Global models and predictions of plant diversity based on advanced machine learning techniques

0573979 - BÚ 2024 RIV GB eng J - Článek v odborném periodiku
Cai, L. - Kreft, H. - Taylor, A. - Denelle, P. - Schrader, J. - Essl, F. - van Kleunen, M. - Pergl, Jan - Pyšek, Petr - Stein, A. - Winter, M. - Barcelona, J. F. - Fuentes, N. - Inderjit, Dr. - Karger, D. N. - Kartesz, J. - Kuprijanov, A. - Nishino, M. - Nickrent, D. L. - Nowak, A. - Patzelt, A. - Pelser, P. B. - Singh, P. - Wieringa, J. J. - Weigelt, P.
Global models and predictions of plant diversity based on advanced machine learning techniques.
New Phytologist. Roč. 237, č. 4 (2023), s. 1432-1445. ISSN 0028-646X. E-ISSN 1469-8137
Grant CEP: GA ČR(CZ) GX19-28807X
Institucionální podpora: RVO:67985939
Klíčová slova: plant diversity * machine learning * distribution
Obor OECD: Ecology
Impakt faktor: 9.4, rok: 2022
Způsob publikování: Open access
https://doi.org/10.1111/nph.18533

We used machine learning (random forests, extreme gradient boosting, and neural networks) and conventional statistical methods (generalized linear models and generalized additive models) to test environment-related hypotheses of broad-scale vascular plant diversity gradients and to model and predict species richness and phylogenetic richness worldwide. To this end, we used 830 regional plant inventories including c. 300 000 species and predictors of past and present environmental conditions. Machine learning showed a superior performance, explaining up to 80.9% of species richness and 83.3% of phylogenetic richness, illustrating the great potential of such techniques for disentangling complex and interacting associations between the environment and plant diversity. Current climate and environmental heterogeneity emerged as the primary drivers, while past environmental conditions left only small but detectable imprints on plant diversity. Finally, we combined predictions from multiple modeling techniques (ensemble predictions) to reveal global patterns and centers of plant diversity at multiple resolutions down to 7774 km2. Our predictive maps provide accurate estimates of global plant diversity available at grain sizes relevant for conservation and macroecology.
Trvalý link: https://hdl.handle.net/11104/0344358