Deep learning and citizen science enable automated plant trait predictions from photographs

Abstract Plant functional traits (‘traits’) are essential for assessing biodiversity and ecosystem processes, but cumbersome to measure. To facilitate trait measurements, we test if traits can be predicted through visible morphological features by coupling heterogeneous photographs from citizen scie...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Christopher Schiller, Sebastian Schmidtlein, Coline Boonman, Alvaro Moreno-Martínez, Teja Kattenborn
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/107cbdaa3c7241659a83173551fcdcc3
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:107cbdaa3c7241659a83173551fcdcc3
record_format	dspace
spelling	oai:doaj.org-article:107cbdaa3c7241659a83173551fcdcc32021-12-02T19:06:33ZDeep learning and citizen science enable automated plant trait predictions from photographs10.1038/s41598-021-95616-02045-2322https://doaj.org/article/107cbdaa3c7241659a83173551fcdcc32021-08-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-95616-0https://doaj.org/toc/2045-2322Abstract Plant functional traits (‘traits’) are essential for assessing biodiversity and ecosystem processes, but cumbersome to measure. To facilitate trait measurements, we test if traits can be predicted through visible morphological features by coupling heterogeneous photographs from citizen science (iNaturalist) with trait observations (TRY database) through Convolutional Neural Networks (CNN). Our results show that image features suffice to predict several traits representing the main axes of plant functioning. The accuracy is enhanced when using CNN ensembles and incorporating prior knowledge on trait plasticity and climate. Our results suggest that these models generalise across growth forms, taxa and biomes around the globe. We highlight the applicability of this approach by producing global trait maps that reflect known macroecological patterns. These findings demonstrate the potential of Big Data derived from professional and citizen science in concert with CNN as powerful tools for an efficient and automated assessment of Earth’s plant functional diversity.Christopher SchillerSebastian SchmidtleinColine BoonmanAlvaro Moreno-MartínezTeja KattenbornNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-12 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Christopher Schiller Sebastian Schmidtlein Coline Boonman Alvaro Moreno-Martínez Teja Kattenborn Deep learning and citizen science enable automated plant trait predictions from photographs
description	Abstract Plant functional traits (‘traits’) are essential for assessing biodiversity and ecosystem processes, but cumbersome to measure. To facilitate trait measurements, we test if traits can be predicted through visible morphological features by coupling heterogeneous photographs from citizen science (iNaturalist) with trait observations (TRY database) through Convolutional Neural Networks (CNN). Our results show that image features suffice to predict several traits representing the main axes of plant functioning. The accuracy is enhanced when using CNN ensembles and incorporating prior knowledge on trait plasticity and climate. Our results suggest that these models generalise across growth forms, taxa and biomes around the globe. We highlight the applicability of this approach by producing global trait maps that reflect known macroecological patterns. These findings demonstrate the potential of Big Data derived from professional and citizen science in concert with CNN as powerful tools for an efficient and automated assessment of Earth’s plant functional diversity.
format	article
author	Christopher Schiller Sebastian Schmidtlein Coline Boonman Alvaro Moreno-Martínez Teja Kattenborn
author_facet	Christopher Schiller Sebastian Schmidtlein Coline Boonman Alvaro Moreno-Martínez Teja Kattenborn
author_sort	Christopher Schiller
title	Deep learning and citizen science enable automated plant trait predictions from photographs
title_short	Deep learning and citizen science enable automated plant trait predictions from photographs
title_full	Deep learning and citizen science enable automated plant trait predictions from photographs
title_fullStr	Deep learning and citizen science enable automated plant trait predictions from photographs
title_full_unstemmed	Deep learning and citizen science enable automated plant trait predictions from photographs
title_sort	deep learning and citizen science enable automated plant trait predictions from photographs
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/107cbdaa3c7241659a83173551fcdcc3
work_keys_str_mv	AT christopherschiller deeplearningandcitizenscienceenableautomatedplanttraitpredictionsfromphotographs AT sebastianschmidtlein deeplearningandcitizenscienceenableautomatedplanttraitpredictionsfromphotographs AT colineboonman deeplearningandcitizenscienceenableautomatedplanttraitpredictionsfromphotographs AT alvaromorenomartinez deeplearningandcitizenscienceenableautomatedplanttraitpredictionsfromphotographs AT tejakattenborn deeplearningandcitizenscienceenableautomatedplanttraitpredictionsfromphotographs
_version_	1718377131240587264

Deep learning and citizen science enable automated plant trait predictions from photographs

Ejemplares similares