We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Tailoring palaeolimnological diatom-based transfer functions.
- Authors
Racca, Julien M. J.; Gregory-Eaves, Irene; Pienitz, Reinhard; Prairie, Yves T.
- Abstract
This paper presents a method designed to build species-tailored diatom–environment models. Using a pruning algorithm of artificial neural networks, powerful species-tailored models constrained to water temperature, water depth, and dissolved organic carbon were developed from a 109-lake training set from northwestern Canada and Alaska. The reasoning behind the approach is that the implementation of a single, gradient-based, organism–environment relationship should only use species that are comprehensively influenced by the variable of interest. By pruning species according to their relevance to each of the three studied variables, the cross-validated performances of all three models were significantly increased, suggesting that nonrelevant species have corrupting influences and need to be removed. The removal of corrupting species also suggests that palaeolimnological transfer functions based on an appropriate subset of useful species are more independent.
- Subjects
DIATOMS; TRANSFER functions; NEURAL computers; ALGORITHMS; ORGANIC compound content of seawater
- Publication
Canadian Journal of Fisheries & Aquatic Sciences, 2004, Vol 61, Issue 12, p2440
- ISSN
0706-652X
- Publication type
Article
- DOI
10.1139/F04-162