Back to The Ecology Plexus Page...
Back to The Plexus Home Page...
 


Bayesian Network Models
in Ecology

Bruce G. Marcot
updated 3 October 2017

Also see:
Structured Decision Making, Expert Systems,
Expert Paneling, & Expert Elicitation in Ecology 

 


Introduction to Bayesian Network Modeling

What are "Bayesian networks?"  ... 
a harmless, simple introduction with virtually no math.
[PDF version but without the animations]


Guidelines & Consideration for Developing, Testing,
and Documenting Bayesian Network Models

A set of guidelines you can follow.
Also see publications below on Guidelines and related topics.

Bayesian network modeling metrics of performance and uncertainty.
A summary of approaches to conducting model sensitivity analysis,
scenario analysis, model complexity, prediction performance, uncertainty

Template for conducting and documenting guided peer reviews of Bayesian network models.
Microsoft Word document format. Follows modeling procedures of Marcot (2006), below.

Template for scheduling and tracking peer reviews of Bayesian network models
Microsoft Excel spreadsheet format. Follows modeling procedures of Marcot (2006), below.
 
    



Papers on Bayesian network modeling

 
Bayesian network modeling: (listed chronologically from most recent)

Pawson, S. M., B. G. Marcot, and O. Woodberry. 2017. Predicting forest insect flight activity: a Bayesian network approach. PLoS ONE 12(9):e0183464, https://doi.org/10.1371/journal.pone.0183464.  PDF   

Havron, A., C. Goldfinger, S. Henkel, B. G. Marcot, C. Romsos, and L. Gilbane. 2017. Mapping marine habitat suitability and uncertainty using Bayesian networks: a case study of northeastern Pacific benthic macrofauna. Ecosphere 8(7):e01859. doi: 10.1002/ecs2.1859.  Find it here. 

Marcot, B. G. 2017. Common quandaries and their practical solutions in Bayesian network modeling. Ecological Modelling 358:1-9.  PDF (1.3MB) 

Fortin, J. K., K. D. Rode, G. V. Hilderbrand, J. Wilder, S. Farley, C. Jorgensen, and B. G. Marcot.  2016.  The impacts of human recreation on brown bears (Ursus arctos): a review and new management tool.  PLoS ONE 11(1):e0141983. doi:10.1371/journal.pone.0141983.  PDF (1MB) 
    The Netica Bayesian network model is available from the Australasian Bayesian Network Modelling Society's model repository, at:  http://abnms.org/bnrepo/bn?bnId=145  

Marcot, B. G., and M. G. Raphael.  2012.  Conservation of martens, sables, and fishers in multispecies bioregional assessments.  Pp. 451-470 in:  K. B. Aubry, W. J. Zielinski, M. G. Raphael, G. Proulx, and S. W. Buskirk, eds.  Biology and conservation of martens, sables, and fishers: a new synthesis.  Cornell University Press, Ithaca, New York.  580 pp.
    [Includes an example of a Bayesian network model of Pacific marten.]

Marcot, B. G.  2012.  Metrics for evaluating performance and uncertainty of Bayesian network models.  Ecological Modelling 230:50-62. PDF (1.0MB) ... Appendix PDF (0.9MB)  

Marcot, B. G., C. Allen, S. Morey, D. Shively, and R. White.  2012.  An expert panel approach to assessing potential effects of bull trout reintroduction on federally listed salmonids in the Clackamas River, Oregon.  North American Journal of Fisheries Management 32(3):450-465.  PDF (1.1MB)  
    [Includes a Bayesian network food web model in Appendix 3.]
    The Netica Bayesian network model is available from the Australasian Bayesian Network Modelling Society's model repository, at:  http://abnms.org/bnrepo/bn?bnId=149  

Pauli, J. N., J. P. Whiteman, B. G. Marcot, T. M. McClean, and M. Ben-David.  2011.  DNA-based approach to aging martens (Martes americana and M. caurina).  Journal of Mammalogy 92(3):500-510.  PDF (397KB)
    The Netica Bayesian network model is available from the Australasian Bayesian Network Modelling Society's model repository, at:  http://abnms.org/bnrepo/bn?bnId=156  

van Rooij, T., D. I. Rumiz, A. R. Montellano, U. Remillard, X. Fernandez, R. Arispe, J. C. Herrera, W. Townsend, R. S. Miserendino, D. Caba, T. Muñoz, and B. Marcot.  2008.  Using the landscape species concept to model habitat suitability for threatened species in Bolivia’s dry tropical forest (preliminary report).  FCBC (Foundation for the Conservation of the Chiquitano Forest), Santa Cruz de la Sierra, Bolivia.  24 pp.  
    [Includes Bayesian network models on jaguar populations.

