Estimation of Cation Exchange Capacity of Fine Grained Soil using AI Techniques

Clay soils play a pivotal role in geotechnical and environmental contexts due to their unique mineral and chemical properties.The main characteristic property of these clay soils is cation exchange capacity (CEC) which is a crucial parameter influencing various soil processes, including nutrient accessibility, soil fertility, and geotechnical characteristics.Traditional laboratory methods for CEC determination are time-consuming and expensive.Recent advancements in artificial intelligence (AI) offer a promising alternative to streamline and enhance the accuracy of CEC predictions.This study explores the feasibility of estimating cation exchange capacity in clay soils by leveraging linear regression model and a comprehensive range of soil parameters, including Liquid Limit (LL), Plastic Limit (PL), Shrinkage Limit (SL) and Plasticity Index (PI).A dataset comprising about 200 data points from various research papers was compiled, and Linear regression model was trained using the dataset through orange data mining software to evaluate the correlation between cation exchange capacity and the Liquid Limit, Plastic Limit, Shrinkage Limit and Plasticity Index.