期刊
METHODS IN ECOLOGY AND EVOLUTION
卷 10, 期 2, 页码 225-232出版社
WILEY
DOI: 10.1111/2041-210X.13107
关键词
block cross-validation; environmental blocking; model evaluation; spatial autocorrelation; spatial blocking; spatial leave-one-out; species distribution modelling; structured environment
类别
资金
- Australian Government Research Training Program Scholarship
- Rowden White Scholarship
- Australian Research Council (ARC) Discovery Early Career Researcher Award [DE160100904]
- ARC's Centre of Excellence for Environmental Decisions [CE11001000104]
When applied to structured data, conventional random cross-validation techniques can lead to underestimation of prediction error, and may result in inappropriate model selection. We present the r package blockCV, a new toolbox for cross-validation of species distribution modelling. Although it has been developed with species distribution modelling in mind, it can be used for any spatial modelling. The package can generate spatially or environmentally separated folds. It includes tools to measure spatial autocorrelation ranges in candidate covariates, providing the user with insights into the spatial structure in these data. It also offers interactive graphical capabilities for creating spatial blocks and exploring data folds. Package blockCV enables modellers to more easily implement a range of evaluation approaches. It will help the modelling community learn more about the impacts of evaluation approaches on our understanding of predictive performance of species distribution models.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据