During the last two decades, forest monitoring and inventory systems have moved from field surveys to remote sensing-based methods. These methods tend to focus on economically significant components of forests, thus leaving out many factors vital for forest biodiversity, such as the occurrence of species with low economical but high ecological values. Airborne hyperspectral imagery has shown significant potential for tree species classification, but the most common analysis methods, such as random forest and support vector machines, require manual feature engineering in order to utilize both spatial and spectral features, whereas deep learning methods are able to extract these features from the raw data.

Our research focused on the classification of the major tree species Scots pine, Norway spruce and birch, together with an ecologically valuable keystone species, European aspen, which has a sparse and scattered occurrence in boreal forests. We compared the performance of three-dimensional convolutional neural networks (3D-CNNs) with the support vector machine, random forest, gradient boosting machine and artificial neural network in individual tree species classification from hyperspectral data with high spatial and spectral resolution. We collected hyperspectral and LiDAR data along with extensive ground reference data measurements of tree species from the 83 km² study area located in the southern boreal zone in Finland. A LiDAR-derived canopy height model was used to match ground reference data to aerial imagery. The best performing 3D-CNN, utilizing 4 m image patches, was able to achieve an F1-score of 0.91 for aspen, an overall F1-score of 0.86 and an overall accuracy of 87%, while the lowest performing 3D-CNN utilizing 10 m image patches achieved an F1-score of 0.83 and an accuracy of 85%. In comparison, the support-vector machine achieved an F1-score of 0.82 and an accuracy of 82.4% and the artificial neural network achieved an F1-score of 0.82 and an accuracy of 81.7%. Compared to the reference models, 3D-CNNs were more efficient in distinguishing coniferous species from each other, with a concurrent high accuracy for aspen classification.

Deep neural networks, being black box models, hide the information about how they reach their decision. We used both occlusion and saliency maps to interpret our models. Finally, we used the best performing 3D-CNN to produce a wall-to-wall tree species map for the full study area that can later be used as a reference prediction in, for instance, tree species mapping from multispectral satellite images. The improved tree species classification demonstrated by our study can benefit both sustainable forestry and biodiversity conservation.

在过去的二十年中，森林监测和清单系统已经从实地调查转变为基于遥感的方法。这些方法往往侧重于森林的经济上重要的组成部分，因此遗漏了许多对森林生物多样性至关重要的因素，例如经济价值低但生态价值高的物种的出现。机载高光谱影像显示了树种分类的巨大潜力，但是最常见的分析方法（例如随机森林和支持向量机）需要人工特征工程以利用空间和光谱特征，而深度学习方法能够提取这些功能来自原始数据。

我们的研究集中在主要树种的分类上，包括苏格兰松树，挪威云杉和桦树，以及具有生态价值的重点树种欧洲白杨，该树种在北方森林中稀少且分散。我们将三维卷积神经网络（3D-CNN）与支持向量机，随机森林，梯度提升机和人工神经网络在具有高空间和光谱分辨率的高光谱数据的单个树种分类中的性能进行了比较。我们收集了83 km ²内树种的高光谱和LiDAR数据以及广泛的地面参考数据研究区位于芬兰南部的寒带地区。使用LiDAR得出的树冠高度模型将地面参考数据与航空影像进行匹配。表现最佳的3D-CNN，利用4 m图像斑块，白杨的F1-分数达到0.91，整体F1-分数为0.86，整体精度为87％，而性能最低的3D-CNN使用10 m个图像斑块的F1分数为0.83，准确度为85％。相比之下，支持向量机的F1分数为0.82，准确度为82.4％，而人工神经网络的F1分数为0.82，准确度为81.7％。与参考模型相比，3D-CNN在区分针叶树种方面效率更高，同时具有较高的白杨分类准确度。

作为黑匣子模型的深度神经网络隐藏了有关如何实现决策的信息。我们使用遮挡图和显着图来解释我们的模型。最后，我们使用性能最好的3D-CNN生成了整个研究区域的墙到墙树种地图，以后可以用作参考预测，例如，从多光谱卫星图像进行树种地图绘制。我们的研究表明，改进的树种分类可以有益于可持续林业和生物多样性保护。