Computational Sustainability | CSE 8803 CompSust
Semester: Spring 2014
Time: TR 12:05 - 1:25pm
Location: Howey (Physics) N210
Instructor: Bistra Dilkina
Email: firstname.lastname@example.org (best way to contact me)
Office hours: Thur 2-3:30pm in my office Klaus Bldg. 1304 (or by appointment)
Computational sustainability is an emerging interdisciplinary field that applies computational techniques from computer and information science, operations research, applied mathematics and statistics to facilitate the integration of environmental, societal and economic needs for sustainable development. In this course, we will study recent computational approaches that have contributed to addressing sustainability topics related to biodiversity, climate, environment, urban design, transportation, buildings and others. Computational themes include optimization, modeling, machine learning and data mining.
The course is designed to be an introduction to computational sustainability, providing a broad coverage of the field. It is suitable for students in computing and engineering or students in other disciplines with good familiarity with computational approaches and mathematical modeling. The main graded components will be 1) a reaction paper critically summarizing a sustainability-related problem and published solution approaches, 2) an in-class presentation, and 3) a course project.
Outline: also click for detailed SCHEDULE.
Introduction to Sustainable Development and Computational Sustainability
Biodiversity Assessment and Conservation Planning
Building Design and Energy
The course will be a combination of lectures and student presentations.
There are no course pre-requisites. The course emphasizes the use of mathematical modeling and algorithms to address sustainability challenges. As such, students should expect to work with computational and mathematical models and should be familiar with basic knowledge of probabilities and calculus.
Each student must read and abide by the Georgia Tech Academic Honor Code, see www.honor.gatech.edu.
Class Participation 10%
Reaction Paper 20%
Class Presentation 20%
Final Project 50%
The reaction paper will critically summarize a sustainability-related problem and published solution approaches. Students can choose to use the reaction paper as background research for their project.
For the class presentation, students can choose to present 1) a paper concerning a computational approach to a sustainability topic, 2) a sustainability domain and its open challenges where computation can play a role, or 3) a computational technique, model or tool that can be used to address sustainability-related problems. Students can also choose to focus their class presentation on the same topic as their reaction paper.
List of the Reaction Papers submitted by students LINK
The course project work will include a brief proposal, a final report and a presentation in class at the end of the semester. For the class project, students are free to come up with their own ideas for projects, including sustainability-related challenges from their respective research disciplines. Students can choose to work on their own or in a small team. See some relevant public datasets are listed below.
There is no required textbook. All relevant materials will be available online.
Some of the papers we will cover in class: LINK
Pointers to resources to find more relevant papers: LINK
Here are some pointers to publicly available datasets on sustainability-related challenges. More will be added later.
[Dataset|Challenge in Conservation]
Large Landscape Conservation - Synthetic and Real-World Datasets
Bistra Dilkina, Katherine Lai, Ronan Le Bras, Yexiang Xue, Carla P. Gomes, Ashish Sabharwal, Jordan Suter, Kevin S. McKelvey, Michael K. Schwartz and Claire Montgomery.
AAAI-13: AAAI Conference on Artificial Intelligence, July 2013
[Dataset | Challenge in Conservation | POMDP]
Adaptive management of migratory birds under sea level rise.
Nicol S, Iwamura T, Buffet O, Chadès I.
International Joint Conference on Artificial Intelligence (IJCAI), 2013.
[Dataset | Challenge in Climate]
Forecast Oriented Classification of Spatio-Temporal Extreme Events.
Z. Chen, Y. Xie, Y. Cheng, K. Zhang, A. Agrawal, W. Liao, N. F. Samatova, and A. Choudhary.
International Joint Conference on Artificial Intelligence (IJCAI), 2013
REDD: A public data set for energy disaggregation research.
Zico Kolter and Matthew J. Johnson.
SustKDD: Workshop on Data Mining Applications in Sustainability, 2011.
Smart*: An Open Data Set and Tools for Enabling Research in Sustainable Homes.
Sean Barker, Aditya Mishra, David Irwin, Emmanuel Cecchet, Prashant Shenoy, and Jeannie Albrecht.
SustKDD: Workshop on Data Mining Applications in Sustainability, 2012.
"Balancing bike sharing systems (BBSS): instance generation from the CitiBike NYC data." arXiv preprint arXiv:1312.3971 (2013).