Automated extraction of leaf mass per area from digitized herbarium specimens.

Abstract

The digitization of vast herbarium collections has made millions of plant specimen images freely available online, which can now be used to generate phenotypic datasets of unprecedented scope. Here, we assess the potential of computer vision tools to automate the extraction of predicted leaf mass per area (LMA pred ) from digitized herbarium specimens. We use an automated pipeline to extract leaf area and petiole width from 22 680 leaves, representing a phylogenetic informed sample of 1580 species of woody angiosperms. LMA pred is estimated using a proxy equation that models the scaling relationship between petiole width and leaf mass. We assess potential sources of error in LMA pred estimates and evaluate whether documented LMA-climate patterns are recovered using this dataset and phylogenetic comparative methods. Our LMA pred dataset responds mainly to temperature and solar radiation and presents a positive correlation with latitude. The proxy equation, not the automated pipeline, is responsible for most of the error in LMA pred estimates. Our pipeline underscores the power of combining herbarium digitization with new techniques for automated trait scoring. The increased size of datasets generated using this tool allows investigation of potential LMA-climate relationships with a geographically balanced sample while also utilizing comprehensive phylogenetic information.

Plant phenotyping relevance

デジタル標本画像から葉面積・葉柄幅を自動抽出し、LMAを推定するコンピュータビジョン・パイプラインが中心であり、植物形質データセットの生成と誤差評価も行っている。

Code and data availability

The paper's Data Availability Statement explicitly deposits all data and code (the leaf_vision pipeline for automated LMA extraction from herbarium images) at the authors' public GitHub repository, which is an allowed URL. Supporting Information also contains the full LM2 measurement results (Table S2).