The Sacramento-San Joaquin Delta genus and community level classification maps derived from airborne spectroscopy data

Since 2004, airborne hyperspectral imagery has been acquired over the Sacramento - San Joaquin Delta in northern California to map submerged and floating invasive species and study how they affect the Delta ecosystem. Acquiring imagery over 2220 square kilometers of the Delta typically required 60-70 flightlines each year, which were then further processed to surface reflectance, georegistered, and prepared for analysis. Further, each flightline was processed using multiple spectral mapping methods such as spectral angle mapper, spectral mixture analysis, spectral indexes, and continuum removal over water and cellulose absorption bands. The outputs of these transformations were used as inputs to a Random Forests classifier. Concurrent with image acquisition, field data (800-2000 points) were collected across the Delta for training and validation of the classification products. The field data were divided into test and training polygons. These polygons were overlaid on the transformed files and pixel data were extracted corresponding to the polygons. The training data were used to train the Random Forests classifier to identify 10 classes (water, submerged aquatic vegetation, emergent marsh, soil, non-photosynthetic vegetation, water hyacinth, water primrose, pennywort, shadow, riparian vegetation). The classifier was validated quantitatively using the test data at both pixel and polygon level using overall accuracy and kappa metrics. The classifier was then applied to all flightlines and class maps were produced. Mosaics of these class maps are published in this dataset.自2004年起，研究团队于美国加利福尼亚州北部的萨克拉门托-圣华金三角洲（Sacramento-San Joaquin Delta）启动机载高光谱影像（airborne hyperspectral imagery）采集工作，旨在绘制水下与漂浮入侵物种的分布图谱，并探究其对该三角洲生态系统的影响。 针对该2220平方千米的三角洲区域，每年通常需执行60至70条飞行航线以完成影像采集；后续需将采集得到的影像进一步处理为地表反射率数据、完成地理配准（georegistration），并开展分析前的预处理工作。 此外，每条飞行航线的影像均采用多种光谱制图方法处理，包括光谱角填图（spectral angle mapper）、光谱混合分析（spectral mixture analysis）、光谱指数（spectral indexes）以及针对水体与纤维素吸收波段的连续统去除（continuum removal）操作。 上述变换得到的输出结果被用作随机森林（Random Forests）分类器的输入数据。 在影像采集的同期，研究团队于三角洲全域采集了800至2000个野外采样点数据，用于分类产品的训练与验证。野外采样数据被划分为测试多边形与训练多边形，将这些多边形叠加至变换后的影像文件中，并提取与多边形区域对应的像素级数据。 利用训练数据对随机森林分类器进行训练，使其可识别10个类别：水体（water）、沉水水生植被（submerged aquatic vegetation）、挺水沼泽植被（emergent marsh）、土壤（soil）、非光合植被（non-photosynthetic vegetation）、凤眼蓝（水葫芦，water hyacinth）、水丁香（water primrose）、铜钱草（pennywort）、阴影（shadow）以及河岸植被（riparian vegetation）。 研究团队利用测试数据从像素级与多边形级两个维度对分类器进行定量验证，验证指标包括总体精度（overall accuracy）与Kappa系数（kappa metrics）。 随后将训练完成的分类器应用于所有飞行航线的影像，生成各类别的分布制图；本数据集已发布这些类别分布图的拼接产物。