Prediction of resilient modulus with pre-post experimental data of undisturbed subgrade soils using machine learning algorithms M. Irsad Ozkaynak, Yuksel Yilmaz Transportation Geotechnics, 2024 The resilient modulus (M R ) of subgrade, which shows relationship between stress and unit deformation of a pavement systems under traffic loads, is a design parameter of the pavement structure. Although a cyclic triaxial test apparatus can be used to directly determine the M R of the subgrade in the laboratory, utilizing prediction models based on easily obtainable soil parameters, is a more efficient method when taking time and cost considerations into account. A comprehensive laboratory testing program is designed to create M R prediction models using machine learning (ML) algorithms. 70 undisturbed soil samples are subjected to M R tests, as well as physical and engineering soil properties tests (water content, field density, specific gravity, gradation, consistency limits, unconfined compressive strength, swell pressure, swell percentage). Soil samples are drilled from a highway that has been in operation for over five years. First, a linear model like MLR is used in the study. Next, nonlinear regression models like RF, GBM, LightGBM, CatBoost, and XGBoost algorithms are used. Research findings showed that nonlinear regression models outperformed linear regression models in predicting the M R (R 2 > 0.85), with the XGBoost algorithm yielding the best accuracy (R 2 = 0.90). Apart from the primary effects such as confining pressure (σ 3 ) and deviatoric stress (σ d ), it was found that unconfined compressive strength (q u ), natural water content (w n ), and swelling percentage (SR) are significant parameters in the prediction of M R among all parameters.
Hydro–Mechanical Behaviour of a Rainfall-Induced Landslide by Instrumental Monitoring: Landslide–Rainfall Threshold of the Western Black Sea Bartin Region of Türkiye Taha Taskiran, Serdar Alli, Yuksel Yilmaz Applied Sciences Switzerland, 2023 Bartin City is located in the Western Black Sea Region of Türkiye, where rainfall-induced landslides are more frequently observed. Although it is known that many landslides are induced by rainfall, there is limited knowledge regarding how rainfall triggers these landslides in the city. To clarify the triggering mechanisms of rainfall-induced landslides, a detailed field monitoring program was performed on a chosen area to represent landslides in Bartin. The instrumentation included the measurements of site suction, volumetric water content, groundwater level, and rainfall amount over a period of two years. Various stability analyses were performed regarding pore pressures after both transient flow infiltration analysis and site-measured suction values. The rainfall intensity–duration thresholds were obtained for both dry and wet periods as a result of the numerical analyses performed by means of parameters obtained from field monitoring. The results show that the wet period conditions create more critical conditions before failure compared to the dry period conditions, so landslides occur more easily in wet periods. According to the landslide–rainfall threshold relations, landslide-risk limits are reached if the rainfall intensity is over 10 mm/h for the dry periods and lasts between 0.85 h and 17 h depending on the saturated hydraulic conductivity of the soil. When the rainfall intensities are less than 10 mm/h, longer rainfall durations are needed for a landslide to occur. For the wet periods, landslide-risk situations are encountered if the rainfall intensity over 1 mm/h continues for 0.36 h–3.67 h, depending on the saturated hydraulic conductivities.
Mechanical behaviour of atrazine-contaminated clay Mahdi Keramatikerman, Amin Chegenizadeh, Hamid Nikraz, Yuksel Yilmaz Applied Sciences Switzerland, 2020 Atrazine (ATZ) is one of the most heavily used types of herbicide that is currently applied in the agricultural industry all around the world, especially Australia and the United States. This study investigates the effect of atrazine contamination on the mechanical characteristics of two Western Australian natural clays and one commercial type of clay. A series of the Atterberg limit, compaction, and torsional ring shear tests were performed on the clays contaminated with 2, 4, and 6% atrazine content. The results showed that increasing the atrazine content led to a reduction in both liquid limit (LL) and plastic (PL) of the tested soils. Similarly, the optimum moisture content (OMC) and maximum dry density (MDD) decreased by increasing the atrazine in all tested clays. The ring shear results showed that the peak shear strength and residual stress ratio of the clays decreased by increasing the contamination. Also, the results showed that atrazine contamination caused an increase in cohesion and a decrease in the friction angle of the tested soils. Also, longer periods of contamination caused a reduction in strength characteristics of the tested soils.
Use of standard and off-spec fly ashes for soil stabilization Yuksel Yilmaz, Haluk Sinan Coban, Bora Cetin, Tuncer B. Edil Journal of Materials in Civil Engineering, 2019 There has been significant utilization of standard fly ashes, Class C and Class F fly ashes, in the cement industry and in soil stabilization applications. However, the majority of the fly ...
Individual and combined effect of portland cement and chemical agents on unconfined compressive strength for high plasticity clayey soils Yüksel Yılmaz, Jongwan Eun, A. Yağmur Gören Geomechanics and Engineering, 2018 Unconfined compressive strength (UCS) of high plasticity clayey soil mixed with 5 and 10 % of Portland cement and four chemical agents such as sodium hexametaphosphate, aluminum sulfate, sodium carbonate, and sodium silicate with 0, 5, 10, and 20% concentrations was comparatively evaluated. The individual and combined effects of the cement and chemical agents on the UCS of the soil mixture were investigated. The strength of the soil-cement mixture generally increases with increasing the cement content. However, if the chemical agent is added to the mixture, the strength of the cement-chemical agent-soil mixture tends to vary depending on the type and the amount of the chemical agent. At low concentrations of 5% of aluminum sulfate and 5% and 10% of sodium carbonate, the average UCS of the cement-chemical agent-soil mixture slightly increased compared to pure clay due to increasing the flocculation of the clay in the mixture. However, at high concentrations (20%) of all chemical agents, the UCS significantly decreased compared to the pure clay and clay-cement mixtures. In the case of high cement content, the rate of UCS reduction is the highest among all cement-chemical agent-soil mixtures, which is more than three times higher in comparison to the soil-chemical agent mixtures without cement. Therefore, in the mixture with high cement (> 10%), the reduction of the USC is very sensitive when the chemical agent is added.
Effect of lime treatment on static liquefaction behavior of sand-bentonite mixtures Mahdi Keramatikerman, Amin Chegenizadeh, Yuksel Yilmaz, Hamid Nikraz Journal of Materials in Civil Engineering, 2018 This research investigated the effect of lime treatment on the static liquefaction behavior of sand–bentonite (SB) mixture by conducting a series of undrained monotonic triaxial compression...
Investigation of the effect of a polypropylene fiber material on the shear strength and CBR characteristics of high plasticity Ankara clay Bearing Capacity of Roads Railways and Airfields Proceedings of the 8th International Conference on the Bearing Capacity of Roads Railways and Airfields, 2009
Stabilization of clays using liquid enzymes Bearing Capacity of Roads Railways and Airfields Proceedings of the 8th International Conference on the Bearing Capacity of Roads Railways and Airfields, 2009
