Interview: Dr. Subit Chakrabarti, Team Lead, Remote Sensing and Geoscience @ Indigo
Subit is a data scientist with an extensive background in the development and application of machine learning algorithms to large scale earth imagery from satellites, unmanned aerial vehicles and aircraft. He leads the remote sensing and geospatial data science team at Indigo Agriculture—an interdisciplinary team of scientists and engineers working to build models at scale that can detect causal relationships among key agricultural drivers, practices and outcomes in the United States, Brazil, Argentina, and the European Union. Prior to Indigo, he was a data scientist at Telluslabs where he developed computer vision techniques for mapping crop species and crop yield in North and South America using satellite imagery.
Subit received the Ph.D. degree in Electrical and Computer Engineering from the University of Florida and a B.Tech in Electronics Engineering from the West Bengal University of Technology in India.
High Performance Computing: Allocation, Jobs, Scheduling, and Front-End
— Matt Dwyer, U.S. Army CCDC, Army Research Laboratory & CIS, UD
This talk will cover a brief introduction to the Caviness HPC environment including how to allocate interactive and batch workloads, executing distributed workloads using MPI, and how to configure port forwarding to connect to front-end applications running on compute nodes.
Matt received the M.S. in Computer Science with a Concentration in Data Science from Colorado Technical University and a B.S. in Computer Science from Lynchburg College. Alongside his career as a computer scientist for CCDC U.S. Army Research Laboratory, Matt is currently in the first year of a Ph.D. program in the Department of Computer and Information Sciences at the University of Delaware. He has a broad area of focus that includes distributed systems, virtualization, data science, machine learning, and blockchain. Matt has over 5 years of career experience with High Performance Computing systems at Los Alamos National Laboratory (DoE) and the CCDC U.S. Army Research Laboratory (DoD). He has extensive experience using a variety of distributed workload management technologies on HPC systems including PBS, LSF, and Slurm.