Monitoring leaf phenology in moist tropical forests by applying a superpixel-based deep learning method to time-series images of tree canopies
Monitoring leaf phenology in moist tropical forests by applying a superpixel-based deep learning method to time-series images of tree canopies
复制标题
DOI：
10.1016/j.isprsjprs.2021.10.023
复制
发表时间：
2022-01
影响因子：
12.7
通讯作者：
Guangqin Song;Shengbiao Wu;Calvin K. F. Lee;S. Serbin;B. Wolfe;Michael K. Ng;Kim S. Ely;Marc Bogonovich;Jing Wang;Ziyu Lin;S. Saleska;B. Nelson;A. Rogers;Jin Wu
中科院分区：
文献类型：
--
作者：
Guangqin Song;Shengbiao Wu;Calvin K. F. Lee;S. Serbin;B. Wolfe;Michael K. Ng;Kim S. Ely;Marc Bogonovich;Jing Wang;Ziyu Lin;S. Saleska;B. Nelson;A. Rogers;Jin Wu
热带叶片物候--尤其是树冠尺度上的变异性--主导着碳通量和水通量的季节性。然而，鉴于物种的巨大多样性，仍然缺乏准确监测热带森林树叶物候的手段。基于塔式红绿蓝(RGB)酚类摄像头的绿色坐标(GCC)度量的时间序列已被广泛用于温带森林的叶片物候监测，但其在热带地区的应用仍存在问题。为了更好地监测热带物候，我们探索了一种深度学习模型(即基于超像素的残差网络50，SP-ResNet50)来自动区分物候图像中的叶和非叶，并得出树冠尺度上的叶比例。为了评估我们的模型，我们使用了巴拿马两个不同森林中六个物候层的一年数据。我们首先建立了一个涵盖不同采集时间、曝光条件和特定物色摄像头的叶子和非叶子像素的综合库。然后，我们将该库分为培训组件和测试组件。我们在三个水平上对该模型进行了评估：1)超像素水平的测试集，2)通过比较模型得到的叶片部分和图像特定监督分类得到的叶片部分的冠层水平，以及3)使用所有的每日图像来暂时地评估模型得到的叶片部分的日稳定性。最后，我们将模型得到的叶组分物候与GCC的叶物候进行了比较。我们的结果表明：1)SP-ResNet50模型准确地区分了叶片和非叶片(总体准确率为93%)，并且在所有三个评估级别上都是稳健的；2)该模型准确地量化了树冠和森林生态系统中的叶片组分物候；3)叶组分和GCC的组合使用有助于推断叶片出现、成熟和衰老的时间，这是模拟热带森林光合作用季节性的关键信息。总体而言，这项研究提供了一种使用酚类摄像头进行热带物候自动监测的改进方法。
Tropical leaf phenology—particularly its variability at the tree-crown scale—dominates the seasonality of carbon and water fluxes. However, given enormous species diversity, accurate means of monitoring leaf phenology in tropical forests is still lacking. Time series of the Green Chromatic Coordinate (GCC) metric derived from tower-based red–greenblue (RGB) phenocams have been widely used to monitor leaf phenology in temperate forests, but its application in the tropics remains problematic. To improve monitoring of tropical phenology, we explored the use of a deep learning model (i.e. superpixel-based Residual Networks 50, SP-ResNet50) to automatically differentiate leaves from non-leaves in phenocam images and to derive leaf fraction at the tree-crown scale. To evaluate our model, we used a year of data from six phenocams in two contrasting forests in Panama. We first built a comprehensive library of leaf and non-leaf pixels across various acquisition times, exposure conditions and specific phenocams. We then divided this library into training and testing components. We evaluated the model at three levels: 1) superpixel level with a testing set, 2) crown level by comparing the model-derived leaf fractions with those derived using image-specific supervised classification, and 3) temporally using all daily images to assess the diurnal stability of the model-derived leaf fraction. Finally, we compared the model-derived leaf fraction phenology with leaf phenology derived from GCC. Our results show that: 1) the SP-ResNet50 model accurately differentiates leaves from non-leaves (overall accuracy of 93%) and is robust across all three levels of evaluations; 2) the model accurately quantifies leaf fraction phenology across tree-crowns and forest ecosystems; and 3) the combined use of leaf fraction and GCC helps infer the timing of leaf emergence, maturation and senescence, critical information for modeling photosynthetic seasonality of tropical forests. Collectively, this study offers an improved means for automated tropical phenology monitoring using phenocams.