Multidisciplinary Research and Education on Big Data + High-Performance Computing + Atmospheric Sciences

Part of NSF Initiative on Workforce Development for Cyberinfrastructure (CyberTraining)

CyberTraining Spring 2018


Introduction

We conducted face-to-face training to 16 participants (5 from computing discipline, 6 from physics discipline, 5 from mathematics discipline). Among them, we have 1 master student, 8 PhD students, 2 post-doc, 3 junior faculty/scientists and 1 senior faculty/scientist. Each team successfully produced a technical report. Two reports extended have been extended for peer-reviewed conference/journal publications. Evaluation shows the training program is very useful to participants, especially the program provides a unique experience for them to work with peers in other disciplines on a research project.


Projects

Team 1 Project: Numerical Methods for Parallel Simulation of Diffusive Pollutant Transport from a Point Source

Team members:
Noah Sienkiewicz, Department of Physics, UMBC
Arjun Pandya, Department of Information Systems, UMBC
Tim Brown, Department of Mathematics and Statistics, UMBC
Graduate Assistant:
Carlos Barajas, Department of Mathematics and Statistics, UMBC
Faculty Mentor:
Matthias K. Gobbert, Department of Mathematics and Statistics, UMBC
Deliverables:
Implementation Source Code at Github Repository
Presentation Slides
Technical Report
Peer reviewed publication: In preparation

Team 2 Project: Benchmarking on Parallel Cloud Type Classification from Satellite Data

Team members:
Carlos Barajas, Department of Mathematics and Statistics, UMBC
Lipi Mukherjee, Department of Physics, UMBC
Pei Guo, Department of Information Systems, UMBC
Susan Hoban, Joint Center for Earth Systems Technology, UMBC
Faculty Mentor:
Daeho Jin, GESTAR, USRA, and NASA GSFC
Aryya Gangopadhyay, Department of Information Systems, UMBC
Jianwu Wang, Department of Information Systems, UMBC
Deliverables:
Implementation Source Code at Github Repository
Presentation Slides
Technical Report
Peer reviewed publication: Benchmarking Parallel Implementations of K-Means Cloud Type Clustering from Satellite Data. Accepted by the International Symposium on Benchmarking, Measuring and Optimizing (Bench’18), 2018.

Team 3 Project: Mineral Dust Detection using Satellite Data

Team members:
Peichang Shi, Department of Information Systems, UMBC
Qianqian Song, Department of Physics, UMBC
Janita Patwardhan, Department of Mathematics and Statistics, UMBC
Faculty Mentor:
Zhibo Zhang, Department of Physics, UMBC
Jianwu Wang, Department of Information Systems, UMBC
Deliverables:
Implementation Source Code at Github Repository
Presentation Slides
Technical Report
Peer reviewed publication: In preparation.

Team 4 Project: Spatio-Temporal Climate Data Causality Analytics – An Analysis of ENSO’s Global Impacts

Team members:
Hua Song, Joint Center for Earth Systems Technology, UMBC
Jing Tian, Department of Mathematics, Towson University
Jingfeng Huang, NOAA NESDIS STAR
Faculty Mentor:
Zhibo Zhang, Department of Physics, UMBC
Jianwu Wang, Department of Information Systems, UMBC
Deliverables:
Implementation Source Code at Github Repository
Presentation Slides
Technical Report
Peer reviewed publication: Spatio-temporal climate data causality analytics – an analysis of ENSO’s global impacts, in Proceedings of the 8th International Workshop on Climate Informatics, 2018.

Team 5 Project: The Impacts of 3D Radiative Transfer Effects on Cloud Radiative Property Simulations and Retrievals

Team members:
Yunwei Cui, Department of Mathematics, Towson University
Meng Gao, Department of Physics, UMBC
Scott Hottovy, Department of Mathematics, US Naval Academy
Graduate Assistant:
Chamara Rajapakshe, Department of Physics, UMBC
Faculty Mentor:
Zhibo Zhang, Department of Physics, UMBC Deliverables:
Implementation Source Code at Github Repository
Presentation Slides
Technical Report
Peer reviewed publication: In preparation.

Some testimonials from anonymous evaluations

  • “I am exposed with more data oriented tools, either big data and machine learning. It is very beneficial in the long term.”
  • “It opened one door to big data and will help me with my dissertation research.”
  • “This course motivated me to learn more about big data, machine learning and HPC, and apply them to my research field.”
  • “It has open a new line of research that I'm excited to dive deeper into.”
  • “With better understanding of the HPC and Big Data technology, we will think very seriously on how to apply HPC and Big Data techniques to our work activities and algorithm operational processing.”