A New Method for Counting Reproductive Structures in Digitized Herbarium Specimens Using Mask R-CNN
A New Method for Counting Reproductive Structures in Digitized Herbarium Specimens Using Mask R-CNN
复制标题
DOI：
10.3389/fpls.2020.01129
复制
发表时间：
2020-07-31
影响因子：
5.6
通讯作者：
Bonnet, Pierre
中科院分区：
文献类型：
--
作者：
Davis, Charles C.;Champ, Julien;Bonnet, Pierre
物候学-生命史事件的时间-是理解生物对气候反应的关键特征。植物标本馆标本的数字化和在线移动正在迅速推进我们对植物物候对气候和气候变化的反应的理解。然而，目前手动采集单个标本数据的做法极大地限制了我们扩大数据收集的能力。最近的调查表明，机器学习方法可以促进这一努力。然而，目前的尝试主要集中在生殖物候的简单化二进制编码（例如，有/没有花）。在这里，我们使用了来自美国东部六种常见野花（Anemone canadensisL.，A.肝，A.西洋参属，延龄草，T. grandiflorum（Michx.）Salisb.，和T. undulatumWild.）使用Mask R-CNN来训练模型，以分割和计数物候特征。单个全局模型能够自动化三个生殖阶段中每个阶段的二进制编码，准确率>87%。我们还成功地估计了标本上每个生殖结构的相对丰度，准确率>= 90%。精确计数的功能也是成功的，但准确性与物候阶段和taxon. Specifically，计数花是显着不准确的芽或果实可能由于其形态变异的压制标本。此外，我们的Mask R-CNN模型比非专家众包提供了更可靠的数据，但不是植物学专家，突出了高质量人类训练数据的重要性。最后，我们还证明了我们的模型的可移植性，自动物候期检测和计数的threeTrilliumspecies，这有大的和显着的形状的生殖器官。这些结果突出了我们的两阶段众包和机器学习管道的承诺，以分割和计算植物标本的繁殖特征，从而提供高质量的数据，以调查植物对持续气候变化的反应。
Phenology-the timing of life-history events-is a key trait for understanding responses of organisms to climate. The digitization and online mobilization of herbarium specimens is rapidly advancing our understanding of plant phenological response to climate and climatic change. The current practice of manually harvesting data from individual specimens, however, greatly restricts our ability to scale-up data collection. Recent investigations have demonstrated that machine-learning approaches can facilitate this effort. However, present attempts have focused largely on simplistic binary coding of reproductive phenology (e.g., presence/absence of flowers). Here, we use crowd-sourced phenological data of buds, flowers, and fruits from >3,000 specimens of six common wildflower species of the eastern United States (Anemone canadensisL.,A. hepaticaL.,A. quinquefoliaL.,Trillium erectumL.,T. grandiflorum(Michx.) Salisb., andT. undulatumWild.) to train models using Mask R-CNN to segment and count phenological features. A single global model was able to automate the binary coding of each of the three reproductive stages with >87% accuracy. We also successfully estimated the relative abundance of each reproductive structure on a specimen with >= 90% accuracy. Precise counting of features was also successful, but accuracy varied with phenological stage and taxon. Specifically, counting flowers was significantly less accurate than buds or fruits likely due to their morphological variability on pressed specimens. Moreover, our Mask R-CNN model provided more reliable data than non-expert crowd-sourcers but not botanical experts, highlighting the importance of high-quality human training data. Finally, we also demonstrated the transferability of our model to automated phenophase detection and counting of the threeTrilliumspecies, which have large and conspicuously-shaped reproductive organs. These results highlight the promise of our two-phase crowd-sourcing and machine-learning pipeline to segment and count reproductive features of herbarium specimens, thus providing high-quality data with which to investigate plant responses to ongoing climatic change.