EUVIMEDObjevte EUVIMED
Open access · CC BY 4.0

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

Lirong Cai iD, Holger Kreft iD, Amanda Taylor iD, Pierre Denelle iD, Julian Schrader iD, Franz Essl iD, Mark van Kleunen iD, Jan Pergl iD, Petr Pyšek iD, Anke Stein, Marten Winter iD, Julie F Barcelona iD and 13 more

New Phytologist · 2023-02 · 237 (4) · 1432-1445

DOI: 10.1111/nph.18533 ↗

At a glance

Journal article in New Phytologist, published online on 2022-11-14. Written by Lirong Cai and 24 co-authors. Institution: Biodiversity, Macroecology and Biogeography, University of Göttingen, 37077, Göttingen, Germany. Major MEDLINE topics: Ecosystem, Biodiversity. Cited 198 times so far (Crossref); 94 references. The full text is freely available (open access, CC BY 4.0). Funded by: China Scholarship Council, Akademie Věd České Republiky, Grantová Agentura České Republiky.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Despite the paramount role of plant diversity for ecosystem functioning, biogeochemical cycles, and human welfare, knowledge of its global distribution is still incomplete, hampering basic research and biodiversity conservation. Here, 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 km 2 . Our predictive maps provide accurate estimates of global plant diversity available at grain sizes relevant for conservation and macroecology.

Subjects

MeSH terms (MEDLINE)

EcosystemBiodiversityHumansPhylogenyClimateLinear ModelsPlants

Author keywords

biodiversitydiversity-environment modelsphylogenetic diversityspecies richnessvascular plants

Authors and institutions

  • Biodiversity, Macroecology and Biogeography, University of Göttingen, 37077, Göttingen, Germany.
  • Centre of Biodiversity and Sustainable Land Use, University of Göttingen, 37077, Göttingen, Germany.
  • School of Natural Sciences, Macquarie University, 2109, Sydney, NSW, Australia.
  • Bioinvasions, Global Change, Macroecology-Group, University of Vienna, 1030, Vienna, Austria.
  • Ecology, Department of Biology, University of Konstanz, 78464, Konstanz, Germany.
  • Zhejiang Provincial Key Laboratory of Plant Evolutionary Ecology and Conservation, Taizhou University, 318000, Taizhou, China.

ORCID profiles: Lirong Cai, Holger Kreft, Amanda Taylor, Pierre Denelle, Julian Schrader, Franz Essl, Mark van Kleunen, Jan Pergl, Petr Pyšek, Marten Winter, Julie F Barcelona, Nicol Fuentes, Inderjit, Dirk Nikolaus Karger, Daniel Nickrent, Arkadiusz Nowak, Annette Patzelt, Pieter B Pelser, Paramjit Singh, Jan J Wieringa, Patrick Weigelt

Funding

  • China Scholarship Council
  • Akademie Věd České Republiky
  • Grantová Agentura České Republiky
  • Deutsche Forschungsgemeinschaft

Cite

APA

Cai, L., Kreft, H., Taylor, A., Denelle, P., Schrader, J., Essl, F., van Kleunen, M., Pergl, J., Pyšek, P., Stein, A., Winter, M., Barcelona, J. F., Fuentes, N., Inderjit, Karger, D. N., Kartesz, J., Kuprijanov, A., Nishino, M., Nickrent, D., …, & Weigelt, P. (2023). Global models and predictions of plant diversity based on advanced machine learning techniques. New Phytologist, 237(4), 1432-1445. https://doi.org/10.1111/nph.18533

Vancouver

Cai L, Kreft H, Taylor A, Denelle P, Schrader J, Essl F, et al. Global models and predictions of plant diversity based on advanced machine learning techniques. New Phytologist. 2023;237(4):1432-1445. doi:10.1111/nph.18533

BibTeX
@article{Cai2023,
  author = {Cai, Lirong and Kreft, Holger and Taylor, Amanda and Denelle, Pierre and Schrader, Julian and Essl, Franz and van Kleunen, Mark and Pergl, Jan and Pyšek, Petr and Stein, Anke and Winter, Marten and Barcelona, Julie F and Fuentes, Nicol and Inderjit and Karger, Dirk Nikolaus and Kartesz, John and Kuprijanov, Andreij and Nishino, Misako and Nickrent, Daniel and Nowak, Arkadiusz and Patzelt, Annette and Pelser, Pieter B and Singh, Paramjit and Wieringa, Jan J and Weigelt, Patrick},
  title = {Global models and predictions of plant diversity based on advanced machine learning techniques},
  journal = {New Phytologist},
  year = {2023},
  volume = {237},
  number = {4},
  pages = {1432--1445},
  doi = {10.1111/nph.18533}
}
Start for free →