mlr3spatiotempcv: Spatiotemporal resampling methods for machine learning in R

TL;DR

The paper introduces the mlr3spatiotempcv R package, which consolidates various spatiotemporal resampling methods into a unified framework within mlr3, facilitating model assessment and selection for spatial and spatiotemporal machine learning.

Contribution

It integrates multiple existing spatiotemporal resampling strategies into the mlr3 framework, providing a consistent interface and simplifying their application in R.

Findings

Provides a unified interface for spatiotemporal resampling methods

Facilitates better model assessment in spatial data analysis

Enhances usability by integrating with mlr3

Abstract

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 reviews the state-of-the-art in spatial and spatiotemporal cross-validation, and introduces 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} machine-learning 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.