Multi-criteria characterization of recent digital soil mapping and modeling approaches

332 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Addressing the issue of digital mapping of soil classes with imbalanced class observations (2019, methodology): “Various modeling techniques such as multinomial logistic regression, random forest, and decision trees models have been applied in predicting and mapping soil classes (Adhikari et al., 2014; Grunwald, 2009).”
Machine learning and soil sciences: a review aided by machine learning tools (2019, result): “Our findings agree with the review by Grunwald (2009), who characterised studies covering the years 2007 and 2008.”
Digital soil mapping: A brief history and some lessons (2016, background): “Grunwald (2009) characterised some recent works on digital soil mapping and modelling, and Grunwald et al.”
Evaluation of modelling approaches for predicting the spatial distribution of soil organic carbon stocks at the national scale (2014, unknown): “Furthermore, as quoted by Minasny et al. (2013) and Grunwald (2009), it is quite common that validation of SOC model predictions is missing entirely from a study.”
Sampling for validation of digital soil maps (2011, background): “Although the educated user knows that digital soil maps, similarly to conventional soil maps, are not perfect and contain errors, they are also frequently not validated (Grunwald, 2009).”