Marvin N. Wright

TL;DR: Improvements in the relative accuracy considering the amount of variation explained, in comparison to the previous version of SoilGrids at 1 km spatial resolution, range from 60 to 230%.

TL;DR: It is shown that ranger is the fastest and most memory efficient implementation of random forests to analyze data on the scale of a genome-wide association study.

TL;DR: Ranger as mentioned in this paper is a C++ application and R package for high-dimensional data, which is a fast implementation of random forests for high dimensional data and supports ensemble of classification, regression and survival trees.

TL;DR: A literature review on the parameters' influence on the prediction performance and on variable importance measures is provided, and the application of one of the most established tuning strategies, model‐based optimization (MBO), is demonstrated.

TL;DR: A random forest for spatial predictions framework (RFsp) where buffer distances from observation points are used as explanatory variables, thus incorporating geographical proximity effects into the prediction process, and appears to be especially attractive for building multivariate spatial prediction models that can be used as “knowledge engines” in various geoscience fields.