Machine-learning techniques, namely deep convolutional neural networks, are
pivotal for image-based identification of biological species in many Citizen
Science platforms. However, the construction of critically sized and sampled
datasets to train the networks and the choice of the network architectures
itself remains little documented and, therefore, does not lend itself to be
easily replicated. In this paper, we develop a streamlined methodology for
building datasets for biological taxa from publicly available research-grade
datasets and for deriving models from these datasets using off-the-shelf deep
convolutional neural networks such as those provided by Google's AutoML Vision
cloud service. Our case study is the Portuguese native flora, anchored in a
high-quality dataset, provided by the Sociedade Portuguesa de Bot\^anica,
scaled up by adding sampled data from iNaturalist, Pl@ntNet, and
Observation.org. We find that with a careful dataset design, off-the-shelf
machine-learning cloud services produce accurate models with relatively little
effort that rival those provided by state-of-the-art citizen science platforms.
The best model we derived, dubbed Floralens, has been integrated into the
public website of Project Biolens, where we gather models for other taxa as
well. The dataset used to train the model and its namesake is publicly
available on Zenodo.

使用机器学习技术，特别是深度卷积神经网络，对生物种类进行基于图像的识别在很多公众科学平台中至关重要。然而，关于训练网络所需的关键数据集构建和网络架构的选择目前有很少的文献资料，因此难以复制。本文提出了一种简化的方法，通过使用公开可用的研究级数据集，构建生物分类的数据集，并使用 Google 的 AutoML Vision 云服务的现成深度卷积神经网络模型。以葡萄牙本土植物为案例研究，该案例研究依托于葡萄牙植物学会提供的高质量数据集，并通过添加来自 iNaturalist、Pl@ntNet 和 Observation.org 的采样数据扩大。我们发现，通过精心设计数据集，现成的机器学习云服务可以轻松生成与最先进的公众科学平台相媲美的准确模型。我们开发的最佳模型，名为 Floralens，已集成到 Project Biolens 的公共网站中，在该网站中我们收集了其他分类的模型。训练该模型所使用的数据集和模型本身均可在 Zenodo 上公开获取。