Problems and Possible Solutions of Geophysics in Eurocode 8 Based Soil Classification

Tildy, P.; Hermann, L.; Neducza, B.

doi:10.3997/2214-4609.20146619

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, NEHRP Provisions (11), Eurocode-8 (12), Turkey Building Earthquake Code (TBDY-2018) (13) and Rodriguez-Marek et al Soils were classified according to (14). Geophysical Problems and Possible Solutions in Soil Classification Based on Eurocode 8 were discussed (15). Artificial neural networks have previously been used to predict the stability of soil and rock slope (16), to estimate the consolidation coefficient (17), to predict the swelling strength of large soils (18) and to estimate rock tension using deep neural networks (19).…”

Section: Introductionmentioning

confidence: 99%

Site Classification using Feed Forward Backpropagation Artificial Neural Networks

Efeoğlu

2023

IJMSIT

View full text Add to dashboard Cite

Strong rock is less affected by the waves propagating during an earthquake. For this reason, structures on strong rocks are less affected by earthquakes. Identifying strong rocks is important for a safe residential area. There are different earthquake codes declaring the characteristics of strong rocks. In this study, site classification was made according to four different earthquake Provisions Nehrp, TBDY, Rm, E code. Feed Forward Backpropagation Artificial Neural Networks was used for site classification. Shear wave velocity (V30), Ground dominant period (To) and H/V ratio were selected as input parameters to this network. Performance analysis was performed to determine which regulation of the Feed Forward Backpropagation Artificial Neural Networks algorithm made the classification more successful. The cross-validation method was used for the analysis. Accuracy, Precision Recall, Kappa, Area under the ROC Curve (AUC) and Root Mean Squared Error (RMS) error values were calculated. As a result, 98% accuracy value was obtained after cross validation in strong rock detection according to E-Code-8 regulation. According to this regulation, all metric values calculated in strong rock detection are higher than other regulations. In addition, hard rock was detected with the least error rate according to this regulation.

show abstract