Leveraging machine learning and citizen science data to describe flowering phenology across South Africa

Abstract

O_LIPhenology -- the timing of recurring life history events--is strongly linked to climate. Shifts in phenology have important implications for trophic interactions, ecosystem functioning and community ecology. However, data on plant phenology can be time consuming to collect and current records are biased across space and taxonomy. C_LIO_LIHere, we explore the performance of Convolutional Neural Networks (CNN) for classifying flowering phenology on a very large and taxonomically diverse dataset of citizen science images. We analyse >1.8 million iNaturalist records for plants listed in the National Botanical Gardens within South Africa, a country famed for its floristic diversity ([~]21,000 species) but poorly represented in phenological databases. C_LIO_LIWe were able to correctly classify images with >90% accuracy. Using metadata associated with each image, we then reconstructed the timing of peak flower production and length of the flowering season for the 6,986 species with >5 iNaturalist records. C_LIO_LIOur analysis illustrates how machine learning tools can leverage the vast wealth of citizen science biodiversity data to describe large-scale phenological dynamics. We suggest such approaches may be particularly valuable where data on plant phenology is currently lacking. C_LI

Plant phenotyping relevance

植物画像にCNNを適用して開花フェノロジーを分類し、開花時期と開花期間を推定する手法が研究の中心であるため、植物フェノタイピング手法研究に該当します。

Code and data availability

The authors publicly release all data and R code needed to recreate the analyses on GitHub (ML-Phenology-Code), and the phenotyping input data are iNaturalist research-grade observation images (1,807,310 images) downloaded via the iNaturalist GBIF DarwinCore Archive, both publicly accessible.