Global patterns of vascular plant alpha diversity

Sabatini, Francesco; Jíménez-Alfaro, Borja; Jandt, Ute; Chytrý, Milan; Field, Richard; Kessler, Michael; Lenoir, Jonathan; Schrodt, Franziska; Wiser, Susan K.; Khan, Mohammed Abu Sayed Arfin; Attorre, Fabio; Cayuela, Luis; Sanctis, Michele De; Dengler, Jürgen; Haider, Sylvia; Hatim, Mohamed Z.; Indreica, Adrian; Jansen, Florian; Pauchard, Aníbal; Peet, Robert K.; Petřík, Petr; Pillar, Valério D.; Sandel, Brody; Schmidt, Marco; Tang, Zhiyao; Bodegom, Peter M. van; Vassilev, Kiril; Violle, Cyrille; Álvarez-Dávila, Esteban; Davidar, Priya; Doležal, Jiří; Hérault, Bruno; Mera, Antonio Galán de; Jiménez, Josué; Kambach, Stephan; Kepfer‐Rojas, Sebastian; Kreft, Holger; Lezama, Felipe; Linares-Palomino, Reynaldo; Mendoza, Abel Monteagudo; N’dja, Justin Kassi; Phillips, Oliver L.; Rivas‐Torres, Gonzalo; Sklenář, Petr; Speziale, Karina L.; Strohbach, Ben J.; Martínez, Rodolfo Vásquez; Wang, Huafeng; Wesche, Karsten; Bruelheide, Helge

doi:10.1038/s41467-022-32063-z

Cited by 90 publications

(87 citation statements)

References 178 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning models are known to not extrapolate well under such conditions (Elith et al ., 2010). Second, even for regions with relatively homogeneous environments, checklists and floras do not only include information on predominant but also azonal vegetation, making them richer than expected from their prevailing conditions and observed at a more local scale (compared to alpha diversity predictions in Sabatini et al ., 2022).…”

Section: Resultsmentioning

confidence: 99%

“…Machine learning approaches represent powerful modeling tools that can effectively deal with multidimensional and correlated data and can reveal nonlinear relationships and interactions of predictors without a priori specification (Olden et al ., 2008; Crisci et al ., 2012). Therefore, machine learning has become a promising alternative to conventional techniques in ecology (Hengl et al ., 2017; Park et al ., 2020; Sabatini et al ., 2022). However, its performance in modeling global plant diversity has yet to be explored.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

et al. 2022

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

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

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…and Sabatini et al . (2022) predict diversity across specific ranges of grain size, these results cannot be extrapolated to all possible spatial scales. Specifically, there remains an important gap of knowledge on global patterns of species richness at the landscape scale (Fig.…”

Section: Diversity Across Scalesmentioning

confidence: 95%

“…Just a few months earlier, Sabatini et al . (2022) modeled plant plot‐level diversity across grain sizes using a machine learning method. Although both the models by Cai et al .…”

Section: Diversity Across Scalesmentioning

confidence: 99%

Macroecology of plant diversity across spatial scales

Puglielli

Pärtel

2023

New Phytologist

View full text Add to dashboard Cite

The distribution of vascular plants on Earth has puzzled scientists for at least three centuries. The description of the first patterns of vascular plants species richnessthe number of species living in a region at a given timedates to Alexander von Humboldt (e.g. the 'latitudinal gradient of diversity ', von Humboldt, 1806). Since the pioneering work of von Humboldt, followed by early approaches for mapping species richness (e.g. Wulff, 1935), (macro)ecologists worldwide have attempted to refine mapping methods, to quantify plant diversity globally and to disentangle its underlying drivers. However, patterns of species richness are scale dependent, originating from the nonlinearity of the 'species-area relationship ' (Arrhenius, 1921). In addition, the multiple determinants of species richness might interact in complex ways, being also habitat dependent and scale dependent (Keil & Chase, 2019). Cai et al. (2023), in this issue of New Phytologist (Cai et al., 2023; pp. 1432-1445, by benefiting from up-to-date machine learning techniques, present a framework to bring a new quality to the global species and phylogenetic diversity predictions across a range of regional grain sizes.

show abstract

“…In terrestrial vegetation, only woody species were recorded since the sampling period was conditioned by the accessibility to the area in the dry season when herbaceous plants are not developed. Further, tropical forests have a relatively species-poor herb layer compared to temperate forest ecosystems (Sabatini et al 2022).…”

Section: Data Collectionmentioning

confidence: 99%

BOVEDA, the Bolivian Vegetation Ecology Database: first stage, the Chacoan forests

Oliveira¹,

Molina²,

Navarro³

2022

VCS

View full text Add to dashboard Cite

Bolivia is a country exceptionally rich in biodiversity and home to about 20,000 vascular plant species and 15 plant formations. Therefore, it is particularly important to document the biodiversity of this territory. The aim of the Bolivian Vegetation Ecology Database (BOVEDA; GIVD ID SA-BO-005) is to record floristic and ecological data of Bolivian vegetation. In the first stage, the database hosts 320 relevés from one of the most unique biogeographical units in the country, the Chaco. In total, 633 species belonging to 114 families have been recorded. Data on vegetation structure, soil, flooding regime and geomorphology have also been stored. The following nine vegetation structural types were identified: (1) deciduous forests of alluvial plains on well to moderately well drained soils; (2) deciduous to semideciduous Chaco forests transitional to the Andes; (3) deciduous and sclerophyllous Cerrado thorn-woodlands and shrublands transitional to the Chaco (Abayoy); (4) xeromorphic thorn shrubland and thickets on vertic, poorly drained soils; (5) woodlands and savannas on sand dunes and aeolian surfaces; (6) freshwater swamp forests; (7) saltwater swamp forests; (8) phreatophytic forests; (9) deciduous to semideciduous Chaco forests transitional to the Chiquitania. Further steps will be to incorporate new types of vegetation already recorded in the field such as Altiplano shrublands, Andean wetlands, Andean Polylepis forests, and vegetation of the dry inter-Andean valleys. Taxonomic reference: Jørgensen et al. (2015). Abbreviations: BOVEDA = Bolivian Vegetation Ecology Database; GIVD = Global Index of Vegetation-Plot Databases.

show abstract

Global patterns of vascular plant alpha diversity

Cited by 90 publications

References 178 publications

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

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

Macroecology of plant diversity across spatial scales

BOVEDA, the Bolivian Vegetation Ecology Database: first stage, the Chacoan forests

Contact Info

Product

Resources

About

Global patterns of vascular plant alpha diversity

Cited by 90 publications

References 178 publications

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

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

Macroecology of plant diversity across spatial scales

﻿BOVEDA, the Bolivian Vegetation Ecology Database: first stage, the Chacoan forests

Contact Info

Product

Resources

About

BOVEDA, the Bolivian Vegetation Ecology Database: first stage, the Chacoan forests