Cargando…

Estimating Alpha, Beta, and Gamma Diversity Through Deep Learning

The reliable mapping of species richness is a crucial step for the identification of areas of high conservation priority, alongside other value and threat considerations. This is commonly done by overlapping range maps of individual species, which requires dense availability of occurrence data or re...

Descripción completa

Detalles Bibliográficos
Autores principales: Andermann, Tobias, Antonelli, Alexandre, Barrett, Russell L., Silvestro, Daniele
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9062518/
https://www.ncbi.nlm.nih.gov/pubmed/35519811
http://dx.doi.org/10.3389/fpls.2022.839407
_version_ 1784698961069604864
author Andermann, Tobias
Antonelli, Alexandre
Barrett, Russell L.
Silvestro, Daniele
author_facet Andermann, Tobias
Antonelli, Alexandre
Barrett, Russell L.
Silvestro, Daniele
author_sort Andermann, Tobias
collection PubMed
description The reliable mapping of species richness is a crucial step for the identification of areas of high conservation priority, alongside other value and threat considerations. This is commonly done by overlapping range maps of individual species, which requires dense availability of occurrence data or relies on assumptions about the presence of species in unsampled areas deemed suitable by environmental niche models. Here, we present a deep learning approach that directly estimates species richness, skipping the step of estimating individual species ranges. We train a neural network model based on species lists from inventory plots, which provide ground truth data for supervised machine learning. The model learns to predict species richness based on spatially associated variables, including climatic and geographic predictors, as well as counts of available species records from online databases. We assess the empirical utility of our approach by producing independently verifiable maps of alpha, beta, and gamma plant diversity at high spatial resolutions for Australia, a continent with highly heterogeneous diversity patterns. Our deep learning framework provides a powerful and flexible new approach for estimating biodiversity patterns, constituting a step forward toward automated biodiversity assessments.
format Online
Article
Text
id pubmed-9062518
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-90625182022-05-04 Estimating Alpha, Beta, and Gamma Diversity Through Deep Learning Andermann, Tobias Antonelli, Alexandre Barrett, Russell L. Silvestro, Daniele Front Plant Sci Plant Science The reliable mapping of species richness is a crucial step for the identification of areas of high conservation priority, alongside other value and threat considerations. This is commonly done by overlapping range maps of individual species, which requires dense availability of occurrence data or relies on assumptions about the presence of species in unsampled areas deemed suitable by environmental niche models. Here, we present a deep learning approach that directly estimates species richness, skipping the step of estimating individual species ranges. We train a neural network model based on species lists from inventory plots, which provide ground truth data for supervised machine learning. The model learns to predict species richness based on spatially associated variables, including climatic and geographic predictors, as well as counts of available species records from online databases. We assess the empirical utility of our approach by producing independently verifiable maps of alpha, beta, and gamma plant diversity at high spatial resolutions for Australia, a continent with highly heterogeneous diversity patterns. Our deep learning framework provides a powerful and flexible new approach for estimating biodiversity patterns, constituting a step forward toward automated biodiversity assessments. Frontiers Media S.A. 2022-04-19 /pmc/articles/PMC9062518/ /pubmed/35519811 http://dx.doi.org/10.3389/fpls.2022.839407 Text en Copyright © 2022 Andermann, Antonelli, Barrett and Silvestro. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Plant Science
Andermann, Tobias
Antonelli, Alexandre
Barrett, Russell L.
Silvestro, Daniele
Estimating Alpha, Beta, and Gamma Diversity Through Deep Learning
title Estimating Alpha, Beta, and Gamma Diversity Through Deep Learning
title_full Estimating Alpha, Beta, and Gamma Diversity Through Deep Learning
title_fullStr Estimating Alpha, Beta, and Gamma Diversity Through Deep Learning
title_full_unstemmed Estimating Alpha, Beta, and Gamma Diversity Through Deep Learning
title_short Estimating Alpha, Beta, and Gamma Diversity Through Deep Learning
title_sort estimating alpha, beta, and gamma diversity through deep learning
topic Plant Science
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9062518/
https://www.ncbi.nlm.nih.gov/pubmed/35519811
http://dx.doi.org/10.3389/fpls.2022.839407
work_keys_str_mv AT andermanntobias estimatingalphabetaandgammadiversitythroughdeeplearning
AT antonellialexandre estimatingalphabetaandgammadiversitythroughdeeplearning
AT barrettrusselll estimatingalphabetaandgammadiversitythroughdeeplearning
AT silvestrodaniele estimatingalphabetaandgammadiversitythroughdeeplearning