Institute of Geography and Geoecology, Karlsruhe Institute of Technology, Reinhard-Baumeister-Platz 1, 76131, Karlsruhe, Germany.
Centre for Ecological Genomics & Wildlife Conservation, Department of Zoology, University of Johannesburg, Auckland Park, Johannesburg, South Africa.
Sci Rep. 2023 Aug 24;13(1):13892. doi: 10.1038/s41598-023-40989-7.
Conventional forest inventories are labour-intensive. This limits the spatial extent and temporal frequency at which woody vegetation is usually monitored. Remote sensing provides cost-effective solutions that enable extensive spatial coverage and high sampling frequency. Recent studies indicate that convolutional neural networks (CNNs) can classify woody forests, plantations, and urban vegetation at the species level using consumer-grade unmanned aerial vehicle (UAV) imagery. However, whether such an approach is feasible in species-rich savanna ecosystems remains unclear. Here, we tested whether small data sets of high-resolution RGB orthomosaics suffice to train U-Net, FC-DenseNet, and DeepLabv3 + in semantic segmentation of savanna tree species. We trained these models on an 18-ha training area and explored whether models could be transferred across space and time. These models could recognise trees in adjacent (mean F1-Score = 0.68) and distant areas (mean F1-Score = 0.61) alike. Over time, a change in plant morphology resulted in a decrease of model accuracy. Our results show that CNN-based tree mapping using consumer-grade UAV imagery is possible in savanna ecosystems. Still, larger and more heterogeneous data sets can further improve model robustness to capture variation in plant morphology across time and space.
传统的森林清查需要大量人力。这限制了木质植被通常被监测的空间范围和时间频率。遥感提供了具有成本效益的解决方案，可以实现广泛的空间覆盖和高采样频率。最近的研究表明，卷积神经网络（CNN）可以使用消费级无人机（UAV）图像对木本森林、人工林和城市植被进行物种级分类。然而，这种方法在物种丰富的热带稀树草原生态系统中是否可行尚不清楚。在这里，我们测试了高分辨率 RGB 正射影像的小数据集是否足以训练 U-Net、FC-DenseNet 和 DeepLabv3+进行热带稀树草原树种的语义分割。我们在 18 公顷的训练区训练这些模型，并探索了模型是否可以跨空间和时间转移。这些模型可以识别相邻（平均 F1 得分=0.68）和遥远地区（平均 F1 得分=0.61）的树木。随着时间的推移，植物形态的变化导致模型精度下降。我们的结果表明，使用消费级 UAV 图像进行基于 CNN 的树木制图在热带稀树草原生态系统中是可行的。尽管如此，更大和更异构的数据集可以进一步提高模型的稳健性，以捕捉植物形态在时间和空间上的变化。
