• Subscribe

Supporting research with HPC in New Zealand

"Being able to get work done faster - completing computations in a day rather than months - is pretty fundamental to many areas of research," says Jones. Image courtesy Dave Allen.

Nick Jones is the director of New Zealand eScience Infrastructure (NeSI), which provides high-performance computing and support systems to New Zealand's researcher community. iSGTW speaks to Jones about the work that NeSI does and the upcoming eResearch NZ 2014 conference.

What does NeSI do and why is it important for New Zealand's researcher community?

NeSI offers new skills and capabilities to researchers who need advanced computing for their research. It's a big change for New Zealand's researchers: We've previously had smaller institutional resources focused on specific communities, whereas now the specialized skills we're providing are available nationally to all researchers and this comes with a support reputation that is second to none.

What did New Zealand's researchers do in the past if they required high-performance computing?

From what we hear in our discussions with researchers, they designed experiments that fit within the available resources. Those that had serious computing needs typically collaborated offshore, finding a colleague with whom they would build a working relationship and establish a way to be able to do their research internationally.

Is NeSI already making a difference for researchers?

Being able to get work done faster - completing computations in a day rather than months - is pretty fundamental to many areas of research. This definitely increases productivity. Having NeSI's platforms available is also starting to increase the complexity of the research problems that people can approach. Researchers want to be able to include the finer-grained picture and pick up the nuances and the subtleties in the way a system works. Very few could have done that before in New Zealand.

New Zealand's government recently instigated a series of National Science Challenges. Can you tell us a bit about these challenges and what they will mean for NeSI?

The National Science Challenges were conceived about two years ago. There are ten challenges and they each have a single national organization formed from the science and research communities to respond to each of them. It's a brave initiative in the sense that it has evolved very rapidly, whereas research collaborations typically evolve very slowly. Over the last 20 to 25 years, we've seen strongly competitive incentives in the sector. So now developing a set of collaborative incentives has been an interesting process both to observe and take part in. The sense that we're going to have these collaborative initiatives with a ten-year perspective is creating new opportunities to explore interdisciplinary projects and is providing a clearer sense (certainly on the infrastructure side) of the sort of common needs that research communities might have.

Speaking of scientific challenges, NeSI is organizing and co-hosting the eResearch NZ 2014 conference in July. Can you tell us a little about the event?

This year we're co-hosting with the wonderful people at the University of Waikato, New Zealand. The University of Waikato was the starting point for internet connectivity in New Zealand (beautifully documented online in Down to the Wire) and it's also one of the homes of data science in New Zealand, as it is the home of the open-source Weka data mining software. We'll have people from organizations like the Research and Education Advanced Network New Zealand (REANNZ) there talking about the major investments in our national and international connectivity, as well as the opportunities this opens up for us, alongside educators, researchers, and those ubiquitous and sexy data scientists! Also, for the first time, we've got several government agencies presenting their key work consolidating administrative data from multiple agencies onto national analytics platforms to support evidence-based decision-making. It should be a rich mix of attendees and presenters.

Finally, who will be giving the keynote talks at eResearch NZ 2014?

Kaitlin Thaney is one of our keynote speakers. She has always come across as someone that's doing very innovative work. She is currently the director of Mozilla Science Lab, an organization that goes right back to the roots of the world wide web, with its origins in high-energy physics and thinking about how to share data and information between scientists distributed around the world. Kaitlin is looking at that and thinking about what an open web looks like for research: What does the web look like when it's facilitating the free exchange and integration of ideas?

Bryan Lawrence is our other keynote speaker. He plays a key leadership role internationally in the areas of data, modeling, and computation associated with environmental research. His community is at the center of the universe when it comes to data and models for the Intergovernmental Panel on Climate Change (IPCC) reports. So, Bryan is right at the heart of the evolution of the infrastructure to support climate research around the world, and has hands-on insights to share on the future of globally collaborative research.

eResearch NZ 2014will be held at the University of Waikato in New Zealand from 30 June to 2 July.

Join the conversation

Do you have story ideas or something to contribute? Let us know!

Copyright © 2018 Science Node ™  |  Privacy Notice  |  Sitemap

Disclaimer: While Science Node ™ does its best to provide complete and up-to-date information, it does not warrant that the information is error-free and disclaims all liability with respect to results from the use of the information.

Republish

We encourage you to republish this article online and in print, it’s free under our creative commons attribution license, but please follow some simple guidelines:
  1. You have to credit our authors.
  2. You have to credit ScienceNode.org — where possible include our logo with a link back to the original article.
  3. You can simply run the first few lines of the article and then add: “Read the full article on ScienceNode.org” containing a link back to the original article.
  4. The easiest way to get the article on your site is to embed the code below.