Prediction of Compaction and Strength Properties of Amended Soil Using Machine Learning

In the current work, a systematic approach is exercised to monitor amended soil reliability for housing development program holistically understand targeted material mixture and building input derived, focusing on three governing parameters: (i) optimum moisture content (OMC), (ii) maximum dry density (MDD), (iii) unconfined compressive strength (UCS). It in essence selection of machine learning algorithms that could optimally show true relation these factors best possible way. Thus, among approaches, optimizable ensemble artificial neural networks were focused on. The data sources those compiled from wide-ranging literature distributed over five continents twelve countries origin. After rigorous manipulation, synthesis, results analyses, it was found selected performed well better approximate OMC UCS, whereas MDD result falls short established threshold set limits referring MSE statistical performance evaluation metrics.