Articles | Volume 22, issue 23
https://doi.org/10.5194/bg-22-7687-2025
https://doi.org/10.5194/bg-22-7687-2025
Research article
 | 
08 Dec 2025
Research article |  | 08 Dec 2025

Utilizing probability estimates from machine learning and pollen to understand the depositional influences on branched GDGT in wetlands, peatlands, and lakes

Amy Cromartie, Cindy De Jonge, Guillemette Ménot, Mary Robles, Lucas Dugerdil, Odile Peyron, Marta Rodrigo-Gámiz, Jon Camuera, Maria Jose Ramos-Roman, Gonzalo Jiménez-Moreno, Claude Colombié, Lilit Sahakyan, and Sébastien Joannin

Related authors

BrGDGT-based palaeothermometer in drylands: the necessity to constrain aridity and salinity as confounding factors to ensure the robustness of calibrations
Lucas Dugerdil, Sébastien Joannin, Odile Peyron, Shafag Bayramova, Xiaozhong Huang, Fahu Chen, Dilfuza Egamberdieva, Jakhongir Alimov, Bazartseren Boldgiv, Amy Cromartie, Juzhi Hou, Lilit Sahakyan, Khachatur Meliksetian, Salomé Ansanay-Alex, Rafig Safarov, Imran Muradi, Shabnam Isayeva, Shehla Mirzayeva, Elshan Abdullayev, Sayyara Ibadullayeva, Parvana Garakhani, and Guillemette Ménot
EGUsphere, https://doi.org/10.5194/egusphere-2025-3658,https://doi.org/10.5194/egusphere-2025-3658, 2025
Short summary
Climate changes during the Late Glacial in southern Europe: new insights based on pollen and brGDGTs of Lake Matese in Italy
Mary Robles, Odile Peyron, Guillemette Ménot, Elisabetta Brugiapaglia, Sabine Wulf, Oona Appelt, Marion Blache, Boris Vannière, Lucas Dugerdil, Bruno Paura, Salomé Ansanay-Alex, Amy Cromartie, Laurent Charlet, Stephane Guédron, Jacques-Louis de Beaulieu, and Sébastien Joannin
Clim. Past, 19, 493–515, https://doi.org/10.5194/cp-19-493-2023,https://doi.org/10.5194/cp-19-493-2023, 2023
Short summary

Cited articles

Acharya, S., Zech, R., Strobel, P., Bliedtner, M., Prochnow, M., and De Jonge, C.: Environmental controls on the distribution of GDGT molecules in Lake Höglwörth, Southern Germany, Org. Geochem., 186, https://doi.org/10.1016/j.orggeochem.2023.104689, 2023. 
Anaissi, A., Kennedy, P. J., Goyal, M., and Catchpoole, D. R.: A balanced iterative random forest for gene selection from microarray data, BMC Bioinform., 14, 104689, https://doi.org/10.1186/1471-2105-14-261, 2013. 
Baker, A., Blyth, A. J., Jex, C. N., Mcdonald, J. A., Woltering, M., and Khan, S. J.: Glycerol dialkyl glycerol tetraethers (GDGT) distributions from soil to cave: Refining the speleothem paleothermometer, Org. Geochem., 136, 103890, https://doi.org/10.1016/j.orggeochem.2019.06.011, 2019. 
Barhoumi, C., Ménot, G., Joannin, S., Ali, A. A., Ansanay-Alex, S., Golubeva, Y., Subetto, D., Kryshen, A., Drobyshev, I., and Peyron, O.: Temperature and fire controls on vegetation dynamics in Northern Ural (Russia) boreal forests during the Holocene based on brGDGT and pollen data, Quaternary Sci. Rev., 305, 108014, https://doi.org/10.1016/j.quascirev.2023.108, 2023. 
Baxter, A. J., Hopmans, E. C., Russell, J. M., and Sinninghe Damsté, J. S.: Bacterial GMGTs in East African lake sediments: Their potential as palaeotemperature indicators, Geochim. Cosmochim. Acta, 259, 155–169, https://doi.org/10.1016/j.gca.2019.05.039, 2019. 
Download
Short summary
BrGDGT (branched glycerol dialkyl glycerol tetraethers) are a molecular biomarker utilized for paleotemperature reconstructions. One issue, however, with utilizing brGDGTs is that the distribution differs in relation to sediment environments (i.e., peat, lake, soil). We utilize the probability estimate outputs from five machine learning algorithms and a new modern brGDGT database to track provenance change and apply these models to two downcore records utilizing pollen, non-pollen polymorphs, and XRF (X-ray fluorescence) to confirm the models’ accuracy.
Share
Altmetrics
Final-revised paper
Preprint