Soil Mapping Using GIS, Expert Knowledge, and Fuzzy Logic

By A-Xing Zhu, B. Hudson, James E. Burt, K. Lubich, D. Simonson. 2001

463 citations recorded by the source corpus.

Subfields: Environmental Engineering, Information Systems, Management, Monitoring, Policy and Law

View Paper: https://www.semanticscholar.org/paper/3b5fbff2c20b71e02dd5c6a951db4edfadf29a7d

How researchers see this paper

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

In Environmental Engineering

1. A-Xing Zhu
2. S. Wills
3. Thomas Scholten
4. THOMAS C. EDWARDS JR.
5. Lin F. Yang
6. K. Schmidt
7. C. Qin
8. Feng Qi

In Information Systems

1. A-Xing Zhu
2. THOMAS C. EDWARDS JR.
3. Lin F. Yang
4. S. Wills

In Management, Monitoring, Policy and Law

1. A-Xing Zhu
2. C. Brungard
3. Alex B. McBratney
4. Budiman Minasny

Citations in the corpus

• Prediction of soil properties using fuzzy membership values (2010, methodology): “SoLIM is a predictive approach to soil mapping (Zhu, 1997; Zhu et al., 2001).”
• Construction of membership functions for predictive soil mapping under fuzzy logic (2010, methodology): “Given that the accuracy of most 1:24,000 scale soil maps produced in U.S. is about 60% (Zhu et al., 2001), 76% accuracy is acceptable for an initial soil mapping.”
• Machine learning for predicting soil classes in three semi-arid landscapes (2015, methodology): “Digital soil mapping (DSM) may have 59 advantages over conventional soil mapping approaches as it may better capture observed spatial 60 variability and reduce the need to aggregate soil types based on a set mapping scale (Zhu et al., 2001).”
• Predictive soil mapping with limited sample data (2015, background): “However, one also needs to consider the effectiveness of environmental covariates in indicating the spatial variation of soil, and the availability of data sources for calculation (Zhu et al., 2001).”
• Multi-scale digital terrain analysis and feature selection for digital soil mapping (2010, background): “Yet, both accuracies (training and validation) are within the range of accuracy achieved by similar prediction approaches and better than those based on conventional field soil surveys (Zhu et al., 2001).”
• Disaggregation of component soil series on an Ohio County soil survey map using possibilistic decision trees (2014, background): “Since the influence of soil forming factors or environmental correlates varies by region, there is no definite set of these correlates (Zhu et al., 2001).”
• Quantitative mapping of soil types based on regression kriging of taxonomic distances with landform and land cover attributes (2002, background): “At each site, the soil can be classified in terms of taxonomic distance (Girard and King, 1988) or membership (Burrough, 1989; McBratney and De Gruitjer, 1992; Zhu et al., 2001) to—not one, but with varying degrees—several centroidal soil types simultaneously.”