-
Shape-Changing Micromachines
Online Presentations | 05 Aug 2021 | Contributor(s):: Daniel Lopez, NACK Network
This presentation will introduce the fundamentals and limitations of current micro-machines and discuss the prospect of creating shape morphing structures by using origami and Kirigami techniques combined with nanoscale materials.
-
Active Learning via Bayesian Optimization for Materials Discovery
Online Presentations | 25 Jun 2021 | Contributor(s):: Hieu Doan, Garvit Agarwal
In this tutorial, we will demonstrate the use of active learning via Bayesian optimization (BO) to identify ideal molecular candidates for an energy storage application.
-
An Introduction to Machine Learning for Materials Science: A Basic Workflow for Predicting Materials Properties
Online Presentations | 25 Jun 2021 | Contributor(s):: Benjamin Afflerbach
This tutorial will introduce core concepts of machine learning through the lens of a basic workflow to predict material bandgaps from material compositions.
-
The Materials Simulation Toolkit for Machine Learning (MAST-ML): Automating Development and Evaluation of Machine Learning Models for Materials Property Prediction
Online Presentations | 25 Jun 2021 | Contributor(s):: Ryan Jacobs
This tutorial contains an introduction to the use of the Materials Simulation Toolkit for Machine Learning (MAST-ML), a python package designed to broaden and accelerate the use of machine learning and data science methods for materials property prediction.
-
A Hands-on Introduction to Physics-Informed Neural Networks
Online Presentations | 16 Jun 2021 | Contributor(s):: Ilias Bilionis, Atharva Hans
Can you make a neural network satisfy a physical law? There are two main types of these laws: symmetries and ordinary/partial differential equations. I will focus on differential equations in this short presentation. The simplest way to bake information about a differential equation with neural...
-
SimTools: Delivering Simulations in the Era of Abundant Data
Online Presentations | 04 Jun 2021 | Contributor(s):: Alejandro Strachan
This presentation introduces SimTool, a library that allows developers to create, publish, and share reproducible workflows with well-defined and verified inputs and outputs.
-
Convenient and efficient development of Machine Learning Interatomic Potentials
Online Presentations | 09 Mar 2021 | Contributor(s):: Yunxing Zuo
This tutorial introduces the concepts of machine learning interatomic potentials (ML-IAPs) in materials science, including two components of local environment atomic descriptors and machine learning models.
-
Constructing Accurate Quantitative Structure-Property Relationships via Materials Graph Networks
Online Presentations | 09 Mar 2021 | Contributor(s):: Chi Chen
This tutorial covers materials graph networks for modeling crystal and molecular properties. We will introduce the graph representation of crystals and molecules and how the convolutional operations are carried out on the materials graphs.
-
Symposium on Nanomaterials for Energy: Atomic Force Microscopy for Energy Applications - A Review
Online Presentations | 05 Feb 2021 | Contributor(s):: Arvind Raman
Atomic Force Microscopy is unique in its ability to measure sub -nanonewton forces arising from a variety physical phenomena between a sharp tip and a sample. In this talk we review the most recent applications of atomic force microscopy to explore and characterize quantitatively the properties...
-
Shape-changing Nanoparticles for Nanomedicine Applications
Online Presentations | 04 Feb 2021 | Contributor(s):: Vikram Jadhao
I will describe the nanoHUB tool “Nanoparticle Shape Lab” that enables simulations of the shape deformation of charged nanoparticles for a broad variety of nanoparticle material properties including nanoparticle surface charge, pattern, elasticity and solution conditions such...
-
U-Net Convolutional Neural Networks for Image Segmentation: Application to Scanning Electron Microscopy Images of Graphene
Online Presentations | 01 Feb 2021 | Contributor(s):: Aagam Rajeev Shah
This tutorial introduces you to U-Net, a popular convolutional neural network commonly developed for image segmentation in biomedicine. Using an assembled data set, you will learn how to create and train a U-Net neural network, and apply it to segment scanning electron microscopy images of...
-
Unsupervised Clustering Methods for Image Segmentation: Application to Scanning Electron Microscopy Images of Graphene
Online Presentations | 27 Jan 2021 | Contributor(s):: Aagam Rajeev Shah
This tutorial will introduce you to some basic image segmentation techniques driven by unsupervised machine learning techniques such as the Gaussian mixture model and k-means clustering. You will learn how to implement k-means clustering and template matching, and use these to segment a...
-
Module 1: Making Data Accessible, Discoverable and Useful
Online Presentations | 27 Jan 2021 | Contributor(s):: Alejandro Strachan, Juan Carlos Verduzco Gastelum
This module focuses on the importance of make materials data discoverable, interoperable, and available and best practices to doing so. Data generation is both time consuming and costly, thus, making the available, as appropriate, with the community is critical to accelerate innovation. This is...
-
Module 3: Materials Descriptors for Data Science
Online Presentations | 27 Jan 2021 | Contributor(s):: Alejandro Strachan, Juan Carlos Verduzco Gastelum, Zachary D McClure
This module focuses on the use of descriptors to improve the description of materials in machine learning. Augmenting input parameters with appropriate descriptors (a process sometimes called featurization) can often significantly improve the accuracy of predictive models. Ideal descriptors are...
-
Teaching Engineering using Jupyter Notebooks
Online Presentations | 29 Dec 2020 | Contributor(s):: Susan P Gentry, Rei Sanchez-Arias, David R. Ely, Jon Nykiel, Cindy Nguyen
This talk discusses the use of Jupyter Notebooks on nanoHUB for teaching materials engineering.
-
Machine Learning Framework for Impurity Level Prediction in Semiconductors
Online Presentations | 15 Dec 2020 | Contributor(s):: Arun Kumar Mannodi Kanakkithodi
In this work, we perform screening of functional atomic impurities in Cd-chalcogenide semiconductors using high-throughput computations and machine learning.
-
Hands-on Deep Learning for Materials Science: Convolutional Networks and Variational Autoencoders
Online Presentations | 13 Nov 2020 | Contributor(s):: Vinay Hegde, Alejandro Strachan
This tutorial introduces deep learning techniques such as convolutional neural networks and variational auto encoders from a materials standpoint.
-
Simulating Electronic Properties of Materials Using Ab Initio Modeling with SIESTA on nanoHUB.org
Online Presentations | 08 Oct 2020 | Contributor(s):: Lan Li
The simulation tool featured in this presentation is MIT Atomic-Scale Modeling Toolkit.
-
Module 5: Neural Networks for Regression and Classification
Online Presentations | 01 Oct 2020 | Contributor(s):: Saaketh Desai, Alejandro Strachan
This module introduces neural networks for material science and engineering with hands-on online simulations. Neural networks are a subset of machine learning models used to learn mappings between inputs and outputs for a given dataset. Neural networks offer great flexibility and have shown...
-
Module 4: Linear Regression Models
Online Presentations | 01 Oct 2020 | Contributor(s):: Michael N Sakano, Saaketh Desai, Alejandro Strachan
This module introduces linear regression in the context of materials science and engineering. We will apply liner regression to predict materials properties and to explore correlations between materials properties via hands-on online simulations. Linear regression is a supervised machine...