Digital Mapping of Soil Classes Using Ensemble of Models in Isfahan Region, Iran

Abstract

Digital soil maps can be used to depict the ability of soil to fulfill certain functions. Digital maps offer reliable information that can be used in spatial planning programs. Several broad types of data mining approaches through Digital Soil Mapping (DSM) have been tested. The usual approach is to select a model that produces the best validation statistics. However, instead of choosing the best model, it is possible to combine all models realizing their strengths and weaknesses. We applied seven different techniques for the prediction of soil classes based on 194 sites located in Isfahan region. The mapping exercise aims to produce a soil class map that can be used for better understanding and management of soil resources. The models used in this study include Multinomial Logistic Regression (MnLR), Artificial Neural Networks (ANN), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Bayesian Networks (BN), and Sparse Multinomial Logistic Regression (SMnLR). Two ensemble models based on majority votes (Ensemble.1) and MnLR (Ensemble.2) were implemented for integrating the optimal aspects of the individual techniques. The overall accuracy (OA), Cohen's kappa coefficient index (κ) and the area under the curve (AUC) were calculated based on 10-fold-cross validation with 100 repeats at four soil taxonomic levels. The Ensemble.2 model was able to achieve larger OA, κ coefficient and AUC compared to the best performing individual model (i.e., RF). Results of the ensemble model showed a decreasing trend in OA from Order (0.90) to Subgroup (0.53). This was also the case for the κ statistic, which was the largest for the Order (0.66) and smallest for the Subgroup (0.43). Same decrease was observed for AUC from Order (0.81) to Subgroup (0.67). The improvement in κ was substantial (43 to 60%) at all soil taxonomic levels, except the Order level. We conclude that the application of the ensemble model using the MnLR was optimal, as it provided a highly accurate prediction for all soil taxonomic levels over and above the individual models. It also used information from all models, and thus this method can be recommended for improved soil class modelling. Soil maps created by this DSM approach showed soils that are prone to degradation and need to be carefully managed and conserved to avoid further land degradation.

The Spatial Prediction of Soil Texture Fractions in Arid Regions of Iran

“…More recently, advanced techniques have been used; including, exponential decay functions [14], polynomials [15], or equal-area splines [16]. One of the most popularly applied are splines which have been used to model continuous changes of soil properties with depth [11,[17][18][19][20][21][22].…”

Salt dome related soil salinity in southern Iran: Prediction and mapping with averaging machine learning models

“…Therefore, an ensemble model is at least as strong as the prediction of any of the primary model. High potential of MA methods in digitally modelling soil texture (Caubet et al, 2019; Román Dobarco et al, 2017), soil taxonomic classes (Taghizadeh‐Mehrjardi et al, 2019), and soil organic carbon (Chen et al, 2020) has also been reported. However, previous studies showed high potential of MA, the best‐performing algorithm may vary between study areas and for different soil properties, and thus optimization of MA methods is case‐specific (Chen et al, 2020).…”

Reducing the Uncertainty of Radiata Pine Site Index Maps Using an Spatial Ensemble of Machine Learning Models

“…A novel ensemble approach was used here to spatially combine predictions from the five most precise prediction models. Although ensemble methods have been widely used in other disciplines [45,47,73,74] this method has not previously been used to predict Site Index. Most ensemble approaches combine predictions from all models across the entire study area using a range of approaches to weight the individual model predictions [73,75].…”

“…As each modelling method has its own limitations and advantages [44] an alternative approach for improving the overall model precision is to combine predictions from each model [45,46]. This method, which is known as Ensemble Modelling, is a well known methodology that can improve prediction through integrating knowledge from many sources [46].…”

“…This method, which is known as Ensemble Modelling, is a well known methodology that can improve prediction through integrating knowledge from many sources [46]. Although this technique has been used for prediction of many soil attributes [46,47] and class prediction studies [45], we are unaware of any studies that use spatial Ensemble Models for the prediction of Site Index. P. radiata is the predominant plantation species within Chile and there is considerable interest within the forest sector in the accurate prediction of Site Index for this species [48].…”