I am Dr. Shady Adib, an Associate Fellow of the Higher Education Academy (AFHEA) and a civil engineering researcher specialising in Digital Twins, AI-enabled Structural Health Monitoring, and infrastructure intelligence. I completed my PhD in Civil Engineering at Newcastle University, UK, where I developed a Hybrid Digital Twin approach for real-time structural damage identification.
My work connects structural engineering, physics-informed modelling, machine learning, and sensing technologies to support reliable assessment and informed decision-making throughout the infrastructure lifecycle. I am particularly interested in how Digital Twins can evolve with physical assets and remain useful as structural behaviour, monitoring conditions, and operational requirements change.
I serve as an Assistant Professor in Civil Engineering at the University of Hertfordshire, hosted by its Global Academic Foundation (GAF) campus in Egypt. I also hold a Visiting Lecturer appointment at the University of Hertfordshire in Hatfield, UK. My teaching and supervision connect structural engineering principles with digital technologies, sustainability, and practical engineering design.
I am undertaking the I-X Global Early-Career AI Fellowship at Imperial College London as a Visiting Researcher in the Department of Civil and Environmental Engineering, working with Dr. Christian Málaga-Chuquitaype. My fellowship project investigates AI-enabled reconstruction of incomplete structural monitoring data for Self-Generating Digital Twins, aiming to support reliable operation under sensor outages and missing measurements.
My research experience also includes work as a Visiting Researcher at University College London (UCL), UK, on Self-Generating Digital Twins and their applications in infrastructure resilience.
My doctoral research developed a Hybrid Digital Twin that integrates mathematical and data-driven approaches to monitor structural behaviour and identify abnormal changes in real time. The framework combines the Reduced Basis (RB) method with Deep Learning (DL), addresses model uncertainties, and uses Internet of Things (IoT) technologies to synchronise physical measurements with virtual models.
Building on this foundation, my current research explores Self-Generating Digital Twins: systems designed to adapt their models and representations as available data, monitoring configurations, and structural conditions evolve. While hybrid modelling concerns the integration of physics-based and data-driven methods, self-generation concerns how a Digital Twin creates, updates, and adapts its representation. Hybrid methods can therefore form part of a Self-Generating Digital Twin.
My current work focuses on missing-data reconstruction, virtual sensing, and uncertainty-aware structural-state estimation. I investigate how machine-learning methods compare with conventional reconstruction approaches across different patterns of data loss, and how reconstructed measurements affect subsequent Digital Twin predictions. A central research question is whether the surviving sensors retain sufficient information to support reliable inference about structural behaviour.
My longer-term aim is to develop adaptive Digital Twins that support infrastructure maintenance, repair, reuse, and resilience through reliable lifecycle intelligence. This includes understanding when predictions can be relied upon, when uncertainty increases, and when additional measurements or model revisions are required.
I am the Co-Founder & CTO of TWINOVUS, a deep-tech infrastructure intelligence startup developing AI-powered Digital Twin systems for resilient and predictive infrastructure. I lead the technical development of modular lifecycle Digital Twin architectures, bringing together AI, physics-informed machine learning, and connected sensing technologies.
Through TWINOVUS, I aim to translate research into practical engineering tools that help infrastructure owners and operators interpret monitoring data, assess asset condition, and make informed maintenance and operational decisions.
My teaching experience includes computational engineering analysis, structural analysis, digital tools, sustainable engineering, and industry-focused group design projects. I encourage students to connect theoretical understanding with practical implementation and to critically evaluate the capabilities and limitations of digital engineering methods.
I have supervised undergraduate projects on AI-based crack detection, low-cost IoT systems for Structural Health Monitoring, and the integration of Digital Twins with Building Information Modelling (BIM). My approach emphasises problem-solving, clear technical communication, and the responsible application of emerging technologies to engineering challenges.
My wider engagement includes serving as a member and Research Associate at the Africa Center for Digital Transformation (ACDT), contributing to work on adaptive, climate-resilient infrastructure using Digital Twin frameworks. This work explores how generative AI, physics-informed machine learning, and real-time data can support transparent and accountable infrastructure decision-making, including bridge resilience in Nigeria and Ghana.
My policy engagement also includes serving as a session lead for the TechForward Policy Fellowship, guiding discussions on Digital Public Infrastructure and ICT infrastructure in Africa. This brings technical research into dialogue with the institutional and policy considerations that influence infrastructure development.