1. Pollen analysis is an important tool in many fields, including pollination ecology, paleoclimatology, paleoecology, honey quality control, and even medicine and forensics. However, labour‐intensive manual pollen analysis often constrains the number of samples processed or the number of pollen analysed per sample. Thus, there is a desire to develop reliable, high‐throughput, automated systems.
2. We present an automated method for pollen analysis, based on deep learning convolutional neural networks (CNN). We scanned microscope slides with fuchsine stained, fresh pollen and automatically extracted images of all individual pollen grains. CNN models were trained on reference samples (122,000 pollen grains, from 347 flowers of 83 species of 17 families). The models were used to classify images of different pollen grains in a series of experiments. We also propose an adjustment to reduce overestimation of sample diversity in cases where samples are likely to contain few species.
3. Accuracy of a model for 83 species was 0.98 when all samples of each species were first pooled, and then split into a training and a validation set (splitting experiment). However, accuracy was much lower (0.41) when individual reference samples from different flowers were kept separate, and one such sample was used for validation of models trained on remaining samples of the species (leave‐one‐out experiment). We therefore combined species into 28 pollen types where a new leave‐one‐out experiment revealed an overall accuracy of 0.68, and recall rates >0.90 in most pollen types. When validating against 63,650 manually identified pollen grains from 370 bumblebee samples, we obtained an accuracy of 0.79, but our adjustment procedure increased this to 0.85.
4. Validation through splitting experiments may overestimate robustness of CNN pollen analysis in new contexts (samples). Nevertheless, our method has the potential to allow large quantities of real pollen data to be analysed with reasonable accuracy. Although compiling pollen reference libraries is time‐consuming, this is simplified by our method, and can lead to widely accessible and shareable resources for pollen analysis.

中文翻译：

---

使用深度学习进行高效，自动化和强大的花粉分析

1. 花粉分析是许多领域的重要工具，包括授粉生态学，古气候学，古生态学，蜂蜜质量控制，甚至医学和法医学。但是，劳动密集型的手动花粉分析通常会限制处理的样品数量或每个样品的花粉分析数量。因此，需要开发可靠的，高吞吐量的自动化系统。
2. 我们提出了一种基于深度学习卷积神经网络（CNN）的自动花粉分析方法。我们用紫红色染色的新鲜花粉扫描了显微镜载玻片，并自动提取了所有单个花粉粒的图像。使用参考样本（来自17个科的83种347朵花的122,000个花粉粒）对CNN模型进行了训练。在一系列实验中，使用该模型对不同花粉粒的图像进行分类。我们还提出了一项调整措施，以减少在样本中可能包含的物种很少的情况下对样本多样性的高估。
3. 首先将每个物种的所有样本汇总，然后分成训练和验证集（分割实验），对于83个物种的模型的准确性为0.98。但是，当将来自不同花朵的单个参考样品分开放置时，准确度要低得多（0.41），并且使用一个这样的样品来验证对该物种的其余样品进行训练的模型（不做一次实验）。因此，我们将物种划分为28种花粉类型，其中一项新的留一法实验显示总体准确性为0.68，大多数花粉类型的召回率> 0.90。当对370个大黄蜂样品中的63,650个人工鉴定的花粉粒进行验证时，我们获得了0.79的准确度，但是我们的调整程序将其提高到0.85。
4. 通过拆分实验进行的验证可能会高估新环境（样本）中CNN花粉分析的稳健性。然而，我们的方法有潜力允许以合理的精度分析大量的实际花粉数据。尽管编译花粉参考库很耗时，但是我们的方法简化了它，并且可以导致花粉分析的广泛访问和共享资源。