ANN‐based pedotransfer and soil spatial prediction functions for predicting Atterberg consistency limits and indices from easily available properties at the watershed scale in western Iran

Abstract

Atterberg consistency limits (liquid limit, LL; plastic limit, PL; shrinkage limit, SL) and indices (plasticity index, PI; friability index, FI) are useful indicators of soil mechanical behaviour. This study was conducted to evaluate the use of soil and environmental data for predicting Atterberg limits or indices using artificial neural network (ANN) models at the watershed scale in western Iran. The LL, PL, SL, PI, FI, particle size distribution, organic matter (OM) and calcium carbonate equivalent (CCE) were measured in soil samples collected from 113 locations. Three sets of readily available properties were employed as inputs. The first of these data sets or models consisted of soil properties. The second included topographic attributes and normalized difference vegetation index (NDVI), and the third was a combination of soil, topographic attributes and NDVI. Developed ANN models could explain a majority of the variability (62–94%) in Atterberg limits and indices. Greatest and poorest performances were attributed to the third and first models, respectively. No significant efficacy difference was observed between the second and third models. Therefore, the second data set with its readily available environmental variables is suggested for use in predicting Atterberg limits and indices at the regional scale. Sensitivity analysis showed that NDVI, OM, clay content, CCE and topographic attributes (wetness index, elevation, plan curvature and slope) could explain much of the variance associated with Atterberg limits and indices at the watershed scale in western Iran.

Wheat yield prediction using machine learning and advanced sensing techniques

“…Ayoubi and Sahrawat (2011) and Norouzi et al (2010) used ANN to predict grain yield as a function of soil properties which were collected/analyzed with traditional lab methods. Zolfaghari et al (2015) developed ANN models that could explain a majority of the variability (62-94%) in Atterberg limits and indices. Shearer et al (1999) investigated a vast number of variables such as soil and crop parameters based on satellite imagery for a few observations during the year from one site.…”

Pedotransfer functions to predict Atterberg limits for South African soils using measured and morphological properties

“…Zolfaghari et al . () also reported no significant correlations between LL and PI and OC, but Seybold et al . () considered OC an important predictor of PI.…”

“…This is in agreement with the results of Zolfaghari et al . () who recorded greater plasticity at deeper positions in the profile. A positive correlation between swelling properties and structure, specifically coarse angular blocky and prismatic, and slickensides confirms tacit knowledge in every soil surveyor working with a variety of swelling soils (Table ).…”

“…The lack of impact by OC on the indicators of PI may be due to a contribution to CEC of the soil imitating higher physical activity but is actually physically stabilizing the soil. Zolfaghari et al (2015) also reported no significant correlations between LL and PI and OC, but Seybold et al (2008) considered OC an important predictor of PI. The PTFs developed (Tables 2 and 3) have low predictive value when compared to other studies with smaller data sets and localized studies.…”

Spatial variability of some soil shrinkage indices in hilly calcareous region of western Iran

“…and Bromus sp, dryland farming and irrigated farming mainly cultivated by winter wheat (Triticum aestivum) and alfalfa (Medicago sativa), respectively (Kelishadi et al, 2014). Studied soils have a variety of clay minerals including montmorillonite, chlorite, illite, and a few kaolinite (Zolfaghari et al, 2015).…”