当前位置: X-MOL 学术Methods Ecol. Evol. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
ENMeval 2.0: Redesigned for customizable and reproducible modeling of species’ niches and distributions
Methods in Ecology and Evolution ( IF 6.6 ) Pub Date : 2021-05-13 , DOI: 10.1111/2041-210x.13628
Jamie M. Kass 1, 2, 3 , Robert Muscarella 4 , Peter J. Galante 5 , Corentin L. Bohl 6 , Gonzalo E. Pinilla‐Buitrago 2, 3 , Robert A. Boria 7 , Mariano Soley‐Guardia 8 , Robert P. Anderson 2, 3, 9
Affiliation  

  1. Quantitative evaluations to optimize complexity have become standard for avoiding overfitting of ecological niche models (ENMs) that estimate species’ potential geographic distributions. ENMeval was the first R package to make such evaluations (often termed model tuning) widely accessible for the Maxent algorithm. It also provided multiple methods for partitioning occurrence data and reported various performance metrics.
  2. Requests by users, recent developments in the field, and needs for software compatibility led to a major redesign and expansion. We additionally conducted a literature review to investigate trends in ENMeval use (2015–2019).
  3. ENMeval 2.0 has a new object-oriented structure for adding other algorithms, enables customizing algorithmic settings and performance metrics, generates extensive metadata, implements a null-model approach to quantify significance and effect sizes, and includes features to increase the breadth of analyses and visualizations. In our literature review, we found insufficient reporting of model performance and parameterization, heavy reliance on model selection with AICc and low utilization of spatial cross-validation; we explain how ENMeval 2.0 can help address these issues.
  4. This redesigned and expanded version can promote progress in the field and improve the information available for decision-making.


中文翻译:

ENMeval 2.0:重新设计以可定制和可复制的物种生态位和分布建模

  1. 优化复杂性的定量评估已成为避免过度拟合估计物种潜在地理分布的生态位模型 (ENM) 的标准。ENMeval是第一个使 Maxent 算法可以广泛访问此类评估(通常称为模型调整)的 R 包。它还提供了多种划分发生数据的方法并报告了各种性能指标。
  2. 用户的要求、该领域的最新发展以及对软件兼容性的需求导致了重大的重新设计和扩展。我们还进行了文献综述以调查ENMeval使用趋势(2015-2019)。
  3. ENMeval 2.0 具有用于添加其他算法的新的面向对象结构,支持自定义算法设置和性能指标,生成大量元数据,实施空模型方法来量化重要性和效果大小,并包括增加分析和可视化广度的功能. 在我们的文献综述中,我们发现模型性能和参数化报告不足,严重依赖 AICc 模型选择,空间交叉验证利用率低;我们解释了ENMeval 2.0 如何帮助解决这些问题。
  4. 这个重新设计和扩展的版本可以促进该领域的进展并改进可用于决策的信息。
更新日期:2021-05-13
down
wechat
bug