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

Abstract

To predict the soil texture fractions, 115 profiles were identified based on the Latin hypercube sampling technique, the horizons were sampled, and the clay, sand, and silt contents (in percentages) of soil samples were measured. Then equal-area quadratic spline depth functions were used to derive clay, sand, and silt contents at five standard soil depths (0–5, 5–15, 15–30, 30–60, and 60–100 cm). Auxiliary variables used in this study include the terrain attributes (derived from a digital elevation model), Landsat 8 image data (acquired in 2015), geomorphological map, and spectrometric data (laboratory data). Artificial neural network (ANN), regression tree (RT), and neuro-fuzzy (ANFIS) models were used to make a correlation between soil data (clay, sand, and silt) and auxiliary variables. The results of this study showed that the ANFIS model was more accurate in the prediction of the three parameters of clay, silt, and sand than ANN and RT. Moreover, the ability of ANFIS model to estimate the soil texture fractions in the surface layers was higher than the lower layers. The mean coefficient of determination (R2) values calculated by 10-fold cross validation suggested the higher prediction performance in the upper depth intervals and higher prediction error in the lower depth intervals (e.g., R2 = 0.91, concordance correlation coefficient (CCC) = 0.90, RMSE = 4.00 g kg−1 for sand of 0–5 cm depth, and R2 = 0.68, CCC = 0.60, RMSE = 8.03 g kg−1 for 60–100 cm depth). The results also showed that the most important auxiliary variables are spectrometric data, multi-resolution, valley-bottom flatness index and wetness index. Overall, it is recommended to use ANFIS models for the digital mapping of soil texture fractions in other arid regions of Iran.

Digital mapping of soil texture classes using Random Forest classification algorithm

“…MrVBF was an effective index in the flat areas, especially for identifying flat valley bottoms which can be used effectively for the prediction of soil texture classes (Taghizadeh-Mehrjardi et al, 2014). MrVBF was identified as the most important variable along with spectrometric data for the prediction of soil texture fraction in the arid region of Iran (Mehrabi-Gohari et al, 2019). Similarly, Jafari et al (2014) predicted soil texture classes using boosted RT in an arid region and found MrVBF and moisture indices are important auxiliary variables for their model.…”

“…Though several studies exist for mapping of soil particle size for different depth intervals using regression algorithms (Akpa et al, 2014;Hengl et al, 2017;Mehrabi-Gohari et al, 2019;Pahlavan-Rad & Akbarimoghaddam, 2018;Poggio & Gimona., 2017;Taghizadeh-Mehrjardi et al, 2020;Taghizadeh-Mehrjardi et al, 2016), mapping of categorical variables such as soil texture classes at different depth intervals is not well documented. In this context, the present study is aimed to apply equal-area quadratic spline function over average sand, silt and clay content of different texture classes for deriving texture classes for six standard depth intervals.…”

Bio-Inspired Hybridization of Artificial Neural Networks: An Application for Mapping the Spatial Distribution of Soil Texture Fractions

“…The use of ML models has become increasingly prevalent for predicting the spatial distribution of soil properties. When predicting soil PSFs, various ML-based DSM studies have included the use of artificial neural networks (ANNs) [17][18][19][20][21], boosted regression tree (BRT) [19,22,23], Random Forest (RF) [18,24], and artificial neuro-fuzzy inference system (ANFIS) [16,25]. Despite the variety of ML models that a DSM practitioner may apply, existing literature does not seem to suggest that one model is universally better than others; furthermore, model comparison studies have shown that different models have the potential to generate drastically different outputs when given the same input data [26].…”

Digital mapping of soil texture classes for efficient land management in the Piedmont plain of Iran

“…Again, in the random forest modelling process of the silt fraction, the most important variable at the IncNodePurity significance level, which represents the reduction of node impurity in the formation of trees, was the F I G U R E 6 Importance in levels of the environmental variables used to predict the content of soil texture fractions using the random forest algorithms, (a, d) clay, (b, e) sand, and (c, f) silt topographic wetness but with a higher difference from GNDVI (Figure 6). The topographic wetness index, which is an important topography variable that affects the amount of moisture accumulation in the soil (Mehrabi-Gohari et al, 2019), can be considered as an important variable in modelling the silt fraction. In terms of showing areas with high moisture accumulation potential, its effect on the estimation of silt content has been reported in other studies (Moore et al, 1993;Nabiollahi et al, 2014;Pinheiro et al, 2018).…”