Hybrid Machine Learning Models for Soil Saturated Conductivity Prediction

The hydraulic conductivity of saturated soil is a crucial parameter in the study any engineering problem concerning groundwater. Hydraulic mainly depends on particle size distribution, compaction, and properties that influence aggregation water retention. Generally, finding simple accurate analytical equations between characteristics which it very hard task. Machine learning algorithms can provide excellent tools for tackling highly nonlinear regression problems. Additionally, hybrid models resulting from combination multiple machine further improve accuracy predictions. Five different were built to predict using dataset extracted Soil Water Infiltration Global database. based predictors. Seven variants each model compared, replacing implemented algorithm. Three individual models, while four models. employed Multilayer Perceptron, Random Forest, Support Vector Regression. largest number predictors led most In addition, across all three hybridized Forest Regression proved be (R2 values up 0.829). However, showed tendency overestimate soils where low.