Capturing expert knowledge for ecosystem mapping using Bayesian networks

Abstract

Large-scale ecosystem maps are essential tools for managers of forest-related activities. In British Columbia, the prevailing approach for ecosystem mapping has been to use an expert system that captures expert knowledge in the form of a belief matrix. In this project, a Bayesian network rather than a belief matrix was used in an attempt to overcome some of the drawbacks of the belief-matrix approach. A Bayesian-network knowledge base was created for each of the following three biogeoclimatic variants: montane very wet maritime coastal western hemlock (CWHvm2), submontane very wet maritime coastal western hemlock (CWHvm1), and central very wet hypermaritime coastal western hemlock (CWHvh2), and applied to a study area encompassing Prince Rupert. A map of ecosystems by grouping site series was produced using each of the knowledge bases. Accuracy assessments performed on each of the maps of grouped site series revealed that the maps poorly predicted the spatial distribution of uncommon and very wet site-series groups. For example, overall map accuracy for the CWHvm2, CWHvm1, and CWHvh2 variants was 47.8%, 50.3%, and 33.3%, respectively. The results of the map-accuracy assessment, however, were consistent with those resulting from a belief-matrix approach conducted in an earlier study. We feel that Bayesian network knowledge bases are easier to develop, interpret, and update than belief matrices.