期刊
ECOLOGICAL INFORMATICS
卷 63, 期 -, 页码 -出版社
ELSEVIER
DOI: 10.1016/j.ecoinf.2021.101302
关键词
Deep learning; Tree species discrimination; Amazon; Very-high-resolution
类别
资金
- Bioverse Tecnologia e Inovacao em Monitoramento Ambiental
- UNICEF Innovation Venture Fund
- Brazilian National Council for Scientific and Technological Development (CNPq) [306345/2020-0]
The study demonstrates the potential of using convolutional neural networks and WorldView-3 satellite images to map individual tree crowns and groves of Bertholletia excelsa in the Brazilian Amazon region. This paves the way for monitoring this important tree species in large tracts of Amazonian forests.
The commercialization of Brazil nuts, seeds of Bertholletia excelsa Bonpl. (Lecythidaceae), represents one of the main income-generation activities for local and indigenous people from the Brazilian Amazon region. Because trees of B. excelsa grow and bear fruit almost exclusively in natural forests, information on their spatial distribution is crucial for nut harvest planning. However, this information is difficult to obtain with traditional approaches such as ground-based surveys. Here, we show the potential of convolutional neural networks (CNNs) and WorldView-3 satellite images (pixel size = 30 cm) to map individual tree crowns (ITCs) and groves of B. excelsa in Amazonian forests. First, we manually outlined B. excelsa ITCs in the WorldView-3 images using field-acquired geolocation information. Then, based on ITC boundaries, we sequentially extracted image patches and selected 80% of them for training and 20% for testing. We trained the DeepLabv3+ architecture with three backbones: ResNet-18, ResNet-50, and MobileNetV2. The average producer's accuracy was 93.87 +/- 0.85%, 93.89 +/- 1.6% and 93.47 +/- 3.6% for ResNet-18, ResNet-50 and MobileNetV2, respectively. We then developed a new random patch extraction training strategy and assessed how a reduction in the percentage of training patches impacted the classification accuracy. To illustrate the robustness of the new training strategy, similar F1scores were achieved whether 80% or 10% of the total number of patches were used to train the CNN model. By analyzing the feature maps derived from ResNet-18, we found that the shadow of emergent B. excelsa trees are important for their discrimination. Geometric distortions in the WorldView-3 images resulting from extreme offnadir viewing angles compromise the presence of shadows, thus potentially hampering B. excelsa detection. Our results show that ITCs and groves of B. excelsa can be mapped by integrating CNNs and very-high-resolution (VHR) satellite images, paving the way for monitoring this important tree species in large tracts of Amazonian forests.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据