blockCV: an R package for generating spatially or environmentally separated folds for k-fold cross-validation of species distribution models
By Roozbeh Valavi, Jane Elith, J. Lahoz‐Monfort, G. Guillera‐Arroita. bioRxiv, 2018
669 citations recorded by the source corpus.
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. 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.
Subfields: Ecological Modeling, Ecology, Nature and Landscape Conservation
View Paper: https://www.semanticscholar.org/paper/a2d00d30abade9e8ec4a77beef11e537469422b1
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Ecological Modeling
In Ecology
In Nature and Landscape Conservation
Citations in the corpus
- Importance of spatial predictor variable selection in machine learning applications - Moving from data reproduction to spatial prediction (2019, methodology): “Several methods for spatial cross-validation have been proposed to account for spatial dependencies in the data (Bren-ning, 2005; Le Rest et al., 2014; Pohjankukka et al., 2017; Roberts et al., 2017; Meyer et al., 2018; Valavi et al., 2018).”
- Predicting into unknown space? Estimating the area of applicability of spatial prediction models (2020, methodology): “…variability in the training data rather than the ability to make predictions beyond the data used for model training, leading to overly optimistic performance estimates (e.g. Meyer et al., 2019, 2018; Roberts et al., 2017; Valavi et al., 2018; Pohjankukka et al., 2017; Schratz et al., 2019).”
- Mixture-of-Experts in Remote Sensing: A Survey (2026, unknown): “For operational RS systems, routing diagnostics are also more actionable when combined with calibrated uncertainty estimates and structured failure auditing [39, 112].”