Schatz Annakate M, Kramer Andrew M, Drake John M
Odum School of Ecology , University of Georgia , 140 East Green Street, Athens, GA 30602 , USA.
Odum School of Ecology, University of Georgia, 140 East Green Street, Athens, GA 30602, USA; Center for the Ecology of Infectious Diseases, University of Georgia, 140 East Green Street, Athens, GA 30602, USA.
R Soc Open Sci. 2017 Mar 29;4(3):160975. doi: 10.1098/rsos.160975. eCollection 2017 Mar.
Species distribution models (SDMs) are a tool for predicting the eventual geographical range of an emerging pathogen. Most SDMs, however, rely on an assumption of equilibrium with the environment, which an emerging pathogen, by definition, has not reached. To determine if some SDM approaches work better than others for modelling the spread of emerging, non-equilibrium pathogens, we studied time-sensitive predictive performance of SDMs for , a devastating infectious fungus of amphibians, using multiple methods trained on time-incremented subsets of the available data. We split our data into timeline-based training and testing sets, and evaluated models on each set using standard performance criteria, including AUC, kappa, false negative rate and the Boyce index. Of eight models examined, we found that boosted regression trees and random forests performed best, closely followed by MaxEnt. As expected, predictive performance generally improved with the length of time series used for model training. These results provide information on how quickly the potential extent of an emerging disease may be determined, and identify which modelling frameworks are likely to provide useful information during the early phases of pathogen expansion.
物种分布模型（SDMs）是预测新出现病原体最终地理分布范围的一种工具。然而，大多数物种分布模型依赖于与环境平衡的假设，而新出现的病原体，根据定义，尚未达到这种平衡。为了确定某些物种分布模型方法在模拟新出现的、非平衡病原体传播方面是否比其他方法更有效，我们使用在可用数据的时间增量子集上训练的多种方法，研究了物种分布模型对蛙壶菌（一种对两栖动物具有毁灭性的传染性真菌）的时间敏感预测性能。我们将数据分为基于时间线的训练集和测试集，并使用标准性能标准（包括AUC、kappa、假阴性率和博伊斯指数）对每个集合中的模型进行评估。在所研究的八个模型中，我们发现增强回归树和随机森林表现最佳，其次是最大熵模型（MaxEnt）。正如预期的那样，预测性能通常随着用于模型训练的时间序列长度的增加而提高。这些结果提供了关于新出现疾病的潜在范围可以多快确定的信息，并确定了在病原体扩散的早期阶段哪些建模框架可能提供有用信息。
