ca 20
Sc 21
Ti 22
V 23
Cr 24
Mn 25
Fe 26
Co 27
Ni 28
Cu 29
Zn 30
Ga 31
Ge 32
As 33
Se 34
Br 35
Kr 36
Rb 37
Sr 38
Y 39 N/A N/A
Zr 40
Nb 41
Mo 42 N/A
Tc 43 N/A N/A
Ru 44 N/A N/A
Rh 45 N/A N/A
Pd 46 N/A
Ag 47
Cd 48
In 49
Sn 50
Sb 51
Te 52
I 53
Xe 54
Cs 55
Ba 56
La 57 N/A N/A
Ce 58
Pr 59
Nd 60
Pm 61
Sm 62
Eu 63
Gd 64
Tb 65
Dy 66
Ho 67
Er 68
Tm 69
Yb 70
Lu 71
Hf 72
Ta 73
W 74
Re 75
Os 76
Ir 77
Pt 78
Au 79
Hg 80
Tl 81
Pb 82
Bi 83
Po 84
At 85
Rn 86
Fr 87
Ra 88
Ac 89
Th 90
Pa 91
U 92
Np 93
Pu 94
Y. Zeng and K. Bai, Journal of Alloys and Compounds 624, p. 201-209 (2015).
9
10. Model Predictive Ability
• Leave one out
cross validation
• Predictive RMS =
0.24 eV – predicts
diffusion of new
impurity within
~10x at 1000K
• Time to predict
new system < 1s!
0 1 2 3 4 5 6
DFT Activation Energy [eV]
0
1
2
3
4
5
6
PredictedActivationEnergy[eV]
Al
Cu
Ni
Pd
Pt
Au
Ca
Ir
Pb
Leave One Out Cross Validation
y = 0.9909x
R
2
= 0.9312
UNPUBLISHED DATA – CONFIDENTIAL – DO NOT DISSEMINATE
10
11. Who Did the Work?
Undergraduate Informatics Team!
Benjamin Anderson
Liam Witteman
Team guru and postdoc
Henry Wu
Aren Lorenson
Haotian Wu
Zachary Jensen
11
13. What the Informatics Skunkworks
Might Provide You
WORKFORCE
A team of talented students who are ready to work quickly with
your company to get the most out of your data
DATA ANALYTICS
Technical skills to help you organize, understand and expand data
sets and utilize data to optimize materials development
13
14. What You Might Provide the
Informatics Skunkworks
FINANCIAL/COURSE CREDIT SUPPORT
Internships, Co-ops, Senior design/Capstone projects, Research
projects, Research funding or course credits
SHARED DATA
Data sets of materials related performance and property data that
are large (> ~50), can be shared (ideally published), and are worth
mining
14
16. Joining the Materials Informatics Skunkworks
Who is welcome?
• Anyone – we focus on undergraduates but graduate students and postdocs are
welcome. We are centered at UW Madison but would love to branch out to
other schools.
• Prerequisites – an excitement about the topic and a willingness to work hard on
it. No informatics skilled needed. We strongly encourage those interested in at
least a year, ideally longer, commitments. But we also encourage those
interested in doing shorter term class and capstone projects.
What would I do?
• We work with you to define a data set and problem and get you the necessary
tools to do the work.
• You apply informatics tools to materials problems, learn from and train other
students, help organize events, and join in the fun.
How do I join?
• Send an email to Dane Morgan at ddmorgan@wisc.edu and we can discuss how
to get you involved.
16
17. Why Join Materials Informatics Skunkworks?
• Have fun doing creative, new, and impactful science!
• Learn about materials informatics, one of the hottest new areas in materials
science.
• Learn computer science methods from informatics, machine learning, data
mining, knowledge discovery, etc. that are changing our world, from diagnosing
cancer to self-driving cars.
• Learn critical skills in teamwork and initiative by independently driving your own
work as part of larger team projects.
• Learn modern programming and IT tools, including python coding, GitHub and
team code development, teamwork with Slack, Matlab, Excel, etc.
• Generate impactful publishable undergraduate research that is critical to
support applications for jobs and graduate school.
• Accomplish more than you can working alone by joining a team whose DNA is
sharing and teamwork for the benefit of everyone involved.
• Strengthen your resume by working with an established team that is part of a
world-class research group and will soon have published scientific papers, a
strong online, and wide notoriety.
• Engage your personal creativity – materials informatics is a transformative new
field and you can help work with us to define it.
17