Soil Water Retention Characteristics of Black Soils of India and Pedotransfer Functions Using Different Approaches

Developing Pseudo Continuous Pedotransfer Functions for International Soils Measured with the Evaporation Method and the HYPROP System: I. The Soil Water Retention Curve

“…However, Model 3 also resulted in a comparable performance when using SSC and BD as inputs. Moreover, Model 3 was the best performing with RMSE of 0.043 cm 3 cm −3 when the Turkish data set was incorporated in the training set, which agrees with the results reported by Patil et al [44]. Minasny and McBratney [17] also found that adding BD improved the performance of the neuro-m model compared to using just the textural constituents.…”

Impact of regression methods on improved effects of soil structure on soil water retention estimates

“…Nowadays, many attempts have been devoted to study soil-water relationships of tropical soils through developing SWRC-PTFs. These PTFs have been derived using rather limited data which represented specific soils in tropical regions; for instance, highly weathered soils on stable landforms (Botula, 2013), recently developed alluvial soils in a dynamic river basin (Nguyen et al, 2014), and black clayey soils with strong shrinking and swelling characteristics (Patil et al, 2013).…”

Introducing a Kriging-based Gaussian Process approach in pedotransfer functions: Evaluation for the prediction of soil water retention with temperate and tropical datasets

“…Nemes et al (2006) and Botula et al (2013). In comparison to other methods, such as SVM, ANN, Linear Regression, it is amongst the best-performing and most flexible PTF algorithms (Nemes et al, 2006;Lakzian et al, 2010;Patil et al, 2012;Nguyen et al, 2017). Similar to Kriging, the prediction is a weighted sum of samples in the training dataset, but the selection of neighbours and attribution of weights solely depends on the Euclidean distance in the predictor space ‖x * − x i ‖ and a power parameter p (Eq.…”