High spatial resolution mapping identifies habitat characteristics of the invasive vine Antigonon leptopus on St. Eustatius (Lesser Antilles)

On the Caribbean island of St. Eustatius, Coralita (Antigonon leptopus) is an aggressive invasive vine posing major biodiversity conservation concerns.  The generation of distribution maps can address these conservation concerns by helping to elucidate the drivers of invasion. We test the use of support vector machines to map the distribution of Coralita on St. Eustatius at high spatial resolution and use this map to identify potential landscape and geomorphological factors associated with Coralita presence. This latter step was performed by comparing the actual distribution of Coralita patches to a random distribution of patches. To train the support vector machine algorithm, we used three vegetation indices and seven texture metrics derived from a 2014 WorldView-2 image. The resulting map shows that Coralita covered 3.18% of the island in 2014, corresponding to an area of 64 ha. The mapped distribution was highly accurate, with 93.2% overall accuracy (Coralita class producer’s accuracy: 76.4%, user’s accuracy: 86.2%). Using this classification map, we found that Coralita is not randomly distributed across the landscape, occurring significantly closer to roads and drainage channels, in areas with higher accumulated moisture, and on flatter slopes. Coralita was found more often than expected in grasslands, disturbed forest and urban areas, but was relatively rare in natural forest. These results highlight the ability of high spatial resolution data from sensors such as WorldView-2 to produce accurate invasive species, providing valuable information for predicting current and future spread risks and for early detection and removal plans.

Methods
A field survey was conducted in July 2015 to collect ground-truthing data to allow for image classification, resulting in a distribution map of the invasive species Antigonon leptopus (referred to as 'Coralita'). On the Caribbean island of St. Eustatius. The resulting distribution of the species on the island comprised 1,852 patches; from each patch, a random location was selected, and additional landscape attributes were calculated for this locations. These characteristics, for all the 1,852 'Coralita' locations, were then compared to characteristics of 1,852 non-Coralita locations, selected randomly on the island of St. Eustatius. The .zip folder contains .txt files containing the land mass and Coralita distribution at 2 m resolution, and the landscape attributes for the 3,704 (i.e. 2*1,852) locations.

在加勒比海圣尤斯特歇斯岛（St. Eustatius）上，珊瑚藤（Coralita，学名*Antigonon leptopus*）是一种极具入侵性的藤本植物，对当地生物多样性保护构成重大威胁。生成入侵物种的分布地图可帮助阐明其入侵驱动因子，从而缓解相关保护压力。本研究采用支持向量机（support vector machines）以高空间分辨率绘制圣尤斯特歇斯岛的珊瑚藤分布，并借此识别与珊瑚藤定植相关的潜在景观与地貌因子。后续分析通过对比珊瑚藤斑块的实际分布与随机斑块分布完成。

为训练支持向量机算法，本研究采用2014年WorldView-2卫星影像提取的3种植被指数与7种纹理特征。最终生成的分布地图显示，2014年珊瑚藤覆盖全岛总面积的3.18%，对应面积达64公顷。该分类地图精度极高，总体分类精度达93.2%（珊瑚藤类别的生产者精度为76.4%，使用者精度为86.2%）。

基于该分类地图，研究发现珊瑚藤并非随机分布于全岛景观中，其显著更趋近于道路与排水沟渠，且多分布于水分累积量更高、坡度更平缓的区域。相较于随机分布，珊瑚藤在草地、受干扰森林与城市区域出现频率更高，但在天然林中相对罕见。本研究结果证明，WorldView-2等高空间分辨率卫星影像可用于精准绘制入侵物种分布，为预测当前及未来的入侵扩散风险、制定早期监测与清除方案提供了宝贵信息。

## 研究方法

本研究于2015年7月开展野外调查以收集地面验证数据，用于影像分类，最终生成入侵物种珊瑚藤（学名*Antigonon leptopus*，俗称Coralita）的分布地图。在加勒比海圣尤斯特歇斯岛上，该物种的分布共包含1852个斑块；从每个斑块中随机选取一个采样点，并计算该点对应的景观属性。随后，将这1852个珊瑚藤采样点的特征与随机选取的1852个非珊瑚藤采样点的特征进行对比。

本数据集的.zip压缩包包含多个.txt文件，分别存储了2米分辨率下的岛屿陆地区域与珊瑚藤分布数据，以及上述3704个（即2×1852）采样点对应的景观属性数据。