Journal article

Comparison of boosted regression trees vs WA-PLS regression on diatom-inferred glacial-interglacial climate reconstruction in Lake Tiancai (southwest China)

Qian Wang, Paul B Hamilton, Min Xu, Giri Kattel



Quantitative paleoclimate reconstructions based on biological fossils over glacial-interglacial timescales are a major source of information on long-term climate variability. However, such reconstructions can present major methodological challenges, as calibration methods based on modern climatic and biological patterns may yield biased results, especially when data are particularly sensitive to the influence of secondary environmental variables in the training set or fossil assemblage. A machine-learning technique, boosted regression tree (BRT), is compared with a weighted averaging-partial least squares (WA-PLS) regression in a diatom-based summer (mean July) temperature transfer function ..

View full abstract

University of Melbourne Researchers


Awarded by National Key R&D program of China

Awarded by National Science Foundation of China

Funding Acknowledgements

We gratefully acknowledge Rong Wang for his help in field sampling and diatom counting. We thank Xuhui Dong for his helpful discussion and suggestions during the preparation of the manuscript. This study was supported by the National Key R&D program of China (2016YFA0600502) and the National Science Foundation of China (41877439, 41502170, and 41701232). Support for PBH was through a Canadian Museum of Nature RAC grant (2018-2020).