Welcome

Welcome to Dr. Simwanda's AI for Risk, Reliability & Resilience Laboratory- AI4R³ Lab.

The AI4R³ Lab advances the safety, reliability, sustainability and resilience of civil and structural infrastructure through the integration of artificial intelligence, probabilistic modelling, reliability analysis and data-driven engineering design.

The lab focuses on developing intelligent tools and models for infrastructure and material systems, including ultra-high-performance concrete, cold-formed steel, hybrid structural systems, bridges, cooling towers and complex industrial structures.

Our Mission

Our mission is to quantify risk, enhance structural reliability and strengthen resilience in the next generation of infrastructure and materials.

We aim to support engineers, researchers and decision-makers in designing safer, more sustainable and adaptive infrastructure systems under uncertain and changing conditions.

Our Research Vision

Modern infrastructure is exposed to increasingly complex demands, including climate variability, ageing structures, multi-hazard loading, material innovation and sustainability targets.

These challenges create important research needs, such as:

• uncertainty in materials, loads, degradation and structural performance;

• high-dimensional data and complex input–output relationships;

• limited experimental data for emerging materials and systems;

• interaction of hazards and potential cascading failures;

• need for interpretable AI in safety-critical engineering applications;

• trade-offs between safety, cost, durability and carbon footprint;

• real-time updating of structural models using monitoring data.

The AI4R³ Lab addresses these challenges by developing robust, scalable and interpretable AI-driven methods for risk-informed infrastructure design, assessment and management.

Research Areas

• Advanced Uncertainty Quantification

  We develop and apply probabilistic methods, Bayesian updating, reliability analysis and uncertainty propagation techniques to support safer engineering decisions under uncertain conditions.

• Generative and Explainable AI

  We use generative modelling, data augmentation, optimization and explainable machine learning to improve prediction accuracy, transparency and trust in engineering applications.

• Structural and Material Reliability

  We investigate the reliability and safety of advanced structural and material systems, including UHPC, cold-formed steel, hybrid systems and innovative structural components.

• Resilient Infrastructure

  We assess infrastructure performance under ageing, deterioration, climate effects and extreme events to support resilient design and adaptation strategies.

• Sustainability and Net-Zero Design

  We integrate lifecycle performance, carbon minimization and sustainable material design to support low-carbon and high-performance infrastructure systems.

• Intelligent Simulation and Surrogate Modelling

  We develop efficient AI-based surrogate models as alternatives to expensive finite element, experimental and multi-physics simulations.

See our Research page for more.