Evaluation of the seismic resilience index using machine learning based on loss function: a case study of a hospital in Iran
Year: 2026
Type: article
Abstract: In recent decades, devastating earthquakes of significant magnitude have frequently occurred in Iran, leading to substantial damage to existing infrastructure. These seismic events have resulted in severe economic losses, tragically high human casualties, and profound psychological distress for survivors. Therefore, researchers have focused on the critical importance of assessing the impact of single or multiple seismic events on various types of infrastructure, especially key buildings. Inherently, a seismic event has the potential for widespread damage to infrastructure, particularly to existing buildings, which can subsequently lead to injuries and fatalities. Thus, it is necessary for structural and earthquake engineers to minimize the extent of damage, injuries, and human casualties. Hence, evaluating the seismic resilience of critical structures assumes a pivotal role in comprehensive disaster prevention and mitigation strategies. In this research, four widely used machine learning techniques—Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF)—were applied. The corresponding seismic resilience index for earthquake hazard level II obtained from these models were 0.5022, 0.4806, 0.51864, and 0.5395, respectively. All models were rigorously trained and validated through loss-function optimization to enhance prediction accuracy and reduce modeling errors.
Institution: Iran University of Science and Technology
Language: English
Subfield: Civil and Structural Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $1,590
OpenAlex ID: W7170260120
FWCI:
Cites:
Cited by:
Related to: