Methods to interpolate soil categorical variables from profile observations: Lessons from Iran

By Tomislav Hengl, N. Toomanian, Hannes I. Reuter, M. J. Malakouti. 2007

168 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Environmental Engineering, Management, Monitoring, Policy and Law

View Paper: https://www.semanticscholar.org/paper/fe45b20e51bb3aec46a23232b9f26bbfbf52172f

How researchers see this paper

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

In Artificial Intelligence

1. Alex B. McBratney
2. Budiman Minasny
3. Gerard B. M. Heuvelink
4. Tomislav Hengl
5. THOMAS C. EDWARDS JR.
6. Madlene Nussbaum
7. E. Dietz
8. J. Boettinger

In Environmental Engineering

1. Budiman Minasny
2. Alex B. McBratney
3. Tomislav Hengl
4. Gerard B. M. Heuvelink
5. Marvin N. Wright
6. Madlene Nussbaum
7. Benedikt Gräler
8. C. Brungard

In Management, Monitoring, Policy and Law

1. Tomislav Hengl
2. Alex B. McBratney
3. Budiman Minasny
4. Gerard B. M. Heuvelink
5. Marvin N. Wright
6. Madlene Nussbaum
7. Benedikt Gräler
8. C. Brungard

Citations in the corpus

• Spatial prediction of USDA‐ great soil groups in the arid Zarand region, Iran: comparing logistic regression approaches to predict diagnostic horizons and soil types (2012, background): “Hengl et al. (2007) found that the success of multinomial logistic regression in predicting WRB soil groups depended heavily on the correlation with predictors for all classes.”
• Machine learning for predicting soil classes in three semi-arid landscapes (2015, methodology): “74 Several broad types of machine learning models have been applied for digital soil mapping of 75 soil types, such as logistic regression (Hengl et al., 2007; Jafari et al., 2012; Kempen et al., 2012; 76 Marchetti et al., 2011), classification trees (Bui and Moran, 2003; Kim et al., 2012; Scull et…”
• Spatial disaggregation of complex soil map units: A decision-tree based approach in Bavarian forest soils (2012, background): “Almost all studies in which categorical map units were disaggregated considered a smaller number of classes (i.e. less than 10 classes: Behrens et al., 2010; Brus et al., 2008; Sun et al., 2011; 10 to 20 classes: Debella-Gilo and Etzelmüller, 2009; Hengl et al., 2007; Kempen et al., 2009; Moonjun et”
• Incorporating taxonomic distance into spatial prediction and digital mapping of soil classes (2007, methodology): “Hengl et al. (2007) discussed some methods for spatial interpolation of soil classes.”
• Random forest as a generic framework for predictive modeling of spatial and spatio-temporal variables (2018, methodology): “This boils down to “Regression Kriging” (RK), “Universal Kriging”150 (UK) and/or “Kriging with External Drift” (KED) (Goldberger, 1962; Goovaerts, 1997; Christensen,151 2001; Hengl et al., 2007a).”