Registration:
Register here. Registration is optional but strongly encouraged to help the speakers understand the audience.
Sign up here if you would like to meet with the speakers.
Locations/Times:
Talks + Tutorial: CNM (440) A105 - 9:30 AM – 12 PM
In-person discussions: APS (401) C4200 - 1 PM – 3 PM
Microsoft Teams meeting
Join on your computer, mobile app or room device
Click here to join the meeting
Meeting ID: 255 060 457 57
Passcode: nmxJPu
Download Teams | Join on the web
Or call in (audio only)
+1 630-556-7958,,222216045# United States, Big Rock
Phone Conference ID: 222 216 045#
Find a local number | Reset PIN
Learn More | Meeting options
Abstract:
The Joint Automated Repository for Various Integrated Simulations (JARVIS) infrastructure at the National Institute of Standards and Technology (NIST) is a large-scale collection of curated datasets and tools with more than 80000 materials and millions of properties. During the JARVIS-School, we'll discuss electronic structure, deep learning, and quantum computation methods with a few hands-on jupyter/colab notebook tutorials. We will cover 1) running and analyzing electronic structure method-based properties of materials, 2) graph neural network for improved atomistic material property predictions, 3) convolutional neural network for microscopy (STM/STEM) image related tasks, 4) natural language processing for chemistry related text, and 5) quantum algorithm method: Variational Quantum Eigensolver (VQE) for predicting electron and phonon properties. We will discuss JARVIS-DFT, which consists of several materials properties beyond conventional formation energies and electronic bandgaps. These include solar cell efficiency, topological properties, superconducting transition temperature for bulk and 2D materials and electronic and magnetic properties calculated with higher accuracy methods (better quality DFT functionals and Quantum Monte Carlo). Many graph neural network models for atomistic property predictions are based on bond-distances mainly. We developed Atomistic Line Graph Neural Network (ALIGNN) that performs message passing on both the bond-distances as well as bond-angles and will apply it to JARVIS-DFT. Next, we'll discuss the AtomVision package which can be used to generate scanning tunneling microscope (STM) and scanning transmission electron microscope (STEM) datasets. Then we apply deep learning frameworks for image classification and object detection tasks with high accuracy using the AtomVision library. We'll discuss the ChemNLP framework to use NLP on literature text data mining. Currently, the application of quantum algorithms such as VQE is mainly limited to molecules. We'll show using tight-binding approaches for electrons and phonons, quantum circuit-based methods can be applied for solids also. Finally, we'll learn about JARVIS-Leaderboard, a community-wide benchmarking effort for materials design using various methods and tasks. All of the above projects are part of the NIST-JARVIS infrastructure (https://jarvis.nist.gov/).
Bio Kamal Choudhary:
Dr. Kamal Choudhary is a research scientist in the Material measurement laboratory at the National Institute of Standards and Technology (NIST), Maryland, USA. He received his PhD in materials science and engineering from University of Florida in 2015 and then joined NIST. His research interests are focused on atomistic materials design using classical, quantum, and machine learning methods. In particular, he has developed the JARVIS database and tools (https://jarvis.nist.gov/) that are used by thousands of researchers all around the world. He is an associate editor for the journal Nature NPJ Computational Materials and Scientific Data. He has published more than 70 research articles in various reputed journals and is an active member of TMS, APS, and MRS societies.
Bio Daniel Wines:
Dr. Daniel Wines is an NRC postdoctoral associate at the National Institute of Standards and Technology (NIST), Maryland, USA. He received his PhD in physics from University of Maryland Baltimore County (UMBC) in 2022 and joined NIST. His research focuses on applying first-principles methods such as density functional theory (DFT) and Quantum Monte Carlo to study next-generation quantum materials. Specifically, he is interested in correlated two-dimensional magnets and superconductors. Using these methodologies, he is an active contributor to the JARVIS project at NIST (https://jarvis.nist.gov/). His work can be divided into two categories: 1) the discovery of new and novel quantum materials and 2) accurately calculating the properties of correlated materials using many-body methods beyond DFT. He is an active member of APS and MRS societies.
Hosts:
AI/ML @ SUFs Working Group
The Applied AI/ML Seminar Series is presented with the goal of increasing communication and collaboration between scientists at the three facilities (Advanced Photon Source (APS), Argonne Tandem Linac Accelerator System (ATLAS) and the Center for Nanoscale Materials (CNM)) and providing a resource for both new and experienced AI/ML practitioners at Argonne National Lab. We plan to host a monthly seminar and tutorial series. Please see the group website for scheduling/resources: https://appliedai-anl.github.io or connect with us on Slack.
Northwestern-Argonne Institute of Science and Engineering (NAISE) and its Center for Hierarchical Materials Design (CHiMaD)
Northwestern-Argonne Institute of Science and Engineering (NAISE)’s mission is to build, sustain and support collaborative research between Northwestern and Argonne. Website
Center for Hierarchical Materials Design (CHiMaD) is a NIST Center of Excellence in Advanced Materials focusing on developing the next generation of computational tools, databases, and experimental techniques in order to enable the accelerated design of novel materials and their integration to industry, one of the primary goals of the U.S. Government's Materials Genome Initiative (MGI). CHiMaD is a Chicago-based partnership between Northwestern, Argonne, University of Chicago, QuesTek Innovations and ASM Materials Education foundation. Website