Marcot, B. G.  2007.  Étude de cas n°5: gestion de ressources naturelles et analyses de risques (Natural resource assessment and risk management).  Pp. 293-315 in: P. Naim, P.-H. Wuillemin, P. Leray, O. Pourret, and A. Becker, eds.  Réseaux bayésiens (Bayesian networks) [in French]. Eyrolles, Paris, France. PDF preprint in English, (252KB); PDF chapter in French (449KB); title pages.  

Marcot, B. G.  2006.  Habitat modeling for biodiversity conservation. Northwestern Naturalist 87(1):56-65.  PDF (236KB).  
    [Discusses various modeling approaches including use of Bayesian belief networks.]   
    Abstract published as:  Marcot, B. G. 2005. Habitat modeling for biodiversity conservation (abstract). Northwestern Naturalist 86(2):107.

Marcot, B. G., R. S. Holthausen, M. G. Raphael, M. M. Rowland, and M. J. Wisdom. 2001. Using Bayesian belief networks to evaluate fish and wildlife population viability under land management alternatives from an environmental impact statement. Forest Ecology and Management 153(1-3):29-42. PDF (252KB).  
    [Also see below for more information on this publication and access to the models used.]

Raphael, M. G., M. J. Wisdom, M. M. Rowland, R. S. Holthausen, B. C. Wales, B. G. Marcot, and T. D. Rich. 2001. Status and trends of habitats of terrestrial vertebrates in relation to land management in the interior Columbia River Basin. Forest Ecology and Management 153(1-3):63-87. PDF (544KB).

  

Bayesian network modeling of future Pacific walrus habitat & populations:  

Jay, C. V., B. G. Marcot, and D. C. Douglas. 2011.  Projected status of the Pacific walrus (Odobenus rosmarus divergens) in the 21st century. Polar Biology 34(7):1065-1084.  PDF (1.7MB) 
     >  With online resource (supplementary material) PDF (240KB) 
    The Netica Bayesian network model is available from the Australasian Bayesian Network Modelling Society's model repository, at:  http://abnms.org/bnrepo/bn?bnId=147  

Jay, C. V., B. G. Marcot, and D. C. Douglas.  2010.  Projected status of the Pacific walrus (Odobenus rosmarus divergens) in the 21st century.  Administrative Report Submitted to the U.S. Fish and Wildlife Service.  U.S. Geological Survey, Alaska Science Center.  Anchorage, Alaska.  90 pp. 


Bayesian network modeling of future polar bear habitat & populations:  

Atwood, T. C., B. G. Marcot, D. C. Douglas, S. C. Amstrup, K. D. Rode, G. M. Durner, and J. F. Bromaghin. 2016. Forecasting the relative influence of anthropogenic stressors on polar bears. Ecosphere 7(6):DOI: 10.1002/ecs2.1370.   PDF (3.6MB) 
    The Netica Bayesian network model is available from the Australasian Bayesian Network Modelling Society's model repository, at:  http://abnms.org/bnrepo/bn?bnId=168  

Atwood, T. C., B. G. Marcot, D. C. Douglas, S. C. Amstrup, K. D. Rode, G. M. Durner, and J. F. Bromaghin. 2015. Evaluating and ranking threats to the long-term persistence of polar bears. U.S. Geological Survey, Open-File Report 2014-1254. http://dx.doi.org/10.3133/ofr20141254. Anchorage, Alaska. 114 pp.  PDF (8MB) 
     > Also available from http://pubs.usgs.gov/of/2014/1254/ 

