气候变化领域集成服务门户

Here we investigate the effect of species selection on planktonic foraminifera transfer functions. We assess species importance for transfer function models using a random forest technique and evaluate the performance of models with an increasing number of species. Irrespective of using models that use the entire training set (weighted averaging) or models that use only a subset of the training set (modern analogue technique), we find that the majority of foraminifera species does not carry useful information for temperature reconstruction. Less than one-third of the species in the training set is required to provide a temperature estimate with a prediction error comparable to a transfer function that uses all species in the training set. However, species selection matters for paleotemperature estimates. We find that transfer function models with a different number of species but with the same error may yield different reconstructions of sea surface temperature when applied to the same fossil assemblages. This ambiguity in the reconstructions implies that fossil assemblage change reflects a combination of temperature and other environmental factors. The contribution of the additional factors is site and time specific, indicating ecological and geological complexity in the formation of the sedimentary assemblages. The possibility of obtaining multiple different reconstructions from a single sediment record presents a previously unrecognized source of uncertainty for sea surface temperature estimates based on planktonic foraminifera assemblages. This uncertainty can be evaluated by determining the sensitivity of the reconstructions to species pruning. © Author(s) 2019. This work is distributed under the Creative Commons Attribution 4.0 License.