Making better MAXENT models of species distributions: complexity, overfitting and evaluation
Making better MAXENT models of species distributions: complexity, overfitting and evaluation
复制标题
DOI：
10.1111/jbi.12227
复制
发表时间：
2014-04-01
影响因子：
3.9
通讯作者：
Anderson, Robert P.
中科院分区：
文献类型：
--
作者：
Radosavljevic, Aleksandar;Anderson, Robert P.
在过去的十年里，物种生态位和分布的模型已经成为宝贵的地理学家，但仍然存在一些突出的方法论问题。在这里，我们解决三个关键问题：选择适当的评估数据，检测过拟合，并调整程序设置，以接近最佳模型的复杂性。我们集成解决方案，这些问题的Maxent模型，使用加勒比多刺的口袋老鼠，Heteromys的，作为examination.LocationNorthwestern南美洲。MethodsWe分区数据到校准和评估数据集通过三个变化的k倍交叉验证：随机分区，地理结构和掩蔽的地理结构（限制背景数据对应的校准地点的区域）。然后，我们通过改变控制模型复杂度的正则化水平进行了调优实验。最后，我们衡量性能通过量化的歧视能力和过拟合，以及通过视觉检查的预测在geography.ResultsPerformance之间的数据分区方法和正则化乘数。随机分区的方法夸大了模型性能的估计，地理结构的方法显示出很高的过拟合。相比之下，掩蔽的地理结构的方法允许选择高性能的模型的基础上的所有标准。判别能力在默认正则化乘数附近表现出轻微的峰值。然而，比默认值高两到四倍的正则化水平会产生更低的过拟合。模型预测的地图的视觉检查符合定量evaluations.Main conclusionsSpecies特定的调整模型参数可以提高Maxent模型的性能。此外，模型性能和过拟合的准确估计取决于使用独立的评估数据。这些模型评估策略也可能对其他建模方法有用。
AimModels of species niches and distributions have become invaluable to biogeographers over the past decade, yet several outstanding methodological issues remain. Here we address three critical ones: selecting appropriate evaluation data, detecting overfitting, and tuning program settings to approximate optimal model complexity. We integrate solutions to these issues for Maxent models, using the Caribbean spiny pocket mouse, Heteromys anomalus, as an example.LocationNorth-western South America.MethodsWe partitioned data into calibration and evaluation datasets via three variations of k-fold cross-validation: randomly partitioned, geographically structured and masked geographically structured (which restricts background data to regions corresponding to calibration localities). Then, we carried out tuning experiments by varying the level of regularization, which controls model complexity. Finally, we gauged performance by quantifying discriminatory ability and overfitting, as well as via visual inspections of maps of the predictions in geography.ResultsPerformance varied among data-partitioning approaches and among regularization multipliers. The randomly partitioned approach inflated estimates of model performance and the geographically structured approach showed high overfitting. In contrast, the masked geographically structured approach allowed selection of high-performing models based on all criteria. Discriminatory ability showed a slight peak in performance around the default regularization multiplier. However, regularization levels two to four times higher than the default yielded substantially lower overfitting. Visual inspection of maps of model predictions coincided with the quantitative evaluations.Main conclusionsSpecies-specific tuning of model parameters can improve the performance of Maxent models. Further, accurate estimates of model performance and overfitting depend on using independent evaluation data. These strategies for model evaluation may be useful for other modelling methods as well.