Do consensus models outperform individual models? Transferability evaluations of diverse modeling approaches for an invasive moth
Do consensus models outperform individual models? Transferability evaluations of diverse modeling approaches for an invasive moth
复制标题
共识模型是否优于个体模型？
DOI：
10.1007/s10530-017-1460-y
复制
发表时间：
2017-05
影响因子：
2.9
通讯作者：
Peterson A. Townsend
中科院分区：
文献类型：
--
作者：
Zhu Gengping 朱耿平;Peterson A. Townsend
可转移性是生态位模型许多最新颖和最有趣的应用的关键，因此最大化模型转移的预测能力至关重要。在这里，我们探讨了共识的方法作为一种手段，减少不确定性和提高模型的可移植性，在预测的潜在分布的入侵蛾（美国白蛾）。使用7个建模算法和4个环境数据集，代表不同程度的维度，空间相关性和生态相关性，并显示不同程度的气候生态位扩展的个人本地范围生态位模型进行了校准。四种共识方法被用来结合联合收割机个人的小生境模型，我们评估了共识模型和用于生成它们的个人模型的可转移性。结果表明，理想的标准，环境变量的选择不同的算法，因为不同的算法表现出不同的敏感性，空间维度和相关性。共识模型反映了个体模型的集中趋势，并通过巩固个体模型之间的一致性来降低不确定性，但并没有优于个体模型。插值精度是否以牺牲可转移性为代价的问题表明，在规划处理生态位模型以预测入侵潜力的方法时要谨慎。这些探索概述了减少不确定性和提高生态位模型可移植性的方法，对集合预报具有重要意义。
Transferability is key to many of the most novel and interesting applications of ecological niche models, such that maximizing predictive power of model transfers is crucial. Here, we explored consensus methods as a means of reducing uncertainty and improving model transferability in anticipating the potential distribution of an invasive moth (Hyphantria cunea). Individual native-range niche models were calibrated using seven modelling algorithms and four environmental datasets, representing different degrees of dimensionality, spatial correlation, and ecological relevance, and showing different degrees of climate niche expansion. Four consensus methods were used to combine individual niche models; we assessed transferability of consensus models and the individual models used to generate them. The results suggested that ideal criteria for environmental variable selection vary among algorithms, as different algorithms showed different sensitivities to spatial dimensionality and correlation. Consensus models reflected the central tendency of individual models, and reduced uncertainty by consolidating consistency across individual models, but did not outperform individual models. The question of whether interpolation accuracy comes at the expense of transferability suggests caution in planning methodologies for processing niche models to predict invasive potential. These explorations outline approaches by which to reduce uncertainty and improve niche model transferability with vital implications for ensemble forecasting.
登录
查看更多内容
影响因子：
1.9
作者：
Z. Yang;X. Y. Wang;J. R. Wei;H. Qu;X. Qiao
通讯作者：
Z. Yang;X. Y. Wang;J. R. Wei;H. Qu;X. Qiao
影响因子：
1.3
作者：
Yosiaki Itǒ;I. Hattori
通讯作者：
Yosiaki Itǒ;I. Hattori
影响因子：
5.9
作者：
Qiao, Huijie;Peterson, A. Townsend;Escobar, Luis E.
通讯作者：
Escobar, Luis E.
影响因子：
6.4
作者：
Fitzpatrick, Matthew C.;Weltzin, Jake F.;Dunn, Robert R.
通讯作者：
Dunn, Robert R.
影响因子：
3.3
作者：
Broennimann, Olivier;Guisan, Antoine
通讯作者：
Guisan, Antoine