An Entropy–MARCOS Intelligent Decision Framework for Optimizing Cement-Stabilized Pond Ash in Geotechnical Applications

Abstract

The reuse of industrial by-products in geotechnical engineering requires systematic optimization frameworks that balance multiple performance criteria simultaneously. Traditional mix design approaches for cement-stabilized pond ash rely primarily on heuristic evaluation of individual strength parameters, often neglecting integrated, data-driven decision support. This study proposes an artificial intelligence–assisted multi-criteria decision framework to identify the optimal cement content for pond ash stabilization. Experimental investigations were conducted to evaluate maximum dry density (MDD), optimum moisture content (OMC), and unconfined compressive strength (UCS) at 7, 14, and 28 days for six pond ash–cement mixtures. The resulting dataset was integrated into an objective weighting and ranking architecture that combines the Entropy method for automated weight derivation with the Measurement of Alternatives and Ranking according to COmpromise Solution (MARCOS) method for alternative prioritization. The Entropy algorithm identified early-age UCS as the most influential criterion, reflecting its high discriminative capacity within the dataset. The MARCOS-based ranking revealed that the 85:15 pond ash–cement proportion provides the optimal compromise, achieving balanced early- and long-term strength performance with acceptable compaction behavior. The proposed framework serves as a transparent, reproducible decision-support model for intelligent selection of geomaterials and demonstrates how artificial intelligence–assisted optimization can enhance sustainable geotechnical material design. The methodology is extensible to other industrial-waste stabilization systems, thereby supporting data-driven infrastructure engineering.