Application of Artificial Intelligence in Predicting Soil Bearing Capacity in Geotechnical Engineering
Application of Artificial Intelligence in Predicting Soil Bearing Capacity in Geotechnical Engineering
Armin Hatami Rad1 Morteza Pahlevan2
1) .Master’s Student in Civil Engineering, Islamic Azad University, Mashhad Branch, Mashhad, Iran
2) Master’s Student in Civil Engineering, Islamic Azad University, Mashhad Branch, Mashhad, Iran Mortezapahlevan13792000@gmail,com
IOI Code
:
AAHF-ABDBBH
Publication :
National Conference on Architecture and Art Technologies, Smart City, Soft and Creative Industries and Technological Culture(icact.ir)
Abstract :
Soil bearing capacity is one of the most important parameters in geotechnical engineering, as it
directly influences the design and safety of foundations. Traditional methods for estimating soil
bearing capacity are often based on empirical formulas and simplified assumptions, which may not
accurately capture the complex and nonlinear behavior of soil. In recent years, artificial intelligence
(AI) techniques have emerged as powerful tools for improving prediction accuracy in engineering
applications. This study explores the application of artificial intelligence methods in predicting soil
bearing capacity using geotechnical parameters obtained from field and laboratory tests. Machine
learning models, such as artificial neural networks and other data-driven approaches, are capable of
identifying hidden relationships between soil properties and bearing capacity. By analyzing datasets
that include parameters such as soil type, unit weight, cohesion, friction angle, and foundation
dimensions, AI models can provide reliable predictions with reduced computational effort. The results
of previous research indicate that artificial intelligence models often achieve higher accuracy
compared to conventional analytical and empirical methods. In addition, these models can handle
large datasets and complex interactions between variables. Therefore, the integration of artificial
intelligence into geotechnical analysis has significant potential to enhance the reliability and efficiency
of foundation design. This paper highlights the advantages, challenges, and future prospects of using
artificial intelligence for predicting soil bearing capacity in geotechnical engineering.
Keywords : artificial intelligence soil bearing capacity geotechnical engineering machine learning foundation design