Integrated GIS-Based Mapping and ANFIS Modelling for Seismic and Geotechnical Characterization of Soil Properties
In this study, geotechnical properties derived through field tests were primarily discussed in GIS-based environments. The distribution of geological formations, seismic and geotechnical soil properties was realized with the maps developed by adopting the Inverse Distance Weight Interpolation (IDWI)...
Gespeichert in:
Veröffentlicht in: | KSCE journal of civil engineering 2024, 28(9), , pp.3708-3721 |
---|---|
1. Verfasser: | |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | In this study, geotechnical properties derived through field tests were primarily discussed in GIS-based environments. The distribution of geological formations, seismic and geotechnical soil properties was realized with the maps developed by adopting the Inverse Distance Weight Interpolation (IDWI) method. Analyzes carried out have revealed that the amplification ratio (the ratio of the horizontal to vertical seismic wave velocity denoted as H/V) of soils reaches 3.3. An Adaptive Neuro-Fuzzy Inference System (ANFIS) model was developed to predict the bearing capacity of soil using data from both field and laboratory experiments. The prediction model created with trapezoidal membership functions was able to predict the bearing capacity of the soils with a very high rate of success with R
2
: 0.91 and MSE: 0.02. The simulations displayed that the maximum bearing capacity of soil is obtained for the soil layer at a depth of 14 m with Poisson’s ratio of 0.1, the dynamic elastic modulus of 7,674 kg/cm
2
, the unit weight of 1.6 g/cm
3
and 477 m/s of shear wave velocity. This study showed that GIS-based mapping processes can be used effectively in the holistic evaluation of a region in terms of seismic and geotechnical characterization. In addition, it has been demonstrated that successful results can be achieved in the characterization and prediction of soil properties with appropriate datasets. |
---|---|
ISSN: | 1226-7988 1976-3808 |
DOI: | 10.1007/s12205-024-2262-2 |