eScience 2012 will include workshops on 8-9 October. In addition to the Microsoft eScience Workshop, other workshops were solicited in the Call for Workshops. Six workshops were accepted:
WORKSHOP | Monday 8 October
Historically, high-performance computing (HPC) has enabled computationally intensive simulations performed in batch mode on a small number of standalone supercomputers, shared among users selected for their computing skills as much as for expertise in their own disciplines. There has been a sustained effort over the past decade to broaden this model by deploying a wider variety of HPC systems tied into emerging national and global cyber-infrastructure (CI), yet only a small fraction of the resources fielded by HPC-based CI programs such as the eXtreme Science and Engineering Discovery Environment (XSEDE) is currently used by people who are not members of communities that have used supercomputing centers since the 1980’s.
Given the digital instruments and methods that are revolutionizing biological, environmental, and physical sciences, as well as the promise of important benefits to social sciences and the arts and humanities, XSEDE is undertaking a proactive effort to work with members of these communities to identify barriers and to develop projects that show how to effectively overcome them.
In this context, the goal of this workshop is to discuss examples of successful projects as well as barriers and practical approaches to overcoming them. The desired outcome is an improved understanding of actions that should be taken by the various stakeholders in order to enable a wide spectrum of practitioners to use HPC resources as part of their work and data flows, and to establish an informal network of people and communities interested in this outcome.
WORKSHOP | Monday 8 October
Social networking is profoundly changing the way that people communicate and interact on a daily basis. As eScience is inherently collaborative, social networks can serve as a vital means for supporting information and resource sharing, aiding discovery of connected individuals, improving communication between globally dispersed individuals, and even measuring scientific impact. Consequently, eScience systems are increasingly integrating social networking concepts to improve collaboration. For example researcher profiles and groups exist in publication networks, such as Google scholar and Mendeley, and eScience infrastructures, such as MyExperiment, NanoHUB and GlobusOnline all utilize social networking principles to enhance scientific collaboration. In addition to incorporating explicit social networks, eScience infrastructures can also leverage implicit social networks extracted from relationships expressed in collaborative activities (e.g. publication and grant authorship or citation networks).
This workshop aims to bring together researchers from a diverse range of areas to establish a new community focused on the application of social networking to analyze and improve scientific collaboration. There are two complementary areas of focus for this workshop 1) how to efficiently share infrastructure and software resources, such as data and tools through social networks, and 2) how to analyze and enhance collaboration in eScience through both implicit and explicit social networks, for example analyzing scientific impact through citation networks or improving collaboration by associating data and tools with networks of publications and researchers.
WORKSHOP | Tuesday 9 October
One of the most pressing issues for computational science is the creation of software and data that is sustainable and reusable. Today’s researchers are using more and more complex software stacks that is produced in increasingly ad hoc ways [Mer10]. Software development has become more and more common (current estimates state that 45% of scientists spend more time developing software now than they did 5 years ago [Han09]), particularly within e-Science projects which often have a mix of research and software development roles. At the same time, stakeholders are asking researchers to consider their software sustainability as part of their data management plans, with “Software as Infrastructure” being adopted as a model [EPSRC11, NSF11]. The management, curation and development of scientific software – which has often started life as a rough prototype – is a key area to support to enable high quality research.
This workshop will focus on the issues relating to the development and maintenance of software that can endure past the limited periods of defined project durations and project funding, and go beyond software engineering best practice to address aspects of cultural, organisational and policy change. By bringing together all those with an interest in ensuring the longer term development and use of software for research, including researchers, developers, research computing specialists, software engineers, infrastructure providers, facilitators, and funders, the goal of this workshop is to understand what software practices can be successfully applied and which lead to long-term improvements in the development of software for e-Science.
As part of the workshop we will also be running a panel on the topic of culture change in software management for research, featuring invited speakers from a variety of disciplines who have experienced or instigated these changes, to talk about their real life experiences of scientists of what worked and didn’t work for them.
WORKSHOP | Tuesday 9 October
New techniques are being developed to assist in the management and processing of the massive amounts of scientific data generated by experimental detectors.
Systems using these techniques are being developed by computer scientists in multiple places to make data more accessible, enable real-time analysis, assist in the interpretation of the data, enable reproduction of the experiment, and to generate reports. Standardization of these systems means that scientists from diverse organizations can cooperate more effectively, leading to new research outcomes and better research practices.
WORKSHOP | Tuesday 9 October
Modern science is generating large amounts of data and timely data transfers are a crucial aspect for the emerging international scientific collaborations. Infrastructural resources such as instruments, storage, computing facilities, and visualization (e.g. tiled displays, 4K video, holography) are increasingly used and shared by researchers at geographically distributed locations.
High-speed networks enable the use and sharing of these resources over long distances. Especially when point-to-point connections with a high, guaranteed bandwidth and low latency and security (aka lightpaths) are used.
In many countries lightpath services are offered as a service of the National Research and Education Networks (NREN’s). Many NREN’s participate in GLIF, the Global Lambda Integrated Facility, to provide lightpaths internationally as an integrated facility to support data-intensive scientific research. NRENs and GLIF have been a motor for novel usecase of the networks.
WORKSHOP | Monday 8 October
In addition, one tutorial was proposed and accepted:
TUTORIAL | Tuesday 9 October