CAST
Supporting functionality to run 'caret' with spatial or spatial-temporal data. 'caret' is a frequently used package for model training and prediction using machine learning. CAST includes functions to improve spatial or spatial-temporal modelling tasks using 'caret'. It includes the newly suggested 'Nearest neighbor distance matching' cross-validation to estimate the performance of spatial prediction models and allows for spatial variable selection to selects suitable predictor variables in view to their contribution to the spatial model performance. CAST further includes functionality to estimate the (spatial) area of applicability of prediction models. Methods are described in Meyer et al. (2018) <doi:10.1016/j.envsoft.2017.12.001>; Meyer et al. (2019) <doi:10.1016/j.ecolmodel.2019.108815>; Meyer and Pebesma (2021) <doi:10.1111/2041-210X.13650>; Milà et al. (2022) <doi:10.1111/2041-210X.13851>; Meyer and Pebesma (2022) <doi:10.1038/s41467-022-29838-9>; Linnenbrink et al. (2023) <doi:10.5194/egusphere-2023-1308>.
- kNNDM: k-fold Nearest Neighbour Distance Matching Cross-Validation for map accuracy estimation
- Predicting into unknown space? Estimating the area of applicability of spatial prediction models
- Improving performance of spatio-temporal machine learning models using forward feature selection and target-oriented validation
- Importance of spatial predictor variable selection in machine learning applications – Moving from data reproduction to spatial prediction
- Nearest neighbour distance matching Leave‐One‐Out Cross‐Validation for map validation
- Machine learning-based global maps of ecological variables and the challenge of assessing them
This page was built for software: CAST
