Capturing long‐tailed individual tree diversity using an airborne imaging and a multi‐temporal hierarchical model
Capturing long‐tailed individual tree diversity using an airborne imaging and a multi‐temporal hierarchical model
复制标题
DOI：
10.1002/rse2.335
复制
发表时间：
2023-05
影响因子：
5.5
通讯作者：
Ben. G. Weinstein;S. Marconi;Sarah J. Graves;Alina Zare;Aditya Singh;Stephanie A. Bohlman;L. Magee;Daniel J. Johnson;P. Townsend;E. White
中科院分区：
文献类型：
--
作者：
Ben. G. Weinstein;S. Marconi;Sarah J. Graves;Alina Zare;Aditya Singh;Stephanie A. Bohlman;L. Magee;Daniel J. Johnson;P. Townsend;E. White
利用陆地调查测量森林生物多样性是昂贵的，而且只能捕获大型异质景观中常见的物种丰度。相比之下，将航空图像与计算机视觉相结合可以生成数十万棵树的单个树木数据。为了训练计算机视觉模型，地面物种标签与机载反射率数据相结合。由于在大景观中难以发现稀有物种，许多分类模型只包括最丰富的物种，导致在大尺度上的预测有偏差。例如，如果只使用常见物种来训练模型，则假设这些样本在整个景观中具有代表性。将分类模型扩展到包括稀有物种需要有针对性的数据收集和算法改进，以克服优势分类群和稀有分类群之间的大量数据不平衡。我们在美国国家生态观测站网络（NEON）内的Ordway Swisher生物站使用了有针对性的采样工作流程，在那里，传统的森林样地已经确定了六种冠层树种，在现场有超过10个个体。将迭代模型开发与稀有物种采样相结合，将训练数据集扩展到包括14种物种。使用一个多时间层次模型，我们证明了在不损失优势物种性能的情况下，在景观中包括预测频率<1%的物种的能力。最终模型对14种稀有物种的分类准确率超过75%，而基线深度学习模型的准确率为61%。在过滤掉死树后，我们生成了超过67万棵树的单个树冠的景观物种地图。我们在全站点尺度上发现了由稀有物种组成的独特森林斑块，这突出了在训练数据中捕获物种多样性的重要性。我们估计了景观中14种物种的相对丰度，并提供了三种不确定性措施来生成每个物种的数量范围。例如，我们估计优势种palustris占预测茎的28%，模型预测的数量范围在16万到21万之间。这些地图提供了NEON站点内包括稀有物种的冠层树木多样性的初步估计，并提供了使用机载计算机视觉在大范围内捕获树木多样性的蓝图。
Measuring forest biodiversity using terrestrial surveys is expensive and can only capture common species abundance in large heterogeneous landscapes. In contrast, combining airborne imagery with computer vision can generate individual tree data at the scales of hundreds of thousands of trees. To train computer vision models, ground‐based species labels are combined with airborne reflectance data. Due to the difficulty of finding rare species in a large landscape, many classification models only include the most abundant species, leading to biased predictions at broad scales. For example, if only common species are used to train the model, this assumes that these samples are representative across the entire landscape. Extending classification models to include rare species requires targeted data collection and algorithmic improvements to overcome large data imbalances between dominant and rare taxa. We use a targeted sampling workflow to the Ordway Swisher Biological Station within the US National Ecological Observatory Network (NEON), where traditional forestry plots had identified six canopy tree species with more than 10 individuals at the site. Combining iterative model development with rare species sampling, we extend a training dataset to include 14 species. Using a multi‐temporal hierarchical model, we demonstrate the ability to include species predicted at <1% frequency in landscape without losing performance on the dominant species. The final model has over 75% accuracy for 14 species with improved rare species classification compared to 61% accuracy of a baseline deep learning model. After filtering out dead trees, we generate landscape species maps of individual crowns for over 670 000 individual trees. We find distinct patches of forest composed of rarer species at the full‐site scale, highlighting the importance of capturing species diversity in training data. We estimate the relative abundance of 14 species within the landscape and provide three measures of uncertainty to generate a range of counts for each species. For example, we estimate that the dominant species, Pinus palustris accounts for c. 28% of predicted stems, with models predicting a range of counts between 160 000 and 210 000 individuals. These maps provide the first estimates of canopy tree diversity within a NEON site to include rare species and provide a blueprint for capturing tree diversity using airborne computer vision at broad scales.