Seminar on Computational Sustainability: Algorithms for Ecology and Conservation

CS 691SU
UMass Amherst
Spring 2014

Schedule

Jan 22 - Course Overview and Logistics (Dan Sheldon)

• D. Sheldon, A. Farnsworth, and J. Irvine, Approximate Bayesian Inference for Reconstructing Velocities of Migrating Birds from Weather Radar, In Proceedings of the 27th AAAI Conference on Artificial Intelligence (AAAI), 2013.

Jan 29 - Data Gathering: Sensor Placement and Citizen Science (Jeffrey Geevarghese and Kevin Winner)

• C. Guestrin, A. Krause, and A. Singh, Near-optimal sensor placements in gaussian processes, Proceedings of the 22nd International conference on Machine Learning (ICML), vol. 1, 2005.
• Y. Xue, B. Dilkina, T. Damoulas, and D. Fink, Improving Your Chances: Boosting Citizen Science Discovery, AAAI Conference on Human Computation and Crowdsourcing, pp. 198-206, 2013.
• Additional resources (optional):
  • Expanded journal version of sensor placement paper (JMLR, 2008)

Feb 5 - No class due to snow

Feb 12 - Species Distribution Modeling: MAXENT (Roy Adams and Aaron Schein)

• S. Phillips, M. Dudík, and R. Schapire, A maximum entropy approach to species distribution modeling, Proceedings of the twenty-first International Conference on Machine Learning (ICML), pp. 655–662, 2004.
• I. W. Renner and D. I. Warton, Equivalence of MAXENT and Poisson point process models for species distribution modeling in ecology., Biometrics, vol. 69, no. 1, pp. 274–81, Mar. 2013.
• Additional resources (optional):
  • See additional MAXENT references under "Species Distribution Modeling" in the full bibliography. Several are written to be more accessible to ecologists.
  • For another view of the equivalence between MAXENT and other models, see: W. Fithian and T. Hastie, Finite-sample equivalence in statistical models for presence-only data, The Annals of Applied Statistics, vol. 7, no. 4, pp. 1917–1939, Dec. 2013.

Feb 19 - Occupancy Modeling Introduction and Background (Xiaojian Wu and Luis Pineda)

• D. MacKenzie, J. Nichols, G. Lachman, S. Droege, J. A. Royle, and C. Langtimm, Estimating site occupancy rates when detection probabilities are less than one, Ecology, vol. 83, no. 8, pp. 2248-2255, 2002.
• Gradient Boosting. Read both of the following
  • G. Ridgeway, Generalized Boosted Models: A guide to the gbm package, (R package vignette)
  (Sections 1 and 2 required; Sections 3 and 4 recommended to understand practical considerations)
  • T. Dietterich, G. Hao, and A. Ashenfelter, Gradient tree boosting for training conditional random fields Journal of Machine Learning Research, vol. 9, pp. 2113–2139, 2008.
  (Section 3 only; the rest of the paper is a good read)
• Additional resources (optional)
  • J. Friedman, Greedy Function Approximation: A Gradient Boosting Machine, The Annals of Statistics, vol. 29, no. 5, pp. 1189-1232, 2001
  Original gradient boosting paper

Feb 26 - Occupancy Models in CS (Tao Sun and Arvind Sowmyan)

• R. Hutchinson, L. Liu, and T. Dietterich, Incorporating Boosted Regression Trees into Ecological Latent Variable Models., AAAI Conference on Artificial Intelligence, 2011.
• J. Yu, W.-K. Wong, and R. A. Hutchinson, Modeling Experts and Novices in Citizen Science Data for Species Distribution Modeling, 2010 IEEE International Conference on Data Mining, pp. 1157-1162, Dec. 2010.

