Sampling for validation of digital soil maps

By Dick Brus, Bas Kempen, Gerard B. M. Heuvelink. 2011

346 citations recorded by the source corpus.

Subfields: Ecology, Environmental Engineering, Management, Monitoring, Policy and Law

View Paper: https://www.semanticscholar.org/paper/36c278124d9751b5597e7fbb6bdab14358330b12

How researchers see this paper

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

In Ecology

1. Gerard B. M. Heuvelink
2. Tomislav Hengl
3. Bas Kempen
4. El-Sayed Ewis Omran
5. Jin Li
6. Andrew D. Heap
7. Dick Brus

In Environmental Engineering

1. Tomislav Hengl
2. Gerard B. M. Heuvelink
3. Bas Kempen
4. A. Samuel-Rosa
5. Dick Brus
6. Budiman Minasny
7. Alex B. McBratney
8. El-Sayed Ewis Omran

In Management, Monitoring, Policy and Law

1. Gerard B. M. Heuvelink
2. Tomislav Hengl
3. Bas Kempen
4. El-Sayed Ewis Omran
5. Dick Brus

Citations in the corpus

• Mapping Soil Properties of Africa at 250 m Resolution: Random Forests Significantly Improve Current Predictions (2015, result): “We should note here that the results of the cross-validation only give an indication of the true accuracy of the prediction maps because not all sampling locations were collected using probability sampling [52].”
• SoilGrids1km — Global Soil Information Based on Automated Mapping (2014, result): “The results of cross-validation are informative but need to be taken with caution because most of the soil profiles (Figure 2) were not collected using probability sampling, so that the cross-validation results possibly carry the same sampling bias as the original data [61].”