Amstrup, S. C., E. T. DeWeaver, D. C. Douglas, B. G. Marcot, G. M. Dumer, C. M. Bitz, and D. A. Bailey.  2010.  Greenhouse gas mitigation can reduce sea-ice loss and increase polar bear persistence.  Nature 468(7326):955-958.  PDF (1.5MB)  
     >  With online resource (supplementary material) PDF (2.5MB)  
    The Netica Bayesian network model is available from the Australasian Bayesian Network Modelling Society's model repository, at:  http://abnms.org/bnrepo/bn?bnId=146  
     >  Note: A news item on this article by the National Science Foundation can be found here .
     >  Additional news items from Oregon Public Broadcasting
radio, and USDA Forest Service .

Amstrup, S. C., B. G. Marcot, and D. C. Douglas.  2007.  Forecasting the range-wide status of polar bears at selected times in the 21st century.  Administrative Report.  U.S. Geological Survey, Alaska Science Center.  Anchorage, Alaska.  126 pp.  PDF (4.4MB, low-res)  
     Also available from: http://treesearch.fs.fed.us/pubs/33235  PDF
(20.8MB, high-res)  

Amstrup, S. C., B. G. Marcot, and D. C. Douglas.  2008.  Forecasting the range-wide status of polar bears at selected times in the 21st century: addition of model outcomes for the decade 2020-2029.  Administrative Report.  U.S. Geological Survey, Alaska Science Center.  Anchorage, Alaska.  6 pp.

Amstrup, S. C., B. G. Marcot, and D. C. Douglas.  2008.  A Bayesian network modeling approach to forecasting the 21st century worldwide status of polar bears.  Pp. 213-268 in: E. T. DeWeaver, C. M. Bitz, and L.-B. Tremblay, eds.  Arctic sea ice decline: observations, projections, mechanisms, and implications.  Geophysical Monograph 180.  American Geophysical Union, Washington, D.C.  PDF (4.4MB) 
    The Netica Bayesian network model is available from the Australasian Bayesian Network Modelling Society's model repository, at:  http://abnms.org/bnrepo/bn?bnId=146  

Amstrup, S. C., H. Caswell, E. DeWeaver, I. Stirling, D. C. Douglas, B. G. Marcot, and C. M. Hunter.  2009.  Rebuttal of "polar bear population forecasts: a public-policy forecasting audit".  Interfaces 39(4):353-369.  PDF (235KB) 
  

Special issue section on Bayesian network modeling, in Canadian Journal of Forest Research:  

Marcot, B. G., J. D. Steventon, G. D. Sutherland, and R. K. McCann.  2006.  Guidelines for developing and updating Bayesian belief networks applied to ecological modeling and conservation.  Canadian Journal of Forest Research 36:3063-3074.  PDF (492KB)

McCann, R., B. G. Marcot, and R. Ellis.  2006.  Bayesian belief networks: applications in natural resource management.  Canadian Journal of Forest Research 36:3053-3062.  PDF (241KB)

McNay, R. S., B. G. Marcot, V. Brumovsky, and R. Ellis.  2006.  A Bayesian approach to evaluating habitat suitability for woodland caribou in north-central British Columbia.  Canadian Journal of Forest Research 36:3117-3133.  PDF (723KB)

Nyberg, J. B., B. G. Marcot, and R. Sulyma.  2006.  Using Bayesian belief networks in adaptive management.  Canadian Journal of Forest Research 36:3104-3116.  PDF (242KB)
   

Two-part series on use of Bayesian network modeling for characterizing species at risk, in Ecology and Society: 

Marcot, B. G.  2006.  Characterizing species at risk I: modeling rare species under the Northwest Forest Plan.  Ecology and Society 11(2):10. [online] http://www.ecologyandsociety.org/vol11/iss2/art10/ ... or article PDF (701KB) and appendix PDF (21KB)  

Marcot, B. G., P. A. Hohenlohe, S. Morey, R. Holmes, R. Molina, M. Turley, M. Huff, and J. Laurence.  2006.  Characterizing species at risk II: using Bayesian belief networks as decision support tools to determine species conservation categories under the Northwest Forest Plan.  Ecology and Society 11(2):12. [online]  http://www.ecologyandsociety.org/vol11/iss2/art12/ ... or article PDF (1.3MB)   
  



Textbook on Bayesian Network Applications:

Pourret, O., P. Naïm, and B. Marcot, editors.  2008.  Bayesian networks: a practical guide to applications.  Wiley.  428 pp.  

