Pacific Atoll Vegetation Maps

Vegetation classification maps of 235 Pacific atolls (1,925.6 km2 in total) featuring four land cover classes (broadleaf tree canopy, coconut palm canopy, low vegetation, and non-vegetated surface) at 2 m resolution. Coconut palms are mapped with a balanced accuracy of 85.3%, producer’s accuracy (sensitivity or recall) of 82.5%, user’s accuracy (positive predictive value) of 68.7%, and specificity of 88.1%. Balanced accuracies for broadleaf tree canopy and low vegetation were lower (75.5% and 70.3%, respectively), in part because these classes often appear similar in satellite imagery. Non-vegetated land was classified with a balanced accuracy of 87.7%. The 235 classification maps feature an overall accuracy of 71.1%, significantly higher than the no-information rate of 34.4% (p = 2.2e−16). Across the 235 mapped atolls, 36.6±1.0% of vegetated surfaces featured a coconut palm canopy. By area, 58.3±1.8% of tree canopies (i.e. excluding low-statured vegetation) were coconut palm. A patch classifier identified 310.9 km2 of dense, monodominant coconut stands across the 235 mapped atolls, representing 51.2% of the study-wide coconut area. The classification maps are provided as georeferenced GeoTIFF files as well as PDF files for ease of viewing. Tabular databases including per-atoll and per-islet land cover data are also included, along with geopolitical and historical data about each atoll.

Methods
Maps are based on an interative random forest classification with spectral and textural features extracted from WorldView-2 imagery and trained and validated by human observers using 44,000 training points and nearly 1,969 validation points. See related manuscripts for more methodological informaion:

Burnett, M.W., French, R., Jones, B., Fischer, A., Holland, A., Roybal, I., White, T.D., Steibl, S., Anderegg, L.D.L., Young, H., Holmes, N.D., Wegmann, A., 2024. Satellite imagery reveals widespread coconut plantations on Pacific atolls. Environmental Research Letters 19, 124095. https://doi.org/10.1088/1748-9326/ad8c66

Burnett, M.W., White, T.D., McCauley, D.J., De Leo, G.A., Micheli, F., 2019. Quantifying coconut palm extent on Pacific islands using spectral and textural analysis of very high resolution imagery. International Journal of Remote Sensing 40, 7329–7355. https://doi.org/10.1080/01431161.2019.1594440

本数据集包含235个太平洋环礁的植被分类图（总面积1925.6平方千米），空间分辨率为2米，共涵盖4类土地覆盖类型：阔叶树冠层、椰子树冠层、低矮植被以及无植被地表。
椰子树冠层的分类结果平衡准确率达85.3%，生产者精度（即灵敏度/召回率）为82.5%，用户精度（即阳性预测值）为68.7%，特异度为88.1%。阔叶树冠层与低矮植被的平衡准确率相对较低，分别为75.5%和70.3%，部分原因是这两类地物在卫星影像中光谱特征较为相似。无植被地表的分类平衡准确率为87.7%。
235幅分类图的总体准确率为71.1%，显著高于34.4%的无信息率（p=2.2×10⁻¹⁶）。在全部235个被制图的环礁中，植被地表的36.6%±1.0%为椰子树冠层；按面积统计，乔木冠层（不含低矮植被）中有58.3%±1.8%为椰子树。通过斑块分类器，在235幅制图环礁中共识别出310.9平方千米的密集单优椰子林，占研究区域内椰子林总面积的51.2%。
分类图以地理配准的GeoTIFF（GeoTIFF）文件格式提供，同时提供PDF文件以方便查看；数据集还包含按环礁和小岛划分的土地覆盖数据表格数据库，以及各环礁的地缘政治与历史数据。

研究方法
本分类图基于迭代随机森林分类算法，从WorldView-2（WorldView-2）卫星影像中提取光谱与纹理特征，并由人工观察员利用44000个训练样本点与近1969个验证样本点进行模型训练与验证。详细方法可参阅相关研究论文：
Burnett, M.W., French, R., Jones, B., Fischer, A., Holland, A., Roybal, I., White, T.D., Steibl, S., Anderegg, L.D.L., Young, H., Holmes, N.D., Wegmann, A., 2024. 卫星影像揭示太平洋环礁上广泛分布的椰子种植园. 环境研究通讯(Environmental Research Letters), 19, 124095. https://doi.org/10.1088/1748-9326/ad8c66

Burnett, M.W., White, T.D., McCauley, D.J., De Leo, G.A., Micheli, F., 2019. 利用超高分辨率影像的光谱与纹理分析量化太平洋岛屿上的椰子棕榈覆盖范围. 国际遥感学报(International Journal of Remote Sensing), 40, 7329–7355. https://doi.org/10.1080/01431161.2019.1594440