Artificial neural network models, crucial for accurate predictions, should be meticulously designed for specific problems using deep learning-based algorithms. In this study, we compare four distinct deep learning-based artificial neural network architectures to evaluate their performance in predicting soil consolidation characteristics. The consolidation features of fine-grained soil have a significant impact on the stability of structures, particularly in terms of long-term stability. Precise prediction of soil consolidation under planned structures is vital for effective foundation design. The compression index (C_c) is an important parameter used in predicting consolidation settlement in soils. Therefore, this study examines the use of deep learning techniques, which are types of artificial neural network algorithms with deep layers, in predicting compression index (C_c) in geotechnical engineering. Four neural network models with different architectures and hyperparameters were modeled and evaluated using performance metrics such as mean absolute percentage error (MAPE), mean squared error (MSE), root mean squared error (RMSE), and coefficient of determination (R²). The dataset contains 916 samples with variables such as natural water content (w), liquid limit (LL), plasticity index (PI), and compression index (C_c). This approach allows the results of soil consolidation tests to be seen more quickly at less cost, although predictively. The findings demonstrate that deep learning models are an effective tool in predicting consolidation of fine-grained soil and offering significant opportunities for applications in geotechnical engineering. This study contributes to a more accurate prediction of soil consolidation, which is critical for the long-term stability of structural designs.

In this study, it is aimed to provide significant advantages in terms of time and cost by estimating critical standard compaction parameters such as maximum dry density (MDD) and optimum moisture content (OMC) with machine learning methods instead of traditional laboratory tests. A large dataset including different soil components such as gravel, sand, fine-grained, liquid limit (LL), plastic limit (PL) and plasticity index (PI) was used and algorithms such as decision tree, random forest, gradient boosting and group data processing method (GMDH) were compared. Model performances were evaluated using metrics such as R $$^{2}$$ 2 (coefficient of determination) and RMSE (root mean square error). The results show that the gradient boosting algorithm achieved high accuracy in estimating optimum moisture content (OMC) with a testing R $$^{2}$$ 2 value of 0.91, while the random forest algorithm was the most successful model in estimating maximum dry density (MDD) with a testing R $$^{2}$$ 2 value of 0.92. Machine learning models have been shown to provide faster and lower-cost predictions by reducing the dependency on laboratory tests and offer an effective alternative for soil standard compaction analyses in geotechnical engineering.

This study presents a novel method for predicting the undrained shear strength (c_u) using artificial intelligence technology. The c_u value is critical in geotechnical applications and difficult to directly determine without laboratory tests. The group method of data handling (GMDH)-type neural network (NN) was utilized for the prediction of c_u. The GMDH-type NN models were designed with various combinations of input parameters. In the prediction, the effective stress (σ_v’), standard penetration test result (N_SPT), liquid limit (LL), plastic limit (PL), and plasticity index (PI) were used as input parameters in the design of the prediction models. In addition, the GMDH-type NN models were compared with the most commonly used method (i.e., linear regression) and other regression models such as random forest (RF) and support vector regression (SVR) models as comparative methods. In order to evaluate each model, the correlation coefficient (R²), mean absolute error (MAE), and root mean square error (RMSE) were calculated for different input parameter combinations. The most effective model, the GMDH-type NN with input parameters (e.g., σ_v’, N_SPT, LL, PL, PI), had a higher correlation coefficient (R² = 0.83) and lower error rates (MAE = 14.64 and RMSE = 22.74) than other methods used in the prediction of c_u value. Furthermore, the impact of input variables on the model output was investigated using the SHAP (SHApley Additive ExPlanations) technique based on the extreme gradient boosting (XGBoost) ensemble learning algorithm. The results demonstrated that using the GMDH-type NN is an efficient method in obtaining a new empirical mathematical model to provide a reliable prediction of the undrained shear strength of soils.

