Computational & Data Methods

Bayesian inference is a statistical framework that updates the probability of a hypothesis as new evidence becomes available, using Bayes' theorem to combine prior knowledge with observed data. It provides a principled approach to decision-making under uncertainty, widely used in earthquake engineering, SHM, and model updating.

Computer vision (CV) is a field of artificial intelligence that enables computers to extract, analyze, and understand information from digital images and videos. In earthquake engineering, it is increasingly used for automated crack detection, post-earthquake damage assessment, and structural component recognition.

Deep learning is a subfield of machine learning that uses artificial neural networks with many layers (deep networks) to learn hierarchical representations of data. It has driven breakthroughs in computer vision, natural language processing, and increasingly in earthquake engineering applications such as damage detection and surrogate modeling.

The Finite Element Method (FEM) is a numerical technique for solving partial differential equations by dividing a complex domain into smaller, simpler subdomains called finite elements. It is the dominant computational tool in structural engineering for analyzing stresses, deformations, and dynamic response of structures under arbitrary loading.

Incremental Dynamic Analysis (IDA) is a nonlinear response history analysis method in which a structure is subjected to a suite of ground motions, each scaled to multiple intensity levels, to develop a comprehensive picture of its performance across the full range of seismic demands — from elastic response to collapse.

Machine learning (ML) is a field of artificial intelligence that develops algorithms capable of learning patterns from data and making predictions without being explicitly programmed. In earthquake engineering, it is increasingly used for damage detection, fragility modeling, rapid post-earthquake assessment, and surrogate modeling.

Monte Carlo simulation is a computational method that uses random sampling to estimate the statistical properties of complex systems. In earthquake engineering, it is used to propagate uncertainty through probabilistic seismic hazard and risk analyses, generating distributions of outcomes instead of single deterministic values.

A neural network is a computational model inspired by the structure and function of biological neurons, consisting of interconnected layers of nodes that transform input data into output predictions. It is the foundational architecture of modern machine learning and deep learning.

A surrogate model — also called a metamodel, emulator, or response surface — is a fast approximation of an expensive computational simulation, trained on a limited number of simulation runs. It enables probabilistic analysis, optimization, and real-time decision-making that would be infeasible with the original simulation.

Uncertainty quantification (UQ) is the discipline of characterizing, propagating, and reducing uncertainty in computational models and engineering predictions. It provides a rigorous framework for making decisions under uncertainty, which is fundamental to modern earthquake engineering.