Abstract:
The numerical relationship between modem pollen assemblages and altitude in high mountain environments from the northern Andes is analysed, in order to found inference models that allow estimating palaeoaltitudes and palaeotemperatures from past pollen records. The calibration set (DM) consists of a 50-sample altitudinal transect between-2300 and-4600 m altitude. The overall and individual pollen responses to altitude were tested by correspondence analysis (CA), generalized linear regression (HOF) and weighted averaging (WA). Transfer functions were derived by weighted averaging partial least squares (WA-PLS) regression. Overall, altitude is the main controlling factor for the composition of pollen assemblages, as shown by the high correlation between altitude and the first CA component (r =-0.88). Individually, around 35% of the 82 pollen taxa show a significant response to altitude through monotonic or unimodal functions. The best transfer function obtained has a good statistical performance, as shown by the determination coefficient (r2tck =0.78). The prediction power, as measured by the root mean square error of prediction (RMSEP), is of 256 m (12% of the total altitudinal gradient), which is equivalent to-1.5C. These parameters fall within the performance range of the inference models developed elsewhere using pollen and other biological proxies. It is concluded that the DM training set is useful to reconstruct Pleistocene and major Holocene palaeoclimatic trends. This study demonstrates the suitability of establishing reliable transfer functions for palaeoclimatic estimation in the highest altitudes of the tropical Andes, and encourages their continued improvement.
