Robust ecological analysis of camera trap data labelled by a machine learning model
Robust ecological analysis of camera trap data labelled by a machine learning model
复制标题
DOI：
10.1111/2041-210x.13576
复制
发表时间：
2021-02
影响因子：
6.6
通讯作者：
Robin C. Whytock;J. Świeżewski;J. Zwerts;Tadeusz Bara‐Słupski;Aurélie Flore Koumba Pambo;Marek Rogala;L. Bahaa-el-din;K. Boekee;S. Brittain;Anabelle W. Cardoso;P. Henschel;David Lehmann;B. Momboua;Cisquet Kiebou Opepa;Christopher Orbell;Ross T. Pitman;H. Robinson;K. Abernethy
中科院分区：
文献类型：
--
作者：
Robin C. Whytock;J. Świeżewski;J. Zwerts;Tadeusz Bara‐Słupski;Aurélie Flore Koumba Pambo;Marek Rogala;L. Bahaa-el-din;K. Boekee;S. Brittain;Anabelle W. Cardoso;P. Henschel;David Lehmann;B. Momboua;Cisquet Kiebou Opepa;Christopher Orbell;Ross T. Pitman;H. Robinson;K. Abernethy
生态数据是使用相机陷阱和生物声波记录器等数字传感器在广阔的地理区域收集的。相机陷阱已经成为调查许多陆地哺乳动物和鸟类的标准方法，但相机陷阱阵列通常会生成数百万张图像，标记这些图像非常耗时。这在数据收集和随后的推断之间造成了很大的延迟，这阻碍了生态危机时期的保护。已经开发了机器学习算法来提高标记相机陷阱数据的速度，但目前还不确定这些模型的输出如何在没有人工二次验证的情况下用于生态分析。在这里，我们介绍了我们的方法来开发，测试和应用机器学习模型到相机陷阱数据，以实现全自动生态分析的目的。作为一个案例研究，我们建立了一个模型，对26种中非森林哺乳动物和鸟类(或组)进行分类。该模型推广到新的空间和时间独立的数据(n=227个摄像站点，n=23,868张图像)，并且在几个方面优于人类(例如，检测到‘看不见的’动物)。我们展示了生态学家如何通过比较来自机器学习标签的物种丰富度、活动模式(n=4个测试物种)和占用(n=4个测试物种)与来自专家标签的相同估计来评估机器学习模型在生态环境中的精确度和准确性。结果表明，在一个完全不在样本的大型测试数据集中计算物种丰富度、活动模式(n=4个测试物种)和估计占有率(n=4个测试物种中的3个)时，全自动物种标签可以等同于专家标签。在计算活动模式和估计占有率时，使用Softmax值的简单阈值(即排除不确定的标签)改善了模型的性能，但不能改善物种丰富度的估计。我们的结论是，通过在生态环境中进行充分的测试和评估，机器学习模型可以生成直接用于生态分析的标签，而不需要人工验证。我们为用户社区提供了一个多平台、多语言的图形用户界面，可用于离线运行我们的模型。
Ecological data are collected over vast geographic areas using digital sensors such as camera traps and bioacoustic recorders. Camera traps have become the standard method for surveying many terrestrial mammals and birds, but camera trap arrays often generate millions of images that are time‐consuming to label. This causes significant latency between data collection and subsequent inference, which impedes conservation at a time of ecological crisis. Machine learning algorithms have been developed to improve the speed of labelling camera trap data, but it is uncertain how the outputs of these models can be used in ecological analyses without secondary validation by a human. Here, we present our approach to developing, testing and applying a machine learning model to camera trap data for the purpose of achieving fully automated ecological analyses. As a case‐study, we built a model to classify 26 Central African forest mammal and bird species (or groups). The model generalizes to new spatially and temporally independent data (n = 227 camera stations, n = 23,868 images), and outperforms humans in several respects (e.g. detecting ‘invisible’ animals). We demonstrate how ecologists can evaluate a machine learning model's precision and accuracy in an ecological context by comparing species richness, activity patterns (n = 4 species tested) and occupancy (n = 4 species tested) derived from machine learning labels with the same estimates derived from expert labels. Results show that fully automated species labels can be equivalent to expert labels when calculating species richness, activity patterns (n = 4 species tested) and estimating occupancy (n = 3 of 4 species tested) in a large, completely out‐of‐sample test dataset. Simple thresholding using the Softmax values (i.e. excluding ‘uncertain’ labels) improved the model's performance when calculating activity patterns and estimating occupancy but did not improve estimates of species richness. We conclude that, with adequate testing and evaluation in an ecological context, a machine learning model can generate labels for direct use in ecological analyses without the need for manual validation. We provide the user‐community with a multi‐platform, multi‐language graphical user interface that can be used to run our model offline.