Program

Friday, February 3th

3:15 – 4:00 pm: Coffee Hour Refreshment

• Walker 319 

4:00 – 5:00 pm: Coffee Hour Colloquium with Johnathan Rush

• Title: SKOPE: A CyberGIS Approach for Understanding Past Environments
• Walker 112 

Saturday, February 4th

09:50 – 10:00 am: Opening Remarks for the Workshop

• Walker 109

10:00 – 11:00 am: Lecture: Introduction to CyberGIS (+ Q&A)

• Walker 109
• Instructor: Johnathan Rush
• Overview of cyberGIS, describe exemplary projects, and discuss educational challenges and opportunities.

11:00 am – 12:30 pm: Lunch Break

• Walker 319 

12:30 – 2:30 pm: Tutorial: Introduction to High Performance Computing

• Walker 109
• Instructor: Johnathan Rush
• Participants will log on to ROGER, the cyberGIS supercomputer, and get hands-on experience on the use of High Performance Computing (HPC) resources. ROGER uses common batch computing standards, and skills practiced in the tutorial are transferable to computing resources at Penn State and nationally through XSEDE. Core concepts include the Bash shell, the shared filesystem, the job queue, geospatial data handling, and visualization in research computing.

2:30 – 3:00 pm: Coffee Break

3:00 – 4:30 pm: Tutorial: Parallel Geospatial Analysis

• Walker 109
• Instructor: Johnathan Rush
• Participants will learn recognize opportunities for speeding up data processing through parallelism. Techniques will be practiced in both Jupyter Notebooks hosted on the cloud computing system, and implemented at scale on the batch computing systems.

4:30 – 5:00 pm: Discussion: CyberGIS Research and Applications

• Walker 109
• Chair: Johnathan Rush
• Discussion and wrap-up on the techniques practiced in the tutorials, and discuss potential uses of cyberGIS technology in PSU research projects.

5:30 – 7:00 pm: Banquet Dinner

• IST Bridge (next to Au Bon Pain)

Sunday, February 5th

9:00 – 9:20 am: Talk: Building a Big Data Analytics Work Force in iSchools

• Walker 112
• Speaker: Jungwoo Ryoo
• Abstract: The big data analytics market is growing rapidly, and so is its demand for qualified big data professionals. We are developing learning modules for educators who are interested in exposing students to big data career paths. Ultimately, our goal is to grow the size of the big data workforce sufficiently to meet the increasing demand in both industry and academia by encouraging students to prepare themselves for and pursue big data careers.

9:30 – 10:45 am: Tutorial: Data Wrangling with R

• Walker 109
• Instructor: Arif Masrur
• Abstract: With the advent of bigdata, data wrangling has become essential for making messy datasets usable for analysis and visualization. Over the years, different platforms (e.g., MongoDB, Trifacta, etc.) and programming environments (e.g., R) have been developed and used for this purpose. Here, we’ll leverage popular R programming environment to learn essentials of data wrangling. RStudio will be used as an integrated development environment (IDE). The tutorial will first attempt at providing some basics of working with data in R and then walk through some data wrangling processes and techniques.
• Tutorial Outline:
  • Introduction to Data Wrangling
  • Introduction to R Environment
    • Basics (Installing R and RStudio, Installing and loading packages, etc.)
    • How to work with different data types
    • Manage data structures
    • Import, scrap, and export data
  • Efficient code creation
  • Wrangling data

10:45 – 11:00 am: Coffee Break

11:00 am – 12:00 pm: Keynote Speech: Data Science Strategies for Business Success

• Walker 109
• Instructor: Chul Sung (IBM Data Scientist)
• Abstract: As cloud computing has seen rapid growth due to its massive scalability in storage and computing power, big data burst on the scene in the first decade of the 21st century. Everyone understands its power and importance in terms of the outcome and financial benefits, but many vacillate to bring the actionable steps and resources required to handle it effectively. In this talk I will introduce how major companies are using big data and bring the actionable insights. Taking such a role as a data scientist I will emphasize practical techniques for working with large-scale data. Specific topics covered will include statistical modeling and machine learning, data pipelines, “big data” tools, and case studies.

12:00 – 1:00 pm: Lunch Break

• Walker 319 

1:00 pm – 3:00 pm: Tutorial: The Ultimate Beginner’s Guide to Deep Learning in Python with Keras

• Walker 109
• Instructor: Eun-Kyeong Kim, Liping Yang
• In this tutorial, we will go through a part of the following tutorial series:
  • Keras Tutorial: The Ultimate Beginner’s Guide to Deep Learning in Python https://elitedatascience.com/keras-tutorial-deep-learning-in-python
  • The recommended prerequisites for this guide are (as this tutorial mentions):
    • Understanding of essential machine learning concepts
    • Python programming skills
  • Please set up your environment ahead of the tutorial:
    • https://elitedatascience.com/keras-tutorial-deep-learning-in-python#step-1
    • If you can’t, we will shortly help you install at the very beginning of the tutorial.

3:00 – 3:15 pm: Coffee Break

3:15 – 4:15 pm: Tutorial: Data Visualization with R

• Walker 109
• Instructor: Mark Simpson
• Abstract: This R tutorial will give an introduction to data visualization with R, both standard statistical graphics and mapping spatial data. It will cover R’s default plotting, basic usage of the powerful ggplot2 package, and the essentials of managing and mapping of spatial data with the GISTools package.