Two successive earthquakes with moment magnitudes of M_w = 7.7 (focal depth = 8.6 km) and M_w = 7.6 (focal depth = 7 km) occurred approximately within 9 h on February 6, 2023, in Türkiye, respectively. The epicenters were the Pazarcık and Elbistan districts of Kahramanmaraş. Both earthquakes occurred in the East Anatolian Fault Zone, one of Türkiye’s two major active fault systems. Between these two severe earthquakes, there was one more big aftershock with a moment magnitude of 6.6, the epicenter of which was in the Nurdağı District of Gaziantep. Then, on February 20, 2023, another aftershock earthquake with a magnitude of M_w = 6.4 occurred in Yayladağı district of Hatay. As a result of the earthquakes, severe damage occurred in several provinces and districts with a population of around 15 million, and more than 50,000 people have lost their lives. This study presents on-site geotechnical and structural investigations by a team of researchers after the Kahramanmaraş earthquakes. It summarizes the performance of the building environments as a result of on-site assessments, taking into account observed structural damage, local site conditions, and strong ground motion data. The possible causes of the observed damage are addressed in detail. These earthquakes once again revealed the common deficiencies of existing reinforced concrete structures in Türkiye, such as poor material quality, poor workmanship, unsuitability of reinforcement detailing, and inadequate earthquake-resistant construction techniques. Precast concrete and masonry structures in the region were also severely damaged during the earthquakes due to insufficient engineering service, poor materials, deficiencies during construction, etc.

The compressive strength (Fc) of cement mortar (CM) is a key parameter in ensuring the mechanical reliability and durability of cement-based materials. Traditional testing methods are labor-intensive, time-consuming, and often lack predictive flexibility. With the increasing adoption of machine learning (ML) in civil engineering, data-driven approaches offer a rapid, cost-effective alternative for forecasting material properties. This study investigates a wide range of supervised linear and nonlinear ML regression models to predict the Fc of CM. The evaluated models include linear regression, ridge regression, lasso regression, decision trees, random forests, gradient boosting, k-nearest neighbors (KNN), and twelve neural network (NN) architectures, developed by combining different optimizers (L-BFGS, Adam, and SGD) with activation functions (tanh, relu, logistic, and identity). Model performance was assessed using the root mean squared error (RMSE), coefficient of determination (R²), and mean absolute error (MAE). Among all models, NN_tanh_lbfgs achieved the best results, with an almost perfect fit in training (R² = 0.9999, RMSE = 0.0083, MAE = 0.0063) and excellent generalization in testing (R² = 0.9946, RMSE = 1.5032, MAE = 1.2545). NN_logistic_lbfgs, gradient boosting, and NN_relu_lbfgs also exhibited high predictive accuracy and robustness. The SHAP analysis revealed that curing age and nano silica/cement ratio (NS/C) positively influence Fc, while porosity has the strongest negative impact. The main novelty of this study lies in the systematic tuning of neural networks via distinct optimizer–activation combinations, and the integration of SHAP for interpretability—bridging the gap between predictive performance and explainability in cementitious materials research. These results confirm the NN_tanh_lbfgs as a highly reliable model for estimating Fc in CM, offering a robust, interpretable, and scalable solution for data-driven strength prediction.