Mar 5 - Mark-Recapture and Cormack-Jolly-Seber Models (Srinivasan Iyengar and Stephen Lee)

• J. Lebreton and K. Burnham, Modeling survival and testing biological hypotheses using marked animals: a unified approach with case studies, Ecological Monographs, vol. 62, no. 1, pp. 67–118, 1992.
  Read the following sections:
  • From beginning (p. 67) up to section on "Model Selection" (p. 79)
  • Starting with "Discussion" on p. 85 to the end of "Example 1: European Dipper" on p. 89
• Chapter 7 of M. Kéry and M. Schaub, Bayesian population analysis using WinBUGS A hierarchical perspective. Academic Press, 2011.
Read the following sections:
• Sections 7.1-7.5, pp.172-199. A considerable part of this is R/BUGS code---you don't need to read this, just understand the modeling that is being done.
• Sections 7.11-7.12

Mar 12 - Extensions to Mark-Recapture Models (Dan Sheldon and Ben Letcher)

• R. Neal, MCMC for Using Hamiltonian Dynamics, Handbook of Markov Chain Monte Carlo, 2011.
  Read pp.113-132
• Guest Lecture by Ben Letcher (USGS and UMass Dept. of Ecological Conservation)

Mar 19 - No class due to spring break

Mar 26 - Phenology (Farahnaz Maroof and Dan Sheldon)

• C. Zonneveld, Estimating Death Rates from Transect Counts, Ecological Entomology, vol. 16, pp. 115–121, 1991.
• Dan Sheldon, informal writeup on proposed extensions to Zonneveld-type models
• Additional resources (optional):
  • D. Sheldon, E. Goldman, E. Childs, O. Poblacion, J. C. Miller, J. A. Jones and T. G. Dietterich. Inferring moth emergence from abundance data: A novel mathematical approach using birth-death contingency tables ESA, 2011. [slides]
  • E. Matechou, E. B. Dennis, S. N. Freeman, and T. Brereton, Monitoring abundance and phenology in ( multivoltine ) butterfly species ; a novel mixture model, 2013.

Apr 2 - AI for Conservation Planning (Xiaojian Wu and Luis Pineda)

• S. Ermon, J. Conrad, C. Gomes, and B. Selman, Playing games against nature: optimal policies for renewable resource allocation, in Proc. of The 26th Conference on Uncertainty in Artificial Intelligence, 2010.
• I. Chades, J. Carwardine, T. Martin, S. Nicol, R. Sabbadin, and O. Buffet, MOMDPs: A Solution for Modelling Adaptive Management Problems., Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence, pp. 267–273, 2012.

Apr 9 - Lansdcape Connectivity and Introduction to Network Cascades (Roy Adams and Aaron Schein)

• B. McRae, B. Dickson, T. Keitt, and V. Shah, Using circuit theory to model connectivity in ecology, evolution, and conservation Ecology, vol. 89, no. 10, pp. 2712–2724, 2008.
• D. Kempe, J. Kleinberg, and É. Tardos, Maximizing the spread of influence through a social network, in Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining, 2003, pp. 137–146.
• Additional resources (optional):
  • P. G. Doyle and J. L. Snell, Random walks and electric networks, January, 2000.

Apr 16 - Optimization for Connectivity (Srinivasan Iyengar and Stephen Lee)

• B. Dilkina and C. Gomes, Solving connected subgraph problems in wildlife conservation CPAIOR-10: 7th International Conference on Integration of AI and OR Techniques in Constraint Programming for Combinatorial Optimization, 2010.
• K. Lai, C. Gomes, and M. Schwartz, The Steiner Multigraph Problem: Wildlife Corridor Design for Multiple Species, AAAI Conference on Artificial Intelligence, 2011.
• Additional resources (optional):
  • J. M. Conrad, C. P. Gomes, W.-J. van Hoeve, A. Sabharwal, and J. F. Suter, Wildlife corridors as a connected subgraph problem, Journal of Environmental Economics and Management, vol. 63, no. 1, pp. 1–18, Jan. 2012

Apr 23 - No class (Monday schedule)

Apr 30 - Landscape Connectivity and Network Cascades (Dan Sheldon)

• D. Sheldon, B. Dilkina, A. Elmachtoub, R. Finseth, A. Sabharwal, J. Conrad, C. Gomes, D. Shmoys, W. Allen, O. Amundsen, and B. Vauguan, Maximizing the Spread of Cascades Using Network Design, in UAI-2010: 26th Conference on Uncertainty in Artificial Intelligence, pp. 517–526.
• Additional resources (optional):
  • D. Golovin, A. Krause, B. Gardner, S. J. Converse, and S. Morey, Dynamic Resource Allocation in Conservation Planning, 2011.