A Comparison of Model Averaging Techniques to Predict the Spatial Distribution of Soil Properties

• Published in: Remote sensing (Basel, Switzerland) Vol. 14; no. 3; p. 472
• Main Authors: Taghizadeh-Mehrjardi, Ruhollah, Khademi, Hossein, Khayamim, Fatemeh, Zeraatpisheh, Mojtaba, Heung, Brandon, Scholten, Thomas
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.02.2022
• Subjects: Accuracy; Artificial neural networks; Bayesian analysis; Bayesian theory; Electrical conductivity; Electrical resistivity; Environmental management; Genetic algorithms; Information management; Iran; machine learning; model averaging; Neural networks; Organic matter; Particle size; prediction; Remote sensing; sand fraction; Soil organic matter; Soil properties; Soils; Spatial discrimination; Spatial distribution; spatial modeling; Spatial resolution; Topography; Variables; Iran
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs14030472

This study tested and evaluated a suite of nine individual base learners and seven model averaging techniques for predicting the spatial distribution of soil properties in central Iran. Based on the nested-cross validation approach, the results showed that the artificial neural network and Random Forest base learners were the most effective in predicting soil organic matter and electrical conductivity, respectively. However, all seven model averaging techniques performed better than the base learners. For example, the Granger–Ramanathan averaging approach resulted in the highest prediction accuracy for soil organic matter, while the Bayesian model averaging approach was most effective in predicting sand content. These results indicate that the model averaging approaches could improve the predictive accuracy for soil properties. The resulting maps, produced at a 30 m spatial resolution, can be used as valuable baseline information for managing environmental resources more effectively.