TY - JOUR ID - 20423 TI - The use of neural networks for predicting the factor of safety of soil against liquefaction JO - Scientia Iranica JA - SCI LA - en SN - 1026-3098 AU - Erzin, Y. AU - Tuskan, Y. AD - Department of Civil Engineering, Faculty of Engineering, Manisa Celal Bayar University, 45140 Manisa, Turkey Y1 - 2019 PY - 2019 VL - 26 IS - 5 SP - 2615 EP - 2623 KW - Artificial Neural Networks KW - factor of safety KW - liquefaction potential KW - multiple regression KW - Simplified method DO - 10.24200/sci.2018.4455.0 N2 - In this study, the performance of the artificial neural network (ANN) and multiple regression (MR) models to predict the factor of safety, Fs, values of soil against liquefaction was investigated and compared. To achieve this, two earthquake parameters, namely, earthquake magnitude (Mw) and horizontal peak ground acceleration (amax ), and  six soil properties, namely, standard penetration test number (SPT-N), saturated unit weight (γsat), natural unit weight (γn),  fines content (FC), the depth of ground water level from the ground surface (GWL), and the depth of the soil from ground surface (d) varied in the liquefaction analysis and then the Fs value  was calculated for each case by using the Excell program developed and used in the development of the ANN and MR models. The results obtained from the simplified method were compared with those obtained from both the ANN and MR models.It was found that the predicted values from the ANN model matched the calculated values much better than those obtained from the MR model. Moreover, the performance indices such asthedetermination coefficient, variance account for, mean absolute error, root mean square error, and the scaled percent error were computed to evaluate the prediction capacity of the models developed. The study demonstrates that the ANN model is able to predict the Fs value of the soil against liquefaction, quite efficiently, and is superior to the MR model. UR - https://scientiairanica.sharif.edu/article_20423.html L1 - https://scientiairanica.sharif.edu/article_20423_a665104367fad5afbec731e6c42b18b0.pdf ER -