Name: Bayesian Belief Networks

Reference: Wooldridge (2003). Bayesian Belief Networks. CSIRO, Australia.

Conservation planning step(s) when this would be used: This is used during the Plan Actions step to help predict the outcomes of potential actions.

Description of tool use: A decision-support framework allowing evidence from observed events to be propagated through a model of the system, to help predict the outcome of events that have not yet been observed.

Experience and expertise required to use the tool: This tool requires specialist expertise.

Data requirements: This tool is suitable for data poor situations.

Cost: Use of BBNs is greatly facilitated by use of an “Enabling Tool” tool such as Netica. An educational license is currently priced at < $300. A limited license is available for free.

Strengths and weaknesses, when to use and interpret with caution: It is necessary to develop probability estimates for events when using this tool, but the tool also facilitates estimating probabilities by breaking them down into simpler sub-events. When empirical data are not available, expert judgment can be a suitable stand-in for estimating these probabilities.  

Case study: 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.


Back to Abruzzi Table 1.

___________________________________________________________________________
Contributor(s): Sarah Converse           
Affiliation: USGS Patuxent Wildlife Research Center
Email: sconverse@usgs.gov                       
Date: 7 February 2012