Available from Wiley and from Amazon.com.  See a synopsis, descriptions from the publisher and authors, and excerpts at Amazon.com.uk.  

See lots more about this book -- background, models and applications, new material -- at "Bayesian Networks ~ Applications" ... a website created by the book editors.   


 
Netica Models from Paper on Constructing Bayesian Networks

Marcot, B. G., R. S. Holthausen, M. G. Raphael, M. Rowland, and M. Wisdom.  2001.  Using Bayesian belief networks to evaluate fish and wildlife population viability under land management alternatives from an environmental impact statement.  Forest Ecology and Management 153(1-3):29-42.   
Download the paper (PDF, 443KB)

Models mentioned in the paper:

Note:  Download these models (they're ASCII files) by right-clicking on the following links.  To run these models you need the Bayesian network program Netica, available from Norsys, Inc., at:  http://www.norsys.com
Model 1: (from Fig. 1)
General structure of a Bayesian belief network (BBN) model for evaluating population viability outcomes of wildlife species, showing 6 shells of nodes.  See Appendix 1 for description of node names.  The state of nature nodes (shells 2-5) can depict parameters as multiple discrete values (as shown here) or as continuous values.

Figure 2:
Example BBNs depicting population response of a wildlife species, Townsend’s big-eared bat (Corynorhinus townsendii), in the interior Columbia River Basin, U.S.A., at 3 levels of geographic resolution.
Model 2a: (from Fig. 2a) - Site-specific BBN model:  relations of site-specific key environmental correlates (KECs);
Model 2b: (from Fig. 2b) - Subwatershed BBN model:  relations of subwatershed-scale KECs and their GIS proxies;
Model 2c: (from Fig. 2c) - Basin BBN model:  overall population outcome.
 

 


  
Other Examples of Bayesian Network Models

  
In addition to the Bayesian network models presented in the various publications listed above, other examples using the Netica modeling shell can be found here: 

  


 
Guidelines for Developing Bayesian Networks

I developed the following guidelines as part of my team work on the Interior Columbia Basin Ecosystem Management Project of USDA Forest Service and USDI Bureau of Land Management.  They have served us well.  They served as the basis for some of the publications listed above.  

A Process for Creating Bayesian Belief Network Models of Species-Environment Relations  (note: much of this was reworked and updated for the journal publication listed above, Marcot, B. G., J. D. Steventon, G. D. Sutherland, and R. K. McCann. 2006. Guidelines for developing and updating Bayesian belief networks applied to ecological modeling and conservation. Canadian Journal of Forest Research 36:3063-3074.  You may wish to use that publication instead.)

Methods for Peer Review Updating of Bayesian Belief Network Species Models

  For other Bayesian network modeling guidelines, also see the lists of publications above.



  
Abstract of Talks on Bayesian Network 
and Decision Support Modeling
 

  
Marcot, B. G. 2014. Of confidence, control, and cause: using Bayesian networks for management decisions. Presented 26 November 2014 at the Sixth Annual Conference of the Australasian Bayesian Network Modelling Society, Rotorua, New Zealand. [Invited keynote address].  View here ... or PDF version (11.7MB)    
  


  
Some Additional Links on Bayesian Network Resources

AgenaRisk  
Australasian Bayesian Network Modelling Society (also see their Resources page) 
Bayesian Intelligence
BUGS & WinBUGS 
Elvira modeling system
BayesFusion - GeNIe & SMILE (Structural Modeling, Inference, and Learning Engine) 
Hugin Expert
International Society for Bayesian Analysis
Microsoft Belief Network (MSBN)
Norsys Software Corp. - Netica
SamIam
  


Back to The Ecology Plexus Page...
Back to The Plexus Home Page...