NEON Tree Crowns Dataset

<strong>Abstract</strong> The NeonTreeCrowns dataset is a set of individual level crown estimates for 100 million trees at 37 geographic sites across the United States surveyed by the National Ecological Observation Network’s Airborne Observation Platform. Each rectangular bounding box crown prediction includes height, crown area, and spatial location. <strong>How can I see the data?</strong> A web server to look through predictions is available through idtrees.org <strong>Dataset Organization</strong> The shapefiles.zip contains 11,000 shapefiles, each corresponding to a 1km^2 RGB tile from NEON (ID: DP3.30010.001). For example "2019_SOAP_4_302000_4100000_image.shp" are the predictions from "2019_SOAP_4_302000_4100000_image.tif" available from the NEON data portal: https://data.neonscience.org/data-products/explore?search=camera. NEON's file convention refers to the year of data collection (2019), the four letter site code (SOAP), the sampling event (4), and the utm coordinate of the top left corner (302000_4100000). For NEON site abbreviations and utm zones see https://www.neonscience.org/field-sites/field-sites-map. The predictions are also available as a single csv for each file. All available tiles for that site and year are combined into one large site. These data are not projected, but contain the utm coordinates for each bounding box (left, bottom, right, top). For both file types the following fields are available: Height: The crown height measured in meters. Crown height is defined as the 99th quartile of all canopy height pixels from a LiDAR height model (ID: DP3.30015.001) Area: The crown area in m² of the rectangular bounding box. Label: All data in this release are "Tree". Score: The confidence score from the DeepForest deep learning algorithm. The score ranges from 0 (low confidence) to 1 (high confidence) <strong>How were predictions made?</strong> The DeepForest algorithm is available as a python package: https://deepforest.readthedocs.io/. Predictions were overlaid on the LiDAR-derived canopy height model. Predictions with heights less than 3m were removed. <strong>How were predictions validated?</strong> Please see Weinstein, B. G., Marconi, S., Bohlman, S. A., Zare, A., &amp; White, E. P. (2020). Cross-site learning in deep learning RGB tree crown detection. <em>Ecological Informatics</em>, <em>56</em>, 101061. Weinstein, B., Marconi, S., Aubry-Kientz, M., Vincent, G., Senyondo, H., &amp; White, E. (2020). DeepForest: A Python package for RGB deep learning tree crown delineation. <em>bioRxiv</em>. Weinstein, Ben G., et al. "Individual tree-crown detection in RGB imagery using semi-supervised deep learning neural networks." <em>Remote Sensing</em> 11.11 (2019): 1309. <strong>Were any sites removed?</strong> Several sites were removed due to poor NEON data quality. GRSM and PUUM both had lower quality RGB data that made them unsuitable for prediction. NEON surveys are updated annually and we expect future flights to correct these errors. We removed the GUIL puerto rico site due to its very steep topography and poor sunangle during data collection. The DeepForest algorithm responded poorly to predicting crowns in intensely shaded areas where there was very little sun penetration. We are happy to make these data are available upon request. # Contact We welcome questions, ideas and general inquiries. The data can be used for many applications and we look forward to hearing from you. Contact [e-mail].摘要：NeonTreeCrowns数据集包含由美国国家生态观测网络（National Ecological Observation Network, NEON）机载观测平台（Airborne Observation Platform）采集的全美37个地理区域内总计1亿棵树木的单木树冠估算数据。每个矩形边界框（bounding box）的树冠预测结果均包含树高、树冠面积与空间位置信息。 如何查看该数据集？可通过idtrees.org访问用于浏览预测结果的Web服务器。 数据集组织形式：shapefiles.zip压缩包内含11000个矢量文件（shapefile），每个文件对应NEON的一块1平方千米的RGB影像瓦片（ID: DP3.30010.001）。例如，`2019_SOAP_4_302000_4100000_image.shp`的预测结果对应可从NEON数据门户获取的`2019_SOAP_4_302000_4100000_image.tif`，访问地址为：https://data.neonscience.org/data-products/explore?search=camera。 NEON的文件命名规则包含：数据采集年份（如2019）、四位字母的站点代码（如SOAP）、采样事件编号（如4）以及影像左上角的UTM坐标（如302000_4100000）。NEON站点缩写与UTM分区信息可参考：https://www.neonscience.org/field-sites/field-sites-map。 每份影像瓦片的预测结果也可单独导出为CSV格式文件；同一站点同一年份的所有影像瓦片预测结果可合并为一个完整的站点级数据集。本数据集未进行投影配准，但包含每个边界框的UTM坐标（左、下、右、上）。 两种文件格式均包含以下字段： - 树高（Height）：以米为单位的树冠高度，其定义为激光雷达（LiDAR）冠层高度模型（ID: DP3.30015.001）中所有冠层高度像素的99分位数； - 树冠面积（Area）：矩形边界框对应的树冠面积，单位为平方米； - 标签（Label）：本批次发布的所有数据均标注为"Tree"； - 置信度得分（Score）：来自DeepForest深度学习算法的置信度得分，取值范围为0（低置信度）至1（高置信度）。 预测方法：DeepForest算法可作为Python包获取，访问地址为：https://deepforest.readthedocs.io/。预测结果叠加在激光雷达衍生的冠层高度模型上，同时筛除了树高低于3米的预测结果。 预测验证方法：请参考以下文献： 1. Weinstein, B. G., Marconi, S., Bohlman, S. A., Zare, A., & White, E. P. (2020). Cross-site learning in deep learning RGB tree crown detection. 《Ecological Informatics》（生态信息学）, 第56卷, 文章编号101061。 2. Weinstein, B., Marconi, S., Aubry-Kientz, M., Vincent, G., Senyondo, H., & White, E. (2020). DeepForest: A Python package for RGB deep learning tree crown delineation. bioRxiv。 3. Weinstein, Ben G., et al. "Individual tree-crown detection in RGB imagery using semi-supervised deep learning neural networks." 《Remote Sensing》（遥感）, 2019年第11卷第11期, 文章编号1309。 是否有站点被移除？部分站点因NEON数据质量不佳被移除：GRSM与PUUM站点的RGB影像质量较差，无法用于冠层预测。NEON的野外调查每年更新，我们预计未来的飞行观测将修正这些问题。此外，我们移除了波多黎各的GUIL站点，因其地形极为陡峭且数据采集时的太阳光照角度不佳，DeepForest算法在光照极少的强阴影区域进行冠层预测时表现较差。我们可应要求提供上述被移除站点的相关数据。 联系方式：我们欢迎任何疑问、创意与一般性咨询。本数据集可应用于诸多场景，期待您的反馈与交流。联系方式：[e-mail]