Interpretable ML Model for Predicting Magnification Factors in Open Ground-Storey Columns to Prevent Soft-Storey Collapse

Open Ground-Storey (OGS) buildings, widely adopted for functional openness, are highly vulnerable to seismic collapse due to stiffness irregularity at the ground storey (GS). The magnification factor (MF), defined as the amplification applied to GS column design forces, acts as a practical strengthening measure to enhance GS stiffness and thereby mitigate the soft storey failure mechanism. While earlier studies recommended fixed MF values, their lack of adaptability often left stiffness deficiencies unresolved. This study develops a rational framework to quantify and predict the required MF for OGS columns, enabling safe yet functionally efficient design. A comprehensive set of three-dimensional reinforced concrete OGS models was analyzed under seismic loads, covering variations in plan geometry, ground-to-upper-storey height ratio (Hr), and GS infill percentage. Iterative stiffness-based evaluations established the MF demand needed to overcome stiffness deficiencies. To streamline prediction, advanced machine learning (ML) models were applied. Among these, black-box models achieved high predictive accuracy, but Symbolic Regression (SR) offered an interpretable closed-form equation that balances accuracy with transparency, making it suitable for design practice. A sensitivity analysis confirmed the Hr as the most influential parameter, with additional contributions from other variables. Validation on additional OGS configurations confirmed the reliability of the SR model, while seismic response comparisons showed that Modified OGS (MOGS) frames with the proposed MF achieved improved stiffness, reduced lateral displacements, uniform drift distribution, and shorter fundamental periods. The study highlights the novelty of integrating interpretable ML into structural design, providing a codifiable and practical tool for resilient OGS construction.