Koala Habitat Suitability Model for North East NSW

A habitat suitability model at a 250 m resolution for the Koala Phascolarctos cinereus in north-eastern New South Wales using ‘presence only’ records and MaxEnt modelling. Model extent was based on the extent of Crafti vegetation mapping for north east NSW. Substantial spatial clustering of records in coastal urban areas was reduced using a 2 km spatial filter and by modelling separately two sub-regions divided by the 500 m elevation contour. An average of 1086 occurrence records was used to develop models. A bias file was prepared that accounted for variable survey effort, including the concentration of Koala records along sealed and unsealed roads. A reduced set of 14 variables was used in model building. The models were evaluated using a test set of 25 % of the records, with a resulting good fit for each model, as measured by AUC. Frequency of wildfire, Australian Soil Classification, floristic mapping and elevation had the highest relative contribution to the model, whilst a number of other variables made minor contributions. The model was field validated at 65 ground-truth sites.本研究构建了空间分辨率为250米的栖息地适宜性模型，研究对象为新南威尔士州东北部的考拉（Phascolarctos cinereus），建模采用仅存在记录（presence only records）与最大熵（MaxEnt）模型方法。模型研究范围以新南威尔士州东北部Crafti植被制图的覆盖范围为基准。针对沿海城区内记录存在的显著空间聚集问题，本研究通过2千米空间滤波，以及以500米海拔等高线为界划分两个子区域分别建模的方式，对聚集偏差进行了校正。本研究平均使用1086条物种出现记录开展模型构建。同时生成偏差文件以校正调查努力量的差异，其中涵盖了考拉记录沿铺装与非铺装道路聚集的情况。模型构建阶段仅选用了精简后的14个环境变量。研究以25%的记录作为测试集对模型进行评估，经受试者工作特征曲线下面积（AUC）验证，各模型均呈现出良好的拟合效果。野火发生频率、澳大利亚土壤分类（Australian Soil Classification）、植被区系制图与海拔对模型的相对贡献度最高，其余多数变量贡献度较低。该模型于65个实地验证点完成了野外验证。