Feature Selection Using Parallel Genetic Algorithm for the Prediction of Geometric Mean Diameter of Soil Aggregates by Machine Learning Methods

Abstract

Aggregate stability is a useful soil physical dynamic index of soil resistivity to surface wind and water erosion in all ecosystems, especially, in arid and semi-arid regions. Two machine learning techniques including support vector machines (SVMs) and artificial neural networks (ANNs) were used to develop predictive models for the estimation of geometric mean diameter (GMD) of soil aggregates. An empirical multiple linear regression (MLR) model was also constructed as the benchmark to compare their performances. Furthermore, the influence of feature space dimension reduction using parallel genetic algorithm (PGA) on the prediction accuracy of all investigated techniques was evaluated. The ANN model achieved greater accuracy in GMD prediction as compared to the MLR and SVM models. The obtained ERROR% value in GMD prediction using the ANN model was 6.9%, while it was 15.7 and 10.6% for the MLR and SVM models, respectively. Feature selection using PGA improved the prediction accuracy of all investigated techniques. The coefficient of determination (R 2 ) values between the measured and the predicted GMD values using PGA-based MLR, SVM, and ANN models increased by 20.0, 12.2, and 8.8% in comparison with the proposed MLR, SVM, and ANN models. In conclusion, it appears that the PGA-based ANN model could be considered as an alternative to conventional regression models for the GMD prediction.

Predicting and Mapping of Soil Organic Carbon Using Machine Learning Algorithms in Northern Iran

“…To eliminate the multicollinearity of variables and exclude unimportant and redundant auxiliary variables, numerous feature selection techniques have been developed for DSM including. Particle swarm optimization [45], the genetic algorithm (GA) [25,32,46], hybrid GA-artificial neural network [47], parallel GA [48], and the artificial bee colony algorithm [36] are among the notable feature selection techniques. Such variable selection techniques can simplify modeling by lowering the number of input variables and potentially improving the accuracy of soil predictions.…”

Soil Particulate Organic Matter (POM) Prediction in a Mountainous Watershed using Artificial Neural Networks

“…For neural network analysis, the MLP with back-propagation (BP) learning rule was used, which is the most commonly used neural network structure in ecological modeling and soil science (Tracey, Zhu, and Crooks 2011;Besalatpour et al 2012Besalatpour et al , 2014. The numbers of neurons and epoch were determined by trial and error.…”

“…In contrast to widespread applications of regression models to predict POM indirectly from other data, artificial intelligence systems such as artificial neural networks (ANNs) have not been exploited for this purpose, although they have shown much potential in similar applications (Uno et al 2005;Kisi et al 2009;Azamathulla et al 2009;Diaconu et al 2010;Besalatpour et al 2012Besalatpour et al , 2014.…”

A Structurally Simplified Hybrid Model of Genetic Algorithm and Support Vector Machine for Prediction of Chlorophyll a in Reservoirs

“…Although the GA used in the prediction model effectively avoided falling into a local optimal solution and producing a low convergence speed, the initial values of the GA's parameters were determined through the trial method in this study. Recent research mainly used two advanced approaches to optimize the initial settings for the GA's parameters: one approach was to optimize the initial population's characteristics and quantity by combining other approaches, such as the heuristic algorithm [31]; another approach was to improve the crossover and mutation rates with adaptive GA [32], such as clustering-based adaptive GA [33]. In future research, the determination of reasonable initial values of the GA's parameters would combine with these approaches.…”