Quantifying Tropical Plant Diversity Requires an Integrated Technological Approach. (December 2020)

• Record Type: Journal Article
• Authors: Draper, Frederick C.; Baker, Timothy R.; Baraloto, Christopher; Chave, Jerome; Costa, Flavia; Martin, Roberta E.; Pennington, R. Toby; Vicentini, Alberto; Asner, Gregory P.
• Is Part Of: Trends in ecology & evolution. Volume 35:Number 12(2020)
• Page Start: 1100
• Page End: 1109
• Publication Date: 2020-12
• Subjects: tropical botany -- plant biodiversity -- technology -- spectroscopy -- DNA -- artificial intelligence; Ecology -- Periodicals; Evolution (Biology) -- Periodicals; 576.8
• DOI: 10.1016/j.tree.2020.08.003
• Languages: English
• ISSNs: 0169-5347

Abstract

Abstract : Tropical biomes are the most diverse plant communities on Earth, and quantifying this diversity at large spatial scales is vital for many purposes. As macroecological approaches proliferate, the taxonomic uncertainties in species occurrence data are easily neglected and can lead to spurious findings in downstream analyses. Here, we argue that technological approaches offer potential solutions, but there is no single silver bullet to resolve uncertainty in plant biodiversity quantification. Instead, we propose the use of artificial intelligence (AI) approaches to build a data-driven framework that integrates several data sources – including spectroscopy, DNA sequences, image recognition, and morphological data. Such a framework would provide a foundation for improving species identification in macroecological analyses while simultaneously improving the taxonomic process of species delimitation. Highlights: Quantifying plant biodiversity in tropical forests is a major challenge. Increasingly, large-scale synthetic studies are attempting to meet this challenge but are limited by insufficient species occurrence data that is exacerbated by taxonomic uncertainties. To quantify tropical forest biodiversity fully depends upon accurate species identifications, and we argue that these can be achieved by using an integrated synthesis of technological approaches including spectroscopy, DNA sequencing, and image recognition, alongside traditional morphological approaches to species delimitation and identification. Crucially, AI approaches could be used to integrate these different technologies and data sources in an objective, repeatable, and scalable way. Our approach would maximize the utility of existing data and collections to build a standardised framework for identifying tropical plants and at the same time could contribute to species discovery and improve underlying taxonomy.