Optimizing Calcium Leaching from Cement Kiln Dust for Indirect CO2 Mineralization: Experimental Design and Machine Learning Driven Insights

• Hybrid machine learning framework optimizes calcium recovery from cement waste • Decision Tree ML outperforms RSM in predictive accuracy and interpretability • Liquid-to-solid ratio and NH 4 Cl concentration are dominant leaching parameters • Optimal leaching yields 21.4 g L -1 Ca with only 1.9 % ML validation error • SEM-EDS, ICP-OES, XRD and FTIR confirms selective Ca extraction The global cement industry produces a significant amount of CO 2 emissions while simultaneously generating large amounts of cement kiln dust (CKD), a highly alkaline byproduct rich in reactive calcium. CO 2 mineralization, a pathway for permanent sequestration through recovered calcium from CKD, has limited efficiency during leaching, owing to many interacting parameters. Traditional statistical models, such as response surface methodology (RSM), are useful to optimize those parameters but may misrepresent the complex, nonlinear interactions thereby limiting prediction accuracy. In this study, calcium leaching from CKD was investigated using a hybrid RSM-machine learning (ML) framework. Preliminary testing showed that stirring speed had little impact, allowing focus on ammonium chloride (NH 4 Cl) concentration, temperature, leaching time, and liquid-to-solid (LS -1 ) ratio. The RSM model had an adjusted R 2 of 0.84 (predicted R 2 of 0.82) providing optimized conditions of 1.5 M NH 4 Cl, 40 °C, 30 min, and 10 L kg -1 . Decision Tree ML model achieved higher accuracy (training R 2 = 0.94, testing R 2 = 0.87, RMSE = 1.5-2.5), using interpretability tools, identified LS -1 ratio and NH 4 Cl concentration as the most impactful parameters. Experimental validation confirmed the robustness of ML with only 1.9 % deviation compared to the 9.8 % for RSM. Structural and compositional characterization confirmed the selective leaching efficiency of NH 4 Cl. Subsequent carbonation of calcium-rich leachate successfully produced calcium carbonate (CaCO 3 ). Therefore, this integrated RSM-ML framework enhances insights and predictive capability for calcium leaching from CKD, a critical step in indirect CO 2 mineralization.