Özgür Yıldız

This study aims to evaluate the effectiveness of sewage sludge ash (SSA) as a sustainable stabilizing agent for low-plasticity clay and to assess the applicability of machine learning techniques for predicting strength parameters. SSA was mixed with CL-type clay at contents of 0%, 5%, 10%, 15%, 20%, and 30% by dry weight. A comprehensive laboratory testing program was conducted, including Atterberg limits, compaction, fall cone, vane shear, and unconfined compressive strength (UCS) tests. The results showed that Atterberg limits increased with increasing SSA contents. As the SSA content increased up to 30%, the maximum dry unit weight decreased by approximately 6%, while the optimum water content increased by about 14%. The addition of SSA significantly enhanced the shear strength, with UCS-derived strength increments ranging from 264 to 771 kPa for 4-day-cured specimens and from 515 to 1351 kPa for 32-day-cured specimens. These findings demonstrate the strong potential of SSA as an alternative and sustainable soil stabilizer. In addition, Self-Organizing Maps (SOMs) were employed to analyze the distribution and relationships of parameters within the experimental dataset, followed by Support Vector Machines (SVMs) for classification and prediction. Using the experimental results, the undrained shear strength parameters obtained from fall cone (s_u-FCT) and laboratory vane shear (s_u-LVT) tests were predicted with accuracies of 83% and 79%, respectively. The novelty of this study lies in the integrated experimental–data-driven framework, in which extensive laboratory testing is combined with machine learning methods to both validate and reliably predict the strength behavior of SSA-stabilized clay.

The 7.7 and 7.6 magnitude Pazarcık and Elbistan earthquakes that struck Kahramanmaraş on 6 February 2023 caused widespread structural damage across many provinces and are considered rare in seismological terms. While many reinforced concrete (RC) buildings designed under current earthquake regulations sustained significant damage, some older RC buildings with outdated designs sustained only moderate damage. This study aims to analyze the seismic performance of such older RC buildings to understand why they did not collapse or suffer severe damage. An 8-story RC building in Adıyaman province, damaged by the earthquake, was considered for analysis. The region’s seismicity and local site conditions were assessed through borehole operations, geotechnical laboratory tests, and seismic field tests. The soil profile was modeled, and one-dimensional seismic site response analyses were performed using records from nearby stations (TK 4615 Pazarcık and TK 4612 Göksun stations) to determine the foundation-level earthquake record. Nonlinear static pushover analysis was carried out via SAP2000 and STA4CAD, utilizing site response analysis and test results taken from the reinforcement and concrete samples of the building. The findings, compared with the observed damage, provide insights into the performance of older RC buildings in this region.

This study presents a comprehensive investigation into the cyclic shear behavior of sand–fly ash mixtures through experimental and data-driven modeling approaches. Cyclic direct shear tests were conducted on mixtures containing fly ash at 0%, 2.5%, 5%, 10%, 15%, and 20% by weight to examine the influence of fly ash content on the shear behavior under cyclic loading conditions. The tests were carried out under a constant stress of 100 kPa to simulate field-relevant stress conditions. Results revealed that the fly ash content initially reduces shear strength at lower additive contents, but shear strength increases and reaches a maximum at 20% fly ash content. The findings highlight the trade-offs in mechanical behavior associated with varying fly ash proportions. To enhance the understanding of cyclic shear behavior, a Nonlinear Autoregressive Model with External Input (NARX) model was employed. Using data from the loading cycles as input, the NARX model was trained to predict the final shear response under cyclic conditions. The model demonstrated exceptional predictive performance, achieving a coefficient of determination (R²) of 0.99, showcasing its robustness in forecasting the cyclic shear performance based on the composition of the mixtures. The insights derived from this research underscore the potential of incorporating fly ash in sand mixtures for soil stabilization in geotechnical engineering. Furthermore, the integration of advanced machine learning techniques such as NARX models offers a powerful tool for predicting the behavior of soil mixtures, facilitating more effective and data-driven decision-making in geotechnical applications. Evidently, this study not only advances the understanding of cyclic shear behavior in fly ash–sand mixtures but also provides a framework for employing data-driven methodologies to address complex geotechnical challenges.