No 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.

No abstract

Diatom analyses of sediments from a high elevation lake situated in an Engelmann Spruce - Subalpine Fir (ESSF) forest of south-central British Columbia, Canada, reveal long-term climate and water chemistry change. During the transition from the late-glacial / Pleistocene to the xerothermic early Holocene, small, benthic Fragilaria diatoms species that grew under low light conditions in Sicamous Creek Lake gave way to planktonic Cyclotella species that require open-water conditions. Warm temperatures in the mesothermic Holocene are indicated by smaller Cyclotella species and large, benthic pennate diatoms. Diatom communities reflected Neoglacial cooling in the late Holocene, with abundant Nitzschia fonticola and Achnanthes minutissima. Small, benthic Fragilaria regained abundance, suggesting cooling and conditions similar to the late-glacial interval. Diatom community composition responded to the deposition of the Mt. Mazama and Mt. St. Helens tephras, though the Mazama eruption caused greater change in relative abundance of various taxa within the assemblage. Correspondence analysis shows distinct communities have occurred since the initiation of sedimentation, likely due to climate controlled landscape and vegetation changes; diatom-inferred pH values using various models and training sets show limited acidification change occurred through the lake’s history.