mlr3spatiotempcv: Spatiotemporal Resampling Methods for Machine Learning in R

mlr3spatiotempcv: Spatiotemporal Resampling Methods for Machine Learning in R

cross-validation, predictive performance, machine learning, autocorrelation, spatial, temporal, R.

Spatial and spatiotemporal machine-learning models require a suitable framework for
their model assessment, model selection, and hyperparameter tuning, in order to avoid
error estimation bias and over-fitting. This contribution provides an overview of the
state-of-the-art in spatial and spatiotemporal cross-validation techniques and their implementations in R while introducing the R package mlr3spatiotempcv as an extension
package of the machine-learning framework mlr3. Currently various R packages implementing different spatiotemporal partitioning strategies exist: blockCV, CAST, skmeans
and sperrorest. The goal of mlr3spatiotempcv is to gather the available spatiotemporal
resampling methods in R and make them available to users through a simple and common
interface. This is made possible by integrating the package directly into the mlr3 machinelearning framework, which already has support for generic non-spatiotemporal resampling
methods such as random partitioning. One advantage is the use of a consistent nomenclature in an overarching machine-learning toolkit instead of a varying package-specific
syntax, making it easier for users to choose from a variety of spatiotemporal resampling
methods. This package avoids giving recommendations which method to use in practice
as this decision depends on the predictive task at hand, the autocorrelation within the
data, and the spatial structure of the sampling design or geographic objects being studied.

Patrick Schratz

https://www.jstatsoft.org/article/view/v111i07

Friedrich Schiller University Jena

November 2024

Fajar bagus W

PDF

English

Text