Accurate tree inventories are critical for urban forest management but challenging to obtain, as many urban trees are on private property (backyards, etc.) and are excluded from public inventories. Here, we examined the feasibility of tree species identification in a large heterogenous urban area (>850 km) by using multi-temporal PlanetScope images (3.2 m resolution, multi-spectral) and inventory data from more than 20,000 ground observations within the urban forest of the Greater Chicago area. Our approach achieved an overall classification accuracy of 0.60 and 0.71 for 18 species and ten genera, respectively, but varied from moderate to high for certain species (0.59–0.92) and genera (0.61–0.91). In particular, we identified key host tree species (, , and ) for two damaging invasive insects, emerald ash borer (EAB, ) and Asian longhorn beetle (ALB, ), with over 0.80 accuracies. In addition, we demonstrated that including images from the autumn months (September–November), either for a single-season model or a combined multiple-season model, improved the identification accuracy of temperate deciduous trees. Further, the high classification accuracy of support vector machine (SVM) over random forest (RF) and neural network (NN) approaches suggests that future work might benefit from comparing multiple classification methods to select the approach that maximizes species classification accuracy. Our study demonstrated the potential for applying multi-temporal high-resolution images in urban tree classification, which can be used for urban forest management at a large spatial scale.

中文翻译：

---

多时相卫星影像在城市树种识别中的应用


准确的树木清单对于城市森林管理至关重要，但获取起来却很困难，因为许多城市树木都位于私有财产（后院等）上，并且被排除在公共清单之外。在这里，我们利用多时相 PlanetScope 图像（3.2m 分辨率、多光谱）和来自城市森林内 20,000 多个地面观测的清单数据，研究了在大型异质城市区域（>850km）进行树种识别的可行性属于大芝加哥地区。我们的方法对 18 个物种和 10 个属的总体分类准确度分别为 0.60 和 0.71，但对于某些物种 (0.59–0.92) 和属 (0.61–0.91) 的分类准确度从中等到高。特别是，我们确定了两种破坏性入侵昆虫——白蜡螟 (EAB, ) 和亚洲长角甲虫 (ALB, ) 的关键寄主树种 (、 和 )，准确度超过 0.80。此外，我们证明，包含秋季（9 月至 11 月）的图像，无论是单季节模型还是组合多季节模型，都可以提高温带落叶乔木的识别准确性。此外，支持向量机 (SVM) 相对于随机森林 (RF) 和神经网络 (NN) 方法的高分类精度表明，未来的工作可能会受益于比较多种分类方法以选择最大化物种分类精度的方法。我们的研究证明了在城市树木分类中应用多时相高分辨率图像的潜力，可用于大空间尺度的城市森林管理。