Computational Sustainability at AAAI-12

Next week is the next event in the summer of CompSust conferences. The Twenty-Sixth Conference on Artificial Intelligence (AAAI-12) is being held next week (July 22-26) in Toronto, Canada. So here’s a little preview of what to expect and how to get the most out of it.

The schedule for the entire conference can be found here. To get a taste of the kind of topics being covered you can take a look at  this excellent review of the papers from last year (complete with an handy chart) by Douglas Fisher from Vanderbilt University. Note that one of the two best papers from the entire conference was from the CompSust Track (“Computational Sustainability and Artificial Intelligence Track: Dynamic Resource Allocation in Conservation Planning” by Daniel Golovin, Andreas Krause, Beth Gardner, Sarah J. Converse, Steve Morey).

CompSust track papers from last year's AAAI-11. Courtesy of Douglas Fisher.

There isn’t a handy chart for this year’s conference yet but a quick look at the topics shows that many of the same topics will be covered as well as some new additions. A brief look at the sustainability topics includes: modelling climate change, ocean eddy monitoring, air pollution, forest management, wildlife conservation design, invasive species and infectious disease control,  power grid management and battery output prediction and control. Just from the titles the range of computational methods used includes at least : linear programming, Q-learning, Lagrangian relaxation, Inverse RL and Bayesian ensemble prediction.

Of course the point of having this track at the AAAI conference is to help broaden the field of AI research and showcase a large cluster of multi-disciplinary collaboration that is already going on. I can tell you that from last year’s conference, the CompSust sessions have a different feel than the other parallel tracks since there are a variety of computational methods being discussed within the same session whether it be on energy management or ecological planning. So if you want a change of pace from the method focussed tracks consider stopping by a CompSust session.


This conference will also be the launch of the official Twitter account for the Computational Sustainability field, @compsust. So follow us at @compsust for the latest updates on the conference or search for the #compsust or #aaai12 tags for posts about what interesting research people are talking about and share your own thoughts.


For discussion that needs more than 140 characters  you could also sign up for the Google+ event for the whole AAAI conference where you can discuss anything going on and meet up with people.

Mailing List

If you aren’t already on the yahoo groups mailing list for computational sustainability make sure you subscribe. There are announcements about conferences, journal deadlines and relevant science news for the community.

That’s all for now. See you next week!

Tusind Tak Copenhagen!

So the CompSust2012 Conference is over and our mixed band of computer scientists, ecologists, operation researchers, engineers, urban planners (and more) are dispersing back to their homes in Denmark, Jordan, Uganda, Italy, the Netherlands, France, Germany, Ireland, the UK, the Netherlands, Switzerland, Canada and the USA (and that’s just people I talked to, who am I missing?).

I think everyone would agree it a was a very well run conference and very productive. Over powerpoint slides, posters, food and even beer we all gained insights into challenging computational and sustainability problems and topics we probably didn’t know about before we came.

We all know finding ways to improve the sustainability is full of important and challenging problems, but it a different thing to see exactly what people are struggling with around the world and what solutions they have found.

For example, did you know that…

  • if you count of all the wireless devices people have access to that the locations of about one third humanity is knowable in principle? Paul Luckowicz described this and other amazing facts about what he calls our digital shadows to us during his Master class discussion on Wednesday. This data can be used for good or for ill but it will be used; so it’s best to start thinking and planning for it, that’s what his FuturICT project is looking at.
  • the widespread use of Linear programming techniques for policy making was essentially kickstarted in the 1970s by the success of these methods at predicting the end of oil independence in US as demand grew? Warren Powell gave a rousing and thought provoking Master class seminar on the broad area of stochastic optimization in dynamic domains and described how he believes a broad range of methods from different communities can work together if there is increased communication between researchers.
  • in Uganda, smart phones with internet connectivity are becoming so common it is assumed that most research projects using technology to help with sustainability will utilize them? So that’s what John Quinn is doing. His machine learning group in Uganda is creating solutions for automated data collection and disease diagnosis using Android phones to augment the restricted access to trained experts on the ground. Their applications range from malaria detection, to plant disease spread to traffic monitoring.
  • owning and powering a fully electric car uses about as much power as an entire household? Hartmut Schmeck pointed out that the concern is not just that this costs a lot of money or uses energy, but also puts a huge new load on power systems already at their maximum level at the local distribution level. Several talks friday morning by Nick Jennings, Hartmut Schmeck and Holger Hermanns described these kinds of power grid challenges in the UK, Germany and elsewhere. The good news is there are ways to make this manageable if we are smart about it. The really good news is there are challenging computational research problems about how to do that.
  • some day your house might be able to learn it own customized weather forecast? It will do this by tracking the actual weather outside and learning how it drifts from the predicted regional forecasts, allowing your house to better manage it’s energy usage. This is one of the projects Nick Jennings is working which he talked about in his plenary talk.
  • some day consumers may be able to band together to demand better or more sustainable policies from their service providers such as power companies? Well, that’s already happening and researchers are using the techniques of co-operative game theory to work out how it would work.

