2026-06-16 ミシガン大学
ミシガン大学の研究チームは、植物化石や花粉などの植生データと人工知能（AI）を組み合わせ、過去の気候や環境を高精度に復元する新たな解析手法を開発した。従来の古気候復元では、限られた化石記録や専門家による解釈に依存する部分が大きかったが、新手法では機械学習を用いて植物種の分布と環境条件の関係を学習し、過去の気温や降水量、生態系の変化を推定する。これにより、地球環境が過去の気候変動にどのように応答したかをより詳細に理解できるようになる。研究成果は、将来の気候変動予測の精度向上にも貢献する可能性があり、生態学、古環境学、データ科学を融合した新たな研究アプローチとして注目されている。
LeafMachine2 logo. Image courtesy of the researchers
＜関連情報＞
- https://news.umich.edu/u-m-researchers-develop-ai-tool-using-plants-to-peer-into-the-past/
- https://nph.onlinelibrary.wiley.com/doi/full/10.1111/nph.70292
- https://www.kew.org/science/state-of-the-worlds-plants-and-fungi
デジタル化された植物標本から単位面積当たりの葉質量を自動抽出する Automated extraction of leaf mass per area from digitized herbarium specimens
Thais Vasconcelos, William N. Weaver, Aly Baumgartner, Zoë Bugnaski, James Boyko
New Phytologist Published: 18 June 2025
DOI:https://doi.org/10.1111/nph.70292
Summary
- 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 (LMApred) 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. LMApred is estimated using a proxy equation that models the scaling relationship between petiole width and leaf mass. We assess potential sources of error in LMApred estimates and evaluate whether documented LMA–climate patterns are recovered using this dataset and phylogenetic comparative methods.
- Our LMApred 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 LMApred 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.
