Through the MADE in SC project, 17 new faculty members will be hired at five South Carolina colleges and universities as part of the Research Infrastructure Improvement (RII) goal of this NSF EPSCoR Track-1 RII award. These faculty benefit from becoming members of a large network of materials science researchers and educators in South Carolina. In addition, to build their institutions' research infrastructure as well as that of the state, they acquire new equipment for their labs to use in research and education of students. In less than three years, 10 new faculty members have been recruited to South Carolina under this project, and to date MADE in SC has invested more that $1.6 million in new equipment (out of $4.2 million equipment budget).

 

Although this equipment is located at the institution where the faculty is hired, it is available for use by the network of researchers throughout the state. The equipment list webpage of what has already been purchased under MADE in SC includes information about the use of the equipment and how they can be accessed by other researchers. Below is a sample of the equipment available.

                                    
     Hitachi HT7800 120kV TEM                                    Cytek Northern Lights 2000 
     at the University of South Carolina                           at Clemson University
 
                                     
     Laser Shearography System                                   Leica TCS SP8 Spectral
     at the College of Charleston                                       Confocal  System
                                                                                         at Furman University  

Research Focus On:

Dr. Jianjun Hu

Director of the Machine Learning and Evolution Lab 

Dr. Jianhjun Hu is a member of the Multiscale Modeling and Computation Core (MCC) team of the Materials Assembly and Design Excellence in South Carolina (MADE in SC). He is Associate Professor of Computer Science at the University of South Carolina in the Department of Computer Science and Engineering. He is also the director of The Machine Learning and Evolution Laboratory at USC. His lab focuses on developing advanced machine learning, deep learning and data mining algorithms that exploit big data for solving prediction, synthesis, and discovery problems in materials sciences, molecular biology, health informatics, and intelligent manufacturing. Of particular interest is developing data-driven AI algorithms for predicting properties and structures of proteins and materials and generative deep learning models for discovering and designing new materials for applications such as batteries and thermal materials.

Discovery of high performance materials such as lithium-ion battery electrolytes or electrodes has a huge impact on society. Such processes are very challenging and time-consuming, which are usually addressed in “trial-and-error” Edisonian way with tedious experiments of which the successes strongly depend on the human expertise and luck. Compared to the almost infinite design space of inorganic materials, the largest database that collect structure information of inorganic materials has only about 200,000 inorganic materials deposited. To overcome this obstacle, Dr. Hu’s team has developed a novel generative machine learning algorithm based on genetic adversarial neural network (GAN) for inverse composition design of inorganic materials. This model is able to learn the intricate and implicit composition rules right from the known materials in the database and generate chemically valid materials recipes or compositions that may be synthesized. By repeatedly running their generation models, Dr. Hu's team has generated more than 2,000,000 materials compositions with low predicted formation energy indicating high probability of being synthesizable, which can greatly enlarge the screening space for seeking new materials with desired function. Here is a demo video of the model showing how it generates 200,000 new materials. This work was partially supported by the SC EPSCoR GEAR-CRP grant in 2019.

A second area of interest is the machine learning algorithms for predicting materials properties from either composition or structures. Read more...

In addition to government websites providing guidance and information about the novel coronavirus (COVID-19), such as the Centers for Disease Control and Prevention (CDC) and the SC Department of Health and Environmental Control (DHEC), below is a partial list of additional resources that might be of interest to our readers who track data and prediction models. 

General Information:
Coronavirus Information from NSF
COVID-19 Information and Resources from Google
Working from Home from Science Magazine

Data:
Visual COVID-19 Data from Johns Hopkins University
COVID-19 World Data from Worldometers.info

Prediction Models:
COVID-19 Predictions from the Institute for Health Metrics and Evaluation
State and County Prediction Model from COVID Act Now. This is the source of the US County Map shown.