In the field of Computational Sustainability, I have worked on learning predictive models of and optimizing policies for domains in invasive species control, forest harvest management and forest fire management. These types of domains offer unique challenges for traditional artificial intelligence and machine learning algorithms for decision making, prediction and anomaly detection.
See my blog for more writing on this topic.
Our Papers on Computational Sustainability
- Semantic Workflows and Machine Learning for the Assessment of Carbon Storage by Urban TreesIn Third International Workshop on Capturing Scientific Knowledge (Sciknow 2019), Collocated with the tenth International Conference on Knowledge Capture (K-CAP) 2019
- Combining MCTS and A3C for prediction of spatially spreading processes in forest wildfire settingsIn Canadian Conference on Artificial Intelligence 2018
- Using Spatial Reinforcement Learning to Build Forest Wildfire Dynamics Models From Satellite ImagesFrontiers in ICT 2018
- PAC Optimal MDP Planning with Application to Invasive Species ManagementJournal of Machine Learning Research 2015
- Using equilibrium policy gradients for spatiotemporal planning in forest ecosystem managementIEEE Transactions on Computers 2014
- PAC Optimal Planning for Invasive Species Management: Improved Exploration for Reinforcement Learning from Simulator-Defined MDPsIn Proceedings of the AAAI Conference on Artificial Intelligence (AAAI-2013) 2013
- Managing Invasive Species in a River NetworkIn Third International Conference on Computational Sustainability 2012
- Equilibrium Policy Gradients for Spatiotemporal Planning2011
- Seeing the Forest Despite the Trees : Large Scale Spatial-Temporal Decision MakingIn Conference on Uncertainty in Artificial Intelligence (UAI09) 2009