Digital soil mapping using artificial neural networks

In the context of a growing demand of high-resolution spatial soil information for environmental planning and modeling, fast and accurate prediction methods are needed to provide high-quality digital soil maps. Thus, this study focuses on the development of a methodology based on artificial neural networks (ANN) that is able to spatially predict soil units. Within a test area in Rhineland-Palatinate (Germany), covering an area of about 600 km 2 , a digital soil map was predicted. Based on feed-forward ANN with the resilient backpropagation learning algorithm, the optimal network topology was determined with one hidden layer and 15 to 30 cells depending on the soil unit to be predicted. To describe the occurrence of a soil unit and to train the ANN, 69 different terrain attributes, 53 geologic-petrographic units, and 3 types of land use were extracted from existing maps and databases. 80% of the predicted soil units (n = 33) showed training errors (mean square error) of the ANN below 0.1, 43% were even below 0.05. Validation returned a mean accuracy of over 92% for the trained network outputs. Altogether, the presented methodology based on ANN and an extended digital terrain-analysis approach is time-saving and cost effective and provides remarkable results.

[1]  Peter Scull,et al.  Predictive soil mapping: a review , 2003 .

[2]  K. Beven,et al.  A physically based, variable contributing area model of basin hydrology , 1979 .

[3]  M. Schaap,et al.  Using neural networks to predict soil water retention and soil hydraulic conductivity , 1998 .

[4]  Berthold K. P. Horn,et al.  Hill shading and the reflectance map , 1981, Proceedings of the IEEE.

[5]  D. Tarboton.  A new method for the determination of flow directions and upslope areas in grid digital elevation models , 1997 .

[6]  P. A. Shary,et al.  Fundamental quantitative methods of land surface analysis , 2002 .

[7]  Shiv O. Prasher,et al.  SOIL SALINITY PREDICTION USING ARTIFICIAL NEURAL NETWORKS 1 , 2002 .

[8]  C. Thorne,et al.  Quantitative analysis of land surface topography , 1987 .

[9]  Walter J. Rawls,et al.  Accuracy and reliability of pedotransfer functions as affected by grouping soils , 1999 .

[10]  S. Tamari,et al.  Application of artificial neural networks for developing pedotransfer functions of soil hydraulic parameters , 1996 .

[11]  Budiman Minasny,et al.  On digital soil mapping , 2003 .

[12]  W. Henry McNab,et al.  Terrain Shape Index : Quantifying EjSCect of Minor Landforms on Tree Height , 2006 .

[13]  Benjamin W. Wah,et al.  Automated learning for reducing the configuration of a feedforward neural network , 1996, IEEE Trans. Neural Networks.

[14]  Mark A. Nearing,et al.  Artificial neural networks of soil erosion and runoff prediction at the plot scale , 2003 .

[15]  A. Zhu.  Mapping soil landscape as spatial continua: The Neural Network Approach , 2000 .

[16]  Paul V. Bolstad,et al.  Predicting Southern Appalachian overstory vegetation with digital terrain data , 2004, Landscape Ecology.

[17]  Gary A. Peterson,et al.  Soil Attribute Prediction Using Terrain Analysis , 1993 .

[18]  Alex J. Cannon,et al.  MODELING TRANSIENT pH DEPRESSIONS IN COASTAL STREAMS OF BRITISH COLUMBIA USING NEURAL NETWORKS 1 , 2001 .

[19]  H.W.G. Booltink,et al.  Neural network models to predict soil water retention , 1999 .

[20]  Chandra A. Madramootoo,et al.  Modeling nitrate leaching using neural networks , 1998 .