KIT | KIT-Bibliothek | Impressum | Datenschutz

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

Schiller, Christopher 1; Schmidtlein, Sebastian 1; Boonman, Coline; Moreno-Martínez, Alvaro; Kattenborn Teja
1 Institut für Geographie und Geoökologie (IFGG), Karlsruher Institut für Technologie (KIT)


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.

Verlagsausgabe §
DOI: 10.5445/IR/1000137011
Veröffentlicht am 12.09.2021
DOI: 10.1038/s41598-021-95616-0
Zitationen: 6
Web of Science
Zitationen: 6
Zitationen: 9
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Geographie und Geoökologie (IFGG)
Publikationstyp Zeitschriftenaufsatz
Publikationsjahr 2021
Sprache Englisch
Identifikator ISSN: 2045-2322
KITopen-ID: 1000137011
Erschienen in Scientific Reports
Verlag Nature Research
Band 11
Heft 1
Seiten Art.-Nr.: 16395
Nachgewiesen in Scopus
Web of Science
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page