通过虫体花粉识别构建植物‒传粉者网络: 人工模型与AI模型高度一致

巴苏艳, 赵春艳, 刘媛, 方强

Constructing a pollination network by identifying pollen on insect bodies: Consistency between human recognition and an AI model

Suyan Ba, Chunyan Zhao, Yuan Liu, Qiang Fang

图1 AI模型的训练效果。(a)不同阈值下的模型准确率, 阈值为0.8时模型达到最高准确率96%。对某类别而言F1-score是指精确率和召回率的调和平均数, 此处为各类别F1-score的平均数。(b)‒(e) AI模型对不同物种花粉图像的识别准确率: (b)瓜木98.2%; (c)一年蓬87.5%; (d)繁缕96.4%; (e)花旗杆91.4%。

Fig. 1 AI model training effect. (a) Model accuracy under different thresholds, the highest accuracy of the model is 96% when the threshold is 0.8. F1-score refers to the harmonic average of accuracy and recall for a category, where the average of F1-score for each category is shown. (b)‒(e) The recognition accuracy of the AI model for pollen images of different species: (b) Alangium platanifolium, 98.2%; (c) Erigeron annuus, 87.5%; (d) Stellaria media, 96.4%; (e) Dontostemon dentatus, 91.4%.