Steven I. Gordon

Influence of neighborhood types on trip distances: Spatial error models for Central Ohio

ABSTRACT This study examines the relationships between land-use, transportation infrastructure, household, and individual characteristics and the resulting average and daily trip distances using data from the 1999 Mid-Ohio Area Household Travel Survey. Spatial error models are developed to analyze the determinants of average and daily trip distances at the person level. First, new neighborhood categories are created using K-means cluster analysis and several land-use and built-environment variables. Then, these new neighborhood categories (such as central city residential areas, medium-density suburbs, low-density suburbs, etc.) are used as independent variables to explain the resulting average and total trip distances, while controlling for sociodemographics, access to transit and bicycle facilities, and spatial autocorrelation. The results indicate that the residential location characteristics are a significant factor in explaining trip distances; people who live in areas that are away from urban centers and with a low mix of employment and population travel longer distances. For the Central Ohio Region, residing in lowest-density suburbs may add up to 44% to average trip distances and 33% to daily trip distances.

Applying verification, validation, and accreditation processes to digital libraries

We propose to address the issue of quality of digital library objects in the Computational Science Education Reference Desk by applying a verification, validation, and accreditation workflow to the review of learning objects

Providing a supported online course on parallel computing

Learning the principles of computational modeling and parallel computing requires more than a short workshop. Workshops generally run from a few hours to a few days and are therefore limited in the amount of material that can be covered. In addition, it is more difficult for participants to retain large amounts of new material under the time pressures of a workshop. Deeper understanding of such complex materials can come from more traditional academic courses. Yet, many institutions either lack the expertise or the curriculum flexibility to offer such courses. In the spring of 2013 we offered the equivalent of a full semester course entitled Applications of Parallel Computing as an open, online course in an effort to address these issues. The course was offered over a period of thirteen weeks using materials captured from the University of California Berkeley course CS267. Enrollment was initially limited to 345 students. Creating and implementing the course involved decisions in several areas: design of the instructional materials, creating an environment to run programming assignments, support mechanisms for the large number of students taking the course, and automatic grading of assignments. In this session, we will present a summary of the experience in addressing these questions along with an evaluation of the course outcomes.

Advancing Computational Science Education through Xsede

Theres a great need for computational science programs that prepare the current and next generation of researchers, educators, and practitioners to effectively utilize digital services in support of science, technology, engineering, and mathematics. Xsede helps facilitate the founding and expansion of such programs.

Architecting an autograder for parallel code

As parallel computing grows and becomes an essential part of computer science, tools must be developed to help grade assignments for large courses, especially with the prevalence of Massive Open Online Courses (MOOCs) increasing in recent years. This paper describes some of the general challenges related to building an autograder for parallel code with general suggestions and sample design decisions covering presented assignments. The paper explores the results and experiences from using these autograders to enable the XSEDE 2013 and 2014 Parallel Computing Course using resources from SDSC-Trestles, TACC-Stampede and PSC-Blacklight.

Building a Community of Practice to Prepare the HPC Workforce

Abstract It has been well documented for more than 30 years, that significantly more effort is needed to prepare the HPC workforce needed today and well into the future. The Blue Waters Virtual School of Computational Science (VSCSE) provides an innovative model for addressing this critical need. The VSCSE uses a Small Private Online Course (SPOC) approach to providing graduate level credit courses to students at multiple institutions. In this paper, we describe the rationale for this approach, a description of the implementation, findings from external evaluations, and lessons learned. The paper concludes with recommendations for future strategies to build on this work to address the workforce needs of our global society.

XSEDE Training: Achieving Access and Inclusion

An XSEDE strategic goal is to extend use of high-end digital services to new communities by preparing the current and next generation of scholars, researchers, and engineers in the use of advanced digital technologies via training, education, and outreach. The mission of XSEDEs Under-Represented Community Engagement (URCE) program is to raise awareness of the value of advanced digital research services and recruit users from new communities. In collaboration with XSEDE training and education programs, the URCE program works with faculty and students that are non-traditional users of XSEDE resources and helps them utilize XSEDEs advanced digital research services and ecosystem. Over the past five years, the URCE program organized and facilitated training across the country at a variety of institutions ranging from small private Historically Black Colleges and Universities (HBCUs) such as Philander Smith to the University of Texas at El Paso, a large public Hispanic Serving Institution. Every URCE-led training workshop included extensive formative and summative evaluation, including longitudinal tracking of participant progress in engaging with XSEDE services in order to identify growth and persistence as well as barriers and opportunities. 85% (209/245) of URCE-led training event participants were first time XSEDE training registrants. After attending, 14% of attendees obtained access to XSEDE resources and more than 18% registered for additional training activities. This paper presents the strategies used to achieve these results.

Extending access to HPC skills through a blended online course

Extending expertise in parallel computing is critical to all those using high performance computing to gain insights into science and engineering problems. Many campuses do not offer such a course because of course load limits, a lack of faculty expertise, and/or lack of access to appropriate computing resources. MOOCs for this type of course are difficult to scale both because of constraints on computing resources as well as the need for individual attention with programming problems. Using a blended online course with collaborating faculty that offer academic credit for their students, we have been able to facilitate course participation at many institutions that might not otherwise have covered the topic. This has had a significant benefit for both the faculty and students. Our paper summarizes the nature of these impacts and offers some insights on best practices for extending technical courses to multiple institutions.

Creation of interdisciplinary programs in computational science (abstract only)

We present the components of model undergraduate and graduate programs in computational science that have been developed as part of the XSEDE Education Program. The models serve as a template to assist institutions in creating formal programs in computational science that span multiple disciplines including the sciences and engineering, mathematics, computer science, and, more recently, social sciences. The aim of the services is to encourage more institutions to consider computational science as a part of their core curriculum and to reduce the time it takes to integrate new materials and programs. The services provided include campus visits to explore program creation in the context of the interests of the current faculty conducting research and instruction that includes computational modeling. XSEDE also sponsors professional development workshops for faculty and students. These include one day to full week workshops focusing on computational science education in various disciplinary areas as well as technical training that focusing on a variety of computational tools and methods. XSEDE has also created an index to sharable instructional materials focused on building a virtual community interested in computational science education. The index will allow faculty and students to find reviewed examples of models, exercises, and instructions that can be incorporated into current and future courses.

HPC university: getting information about computational science professional and educational resources and opportunities for engagement

This paper describes the HPC University website and how it can be utilized to obtain information about computational science and high performance computing education and training resources, opportunities for student internships, shared educational materials, and news and information about HPC related events. The site provides access to a variety of materials relating to HPC events and education and training at a single site.