This is just a sample of some of the topics from the plenary talks alone, there were also great parallel track talks on energy management, species distribution modeling and conservation planning, water management, social analysis and incentives and how to integrate computational sustainability into computer science education.

The full program can be found here and many of the slides from talks will be up on line at the conference website when they become available.

Finally, I’ll end this little summary where Carla Gomes began the conference, with her inspiration for the field of Computational Sustainability. She described it as being part of the evolution of Computer Science into what could be considered a third age. The first age included working out the practicalities or hardware, computation and networks; the second included, among other things, the creation of the powerful abstractions of artificial intelligence and machine learning. The third age involves these and other advances of computer science reaching out an integrating with other disciplines to bring the power of computational thinking to bear on the world’s most challenging problems.

Few problems are more challenging than how to make our growing civilization sustainable on the finite resources of the Earth; but that is what Computational Sustainability faces and it looks like we’re well on our way to contributing to meeting this challenge.

If you went to CompSust2012 keep the discussion going :

CompSust’12 Conference underway

It’s already Thursday afternoon here in Copenhagen, and CompSust’12 is off to an exciting start. Yesterday we had a terrific turn out for the 1st International Master Class on Computational Sustainability.  Today our computational sustainability crowd grew with the official start of the conference. The panel about growing and nurturing the computational sustainability community yielded a number of helpful ideas and suggestions, and we hope many of you who participated will be joining us here on the blog soon. If you’re in Copenhagen right now, Mark Crowley has invited any potential bloggers to chat with him, and you’re welcome to talk with any of us associated with the Institute for Computational Sustainability as well. If you’re unable to join us in Copenhagen, we hope to have slides posted soon so you can join in via the internet!

CompSust Summer Conference Preview

It’s going to be an exciting summer.

There is tremendous research happening around the world attempting to bridge the gap between computational fields such as artificial intelligence, constraint programming, optimization and machine learning with scientists carrying out research in fields such as ecology, sustainability, climate systems, power planning.

This collaborative research goes under many different names such as Computational Sustainability, Ecosystem Informatics, Sustainable Computing and Climate Informatics but they all share the idea that there is enormous potential sitting at the intersection between the latest computational research and the effort to improve the sustainability of human society in the broadest possible sense.

In an effort to get this blog kickstarted I thought I’d write the itinerary for some very ambitious CompSust researcher who wanted to see it all over the summer. (Although I suppose you should be sure to buy lots of carbon offsets…)  If there are others I’m missing (likely), feel free to let me know in the comments.

The first stop would have been a few weeks ago in San Diego at the International Green Computing Conference which looked at both sides of the Computing/Sustainability coin by bringing together researchers in the “fields of sustainable and energy-efficient computing, and computing for a more sustainable planet”.

Next up, you could head over to Edinburgh for ICML2012 at the end of June. ICML will have some focus on machine learning for sustainability including an invited talk by David MacKay on using machine learning to make sure the challenges of climate change and sustainable energy management are faced head on with reliable numbers.

The following week, it’s a short hop over to Copenhagen, Denmark for Computational Sustainability 2012 which starts with a day of Master Class Seminars by leaders in the field on existing results and problem domains followed by two days of the latest research. The schedule isn’t out yet but the topics promise to include research on computational approaches to land use planning, climate modelling and natural resource and energy planning.

AAAI2012 is in Toronto this year and once again running a special track on Computational Sustainability. A brief look at the sustainability topics includes: modelling climate change, ocean eddy monitoring, air pollution, forest management, wildlife conservation design, invasive species and infectious disease control,  power grid management and battery output prediction and control. Just from the titles the range of computational methods used includes at least : linear programming, Q-learning, Lagrangian relaxation, Inverse RL and Bayesian ensemble prediction.

In September you could then head over to Boulder, Colorado for the Climate Informatics 2012 conference which will bring together researchers in machine learning working specifically on the problems of climate modelling. Part of the focus is to brainstorm ideas on how to accelerate progress on climate change questions as well as discover challenging new domains to push existing machine learning approaches.

Finally in October (ok, this is well out of the summer, but still) there is the International Workshop on Constraint Reasoning and Optimization for Computational Sustainability (CROCS-12) in Quebec City. You even still have time to submit for that one, Quebec City should be very nice in October…before the snow comes.

Some other events can also be found on the CompSust page at the CRA.

I’m planning on writing up some highlights from the CompSust2012 and AAAI conferences this summer so if there is something fantastic you see there, at another conference or elsewhere let us know in the comments.


Welcome to the new computational sustainability blog! This blog
is intended to encourage interaction among researchers with
various interests connected to computational sustainability. The
goal is to bring together a community of researchers, educators,
policy makers, and students interested in applying and developing
state of the art techniques from computational sciences to help
balance environmental, economic, and societal needs for
sustainable development.

This is also a terrific opportunity to announce the 3rd International
Conference on Computational Sustainability, to be held in July
2012 in Copenhagen, Denmark. Please visit for more
details, and do take advantage of this opportunity to use the
blog to communicate with others interested in computational

Computational Sustainability Community Blog

Skip to toolbar