Accurate taxonomic identification of diatoms is essential for aquatic ecosystem monitoring, yet conventional methods depend heavily on expert taxonomists. Recent deep learning approaches improve automation, but most treat diatom recognition as flat classification, predicting only one taxonomic rank. We investigate whether embedding taxonomic hierarchy into neural network architectures can improve both accuracy and error locality. We introduce DiatomCascadeNet (H-COFGS), a hierarchical convolutional network with five cascaded heads that jointly predict class, order, family, genus, and species. Each head receives shared backbone features and probability distributions from higher levels, with binary masks restricting predictions to valid descendants during training and inference. Using a filtered dataset of 1,456 diatom images covering 82 species, we compare hierarchical and flat models under identical settings. H-COFGS matches flat baselines at the species level (69.4% accuracy) while outperforming at all upper taxonomic levels. When species predictions fail, errors remain taxonomically local: 92.5% of misclassified species are correctly predicted at the genus level, versus 67.2% for flat baselines. H-COFGS reduces mean taxonomic distance by 38.2% (1.209 vs. 1.955). Progressive training reveals bidirectional mechanisms: hierarchical constraint masks operate top-down to constrain prediction space, while gradients from fine-grained levels propagate bottom-up through the shared backbone, refining features. This improves class accuracy from 96.2% to 99.5% and yields 6-8% gains at upper levels, producing more robust, interpretable, and biologically aligned predictions for multi-level taxonomic classification.

翻译：硅藻的精确分类学鉴定对于水生生态系统监测至关重要，然而传统方法高度依赖专家分类学家。近期的深度学习方法提升了自动化水平，但大多将硅藻识别视为扁平分类，仅预测单一分类等级。本研究探讨将分类学层次结构嵌入神经网络架构是否能同时提升准确性和错误定位能力。我们提出了DiatomCascadeNet（H-COFGS），这是一种具有五个级联头的层次化卷积网络，可联合预测纲、目、科、属和种。每个头接收共享主干特征及来自更高层级的概率分布，并通过二元掩码在训练和推理过程中将预测限制在有效后代分类群内。使用包含82个物种的1,456张硅藻图像过滤数据集，我们在相同设置下比较了层次化与扁平模型。H-COFGS在物种层级达到与扁平基线相当的准确率（69.4%），并在所有上级分类层级上表现更优。当物种预测失败时，错误仍保持分类学局部性：92.5%的错误分类物种在属级被正确预测，而扁平基线仅为67.2%。H-COFGS将平均分类学距离降低了38.2%（1.209对比1.955）。渐进式训练揭示了双向机制：层次化约束掩码自上而下地限制预测空间，而细粒度层级的梯度通过共享主干自下而上传播，从而优化特征表示。这使得纲级准确率从96.2%提升至99.5%，并在上级层级获得6-8%的性能增益，为多级分类学分类提供了更鲁棒、可解释且符合生物学规律的预测。