Tensay, Gebremedhin (PhD)Hanna, Yoseph2022-06-282023-11-112022-06-282023-11-112022-05http://etd.aau.edu.et/handle/12345678/32158Shear strength of a soil is perhaps the most important of its engineering properties, as stability analyses in the field of geotechnical engineering are dependent on it. This research work seeks to develop models for predicting the shear strength parameters (cohesion and angle of friction) of soils in Addis Ababa city using artificial neural network modeling technique; with a view to reducing time, effort and cost usually incurred in determining these shear strength parameters in the laboratory for future planning, design and construction projects in the study area. An attempt has been made to develop separate neural network models for c and ϕ from the index properties of soil consisting of Sand % (SP), Fines % (FP), Liquid limit (LL), Plasticity Index (PI), water content (ω), and Bulk density (BD) as input parameters. A multi-layer perceptron network with feed forward back propagation is used to model varying the number of hidden layers. For this purpose, 284 soil test result data was used. The geotechnical soil properties were determined in accordance with ASTM Standards. Direct shear box method was used to determine soil cohesion and soil internal friction angle. The developed models were found to be quite satisfactory in predicting shear strength parameters with correlation coefficients of about 0.98 and 0.92 for cohesion and angle of internal friction, respectively during the testing phase. The models are validated by primary soil test data and compared with some existing correlation methods. The result showed that the artificial neural network method gave better fit and accuracy than the selected empirical formulae in the prediction of shear strength parameters.en-USANNShear StrengthCohesionFriction AnglePredictionIndex PropertyThesis