Department of Entomology, National Taiwan University, Taipei City, 10617, Taiwan.
Institute of Hydrobiology, Chinese Academy of Sciences, Wuhan City, 430072, China.
Sci Rep. 2020 Sep 3;10(1):14632. doi: 10.1038/s41598-020-71798-x.
The accurate identification of biological control agents is necessary for monitoring and preventing contamination in integrated pest management (IPM); however, this is difficult for non-taxonomists to achieve in the field. Many machine learning techniques have been developed for multiple applications (e.g., identification of biological organisms). Some phytoseiids are biological control agents for small pests, such as Neoseiulus barkeri Hughes. To identify a precise biological control agent, a boosting machine learning classification, namely eXtreme Gradient Boosting (XGBoost), was introduced in this study for the semi-automated identification of phytoseiid mites. XGBoost analyses were based on 22 quantitative morphological features among 512 specimens of N. barkeri and related phytoseiid species. These features were extracted manually from photomicrograph of mites and included dorsal and ventrianal shield lengths, setal lengths, and length and width of spermatheca. The results revealed 100% accuracy rating, and seta j4 achieved significant discrimination among specimens. The present study provides a path through which skills and experiences can be transferred between experts and non-experts. This can serve as a foundation for future studies on the automated identification of biological control agents for IPM.
准确识别生物防治剂对于综合虫害管理（IPM）中的监测和防止污染是必要的；然而，对于非分类学家来说，在现场做到这一点是很困难的。许多机器学习技术已经被开发出来用于多种应用（例如，生物有机体的识别）。一些捕食螨是小型害虫的生物防治剂，如 Neoseiulus barkeri Hughes。为了识别精确的生物防治剂，本研究引入了一种机器学习分类的提升方法，即极端梯度提升（XGBoost），用于半自动化识别捕食螨。XGBoost 分析基于 512 个 N. barkeri 和相关捕食螨种的 22 个定量形态特征。这些特征是从螨虫的显微照片中手动提取的，包括背盾和腹盾的长度、刚毛的长度以及精囊的长度和宽度。结果显示准确率达到 100%，刚毛 j4 对标本有显著的区分能力。本研究提供了一种在专家和非专家之间转移技能和经验的途径。这可以为未来的 IPM 中生物防治剂自动识别的研究奠定基础。