The 2023 Kahramanmaraş earthquake sequence, consisting of two major earthquakes ( M _w 7.8 and M _w 7.5) that occurred on the same day in southeastern Türkiye, caused extensive structural damage and severe site‐related impacts across the affected region. This study investigates the post‐earthquake mechanical performance and durability characteristics of concrete and reinforcement samples collected from earthquake‐damaged reinforced concrete (RC) structures in the Antakya and Düziçi regions. Laboratory analyses including capillary water absorption, ultrasonic pulse velocity (UPV), compressive strength, and tensile tests were conducted to evaluate earthquake‐induced material deterioration and residual structural integrity. The results revealed that concretes from Düziçi exhibited higher sorptivity, lower UPV values, and compressive strengths generally below 20 MPa, indicating severe microcracking and increased pore connectivity. In contrast, the Antakya specimens maintained comparatively denser matrices and higher compressive strength values (~25 MPa). The findings demonstrate that intense seismic loading, together with local geological and construction‐related conditions, significantly influenced the deterioration behavior of RC materials. The study highlights the importance of comprehensive post‐earthquake material characterization for reliable damage assessment and for improving future seismic design, rehabilitation, and resilience strategies in earthquake‐prone regions.

The California Bearing Ratio (CBR) is a critical parameter in pavement design and building foundation assessment; however, it requires labor intensive laboratory testing, including a 96 h soaking period. This study evaluated nine machine learning algorithms for predicting CBR from soil index properties: Extra Trees, Support Vector Regression (SVR), Random Forest, Gaussian Process Regression (GPR), CatBoost, LightGBM, XGBoost, Artificial Neural Network (ANN), and ElasticNet. Using 236 soil samples characterized by eight features, we conducted repeated stratified 10-fold cross validation (100 iterations). Extra Trees achieved the highest cross validation R² of 0.789 ± 0.095 (RMSE = 2.064 ± 0.481, MAE = 1.482 ± 0.294), followed by SVR (R² = 0.783 ± 0.102, RMSE = 2.090 ± 0.511, MAE = 1.446 ± 0.300) and Random Forest (R² = 0.777 ± 0.104, RMSE = 2.117 ± 0.460, MAE = 1.518 ± 0.299). The Friedman statistical test confirmed significant performance differences (χ² = 191.97, p < 10⁻³⁷), and Nemenyi post hoc analysis identified Extra Trees, SVR, Random Forest, and GPR as statistically equivalent superior groups. SHAP analysis highlighted gravel content (29.0%), maximum dry density (23.8%), and fines content (14.8%), which is consistent with geotechnical principles. Systematic noise injection (20% perturbation) demonstrated model stability, with less than 7% performance degradation at 15% noise. On this heterogeneous compiled dataset, which extends beyond the calibration domain of the empirical equations, all six empirical methods yielded negative R² (range: −0.803 to −22.639), while all ML models achieved positive R² (≥0.655 to 0.789). Extra Trees achieved a 3.1× lower RMSE than the best empirical equation, confirming substantially better predictive performance in this out-of-calibration setting. The framework provides a practical five step implementation workflow that may reduce the need for preliminary CBR tests under project specific accuracy thresholds.

It is very important to analyze the polluted water that streams transfer around them by diffusion. Dirty water leaking from streams like this causes soil and water pollution. The protection of surface and underground water resources is very important given the decreasing water resources. How deep a pollutant has infiltrated can be found by solving the diffusion equation. In this study, the concentration amount of the pollutant passing from a long-polluted stream to the soil was investigated by the finite difference method. Instead of using expensive packet programs, a widespread program Matlab used by engineers and scientists to analyze data, develop algorithms, solve problems analytically and numerically, and create models is preferred in this study. The cross-section of the stream is rectangular and its length is considered to be quite long. Therefore, the problem has been examined in two dimensions. First, the necessary finite difference equations are derived and this problem is analyzed using appropriate boundary conditions. A numerical solution has been obtained for two cases in which the bottom of the stream is permeable and it is not. The mass flow rate of both of the cases was calculated and it is found that the mass flow rate in the first case in which the bottom of the stream is permeable is almost double of the second case. The flow velocities on the boundaries have been found to be less in the case in which the bottom of the stream is impermeable.