A Convolutional Neural Network classifier identifies tree species in mixed-conifer forest from hyperspectral imagery

Published online: https://www.mdpi.com/2072-4292/11/19/2326 DOI: 10.3390/rs11192326 Abstract: In this study, we automate tree species classification and mapping using field-based training data, high spatial resolution airborne hyperspectral imagery, and a convolutional neural network classifier (CNN). We tested our methods by identifying seven dominant trees species as well as dead standing trees in a mixed-conifer forest in the Southern Sierra Nevada Mountains, CA (USA) using training, validation, and testing datasets composed of spatially-explicit transects and plots sampled across a single strip of imaging spectroscopy. We also used a three-band ‘Red-Green-Blue’ pseudo true-color subset of the hyperspectral imagery strip to test the classification accuracy of a CNN model without the additional non-visible spectral data provided in the hyperspectral imagery. Our classifier is pixel-based rather than object based, although we use three-dimensional structural information from airborne Light Detection and Ranging (LiDAR) to identify trees (points > 5 m above the ground) and the classifier was applied to image pixels that were thus identified as tree crowns. By training a CNN classifier using field data and hyperspectral imagery, we were able to accurately identify tree species and predict their distribution, as well as the distribution of tree mortality, across the landscape. Using a window size of 15 pixels and eight hidden convolutional layers, a CNN model classified the correct species of 713 individual trees from hyperspectral imagery with an average F-score of 0.87 and F-scores ranging from 0.67–0.95 depending on species. The CNN classification model performance increased from a combined F-score of 0.64 for the Red-Green-Blue model to a combined F-score of 0.87 for the hyperspectral model. The hyperspectral CNN model captures the species composition changes across ~700 meters (1935 to 2630 m) of elevation from a lower-elevation mixed oak conifer forest to a higher-elevation fir-dominated coniferous forest. High resolution tree species maps can support forest ecosystem monitoring and management, and identifying dead trees aids landscape assessment of forest mortality resulting from drought, insects and pathogens. We publicly provide our code to apply deep learning classifiers to tree species identification from geospatial imagery and field training data Digital Publication of the training data polygons and hyperspectral imagery used in the manuscript "A Convolutional Neural Network classifier identifies tree species in mixed-conifer forest from hyperspectral imagery". Code is available in a Jupyter Notebook and can be found here: https://github.com/jonathanventura/canopy National Ecological Observatory Network. 2018. Provisional data downloaded from http://data.neonscience.org on 22 June 2018. Battelle, Boulder, CO, USA在线发表于：https://www.mdpi.com/2072-4292/11/19/2326，DOI：10.3390/rs11192326。摘要：本研究借助野外实测训练数据、高空间分辨率机载高光谱影像与卷积神经网络分类器（Convolutional Neural Network, CNN），实现树木物种分类与制图的自动化流程。本研究以美国加利福尼亚州内华达山脉南部混合针叶林为研究区，利用由单条成像光谱仪航带采集的空间显式样带与样地数据构建的训练、验证与测试数据集，对7个优势树种及枯立木的识别方法进行了验证。本研究同时选取高光谱影像航带的三波段红绿蓝（Red-Green-Blue, RGB）伪真彩色子集，测试未使用高光谱影像额外非可见光谱数据的CNN模型分类精度。本研究的分类器基于像元而非对象，尽管我们借助机载激光雷达（Light Detection and Ranging, LiDAR）获取的三维结构信息识别地面以上高度大于5米的树木，并将分类器应用于被识别为树冠的影像像元。通过利用野外实测数据与高光谱影像训练CNN分类器，本研究得以在研究区范围内精准识别树木物种、预测其分布格局以及树木死亡率的空间分布。本研究采用15像元窗口与8个隐藏卷积层构建的CNN模型，从高光谱影像中对713棵单株树木的物种进行分类，平均F值为0.87，不同树种的F值介于0.67至0.95之间。CNN分类模型的综合F值从红绿蓝模型的0.64提升至高光谱模型的0.87。高光谱CNN模型能够捕捉海拔约700米（1935米至2630米）范围内的物种组成变化，研究区从低海拔的栎类混交针叶林过渡至高海拔以冷杉为主的针叶林。高分辨率树木物种分布图可为森林生态系统监测与管理提供支撑，而枯立木识别则有助于评估干旱、昆虫及病原菌引发的森林死亡率的景观格局。本研究公开了用于从地理空间影像与野外训练数据中应用深度学习分类器进行树木物种识别的代码。本文献"A Convolutional Neural Network classifier identifies tree species in mixed-conifer forest from hyperspectral imagery"中所使用的训练数据多边形与高光谱影像已进行数字化公开。代码以Jupyter Notebook形式提供，可从以下链接获取：https://github.com/jonathanventura/canopy。数据来源：美国国家生态观测站网络（National Ecological Observatory Network, NEON）2018年发布的临时数据，于2018年6月22日从http://data.neonscience.org下载，由位于美国科罗拉多州博尔德市的Battelle公司提供。