Technology innovation lies at the heart of engineering sustainability, driving the creation of processes, products, and systems that align economic growth and societal benefit with reduced environmental impact. Yet innovation efforts are beset by cross-cutting challenges, such as technical complexity (e.g., proof-of-concept validation, component integration, reliability), constrained budgets and time pressures, scale-up and manufacturability hurdles, regulatory and compliance barriers, and technical and commercial risks. From a sustainability science standpoint, robust, predictive assessment and decision-making frameworks are essential to quantify uncertainties and ensure that innovative technologies deliver genuine sustainability values.
The emergence of Industry 4.0 and beyond positions AI and digital transformation as pivotal enablers of smart and sustainable engineering. In this talk, we will highlight how digital twins, physics-informed neural networks, and domain-specific large language models empower real-time monitoring, sustainability assessment predictive optimization, and intelligent decision making, which can drastically reduce energy consumption, material waste, and manufacturability. Two case studies will illustrate these principles in action: the development of sustainable nanopaint materials and automotive coating manufacturing, and the design and operation of a smart, sustainable electroplating system.
