The increasing severity of climate change poses significant challenges to process industries, requiring innovative solutions to enhance sustainability and resilience. Traditional systems often lack the flexibility to adapt to rapidly changing environmental conditions, including fluctuating energy demands, global warmig and related temperature variations, and the growing integration of renewable energy sources. Modular process systems, with their reconfigurable and scalable nature, provide a promising foundation for addressing these challenges. However, fully unlocking their potential necessitates advanced optimization techniques that incorporate dynamic climate considerations. Deep Learning (DL), with its capacity to model complex, nonlinear relationships, offers transformative opportunities for optimizing process systems. By employing DL models, industries can predict system performance under diverse and uncertain environmental conditions, automate design processes, and enable adaptive real-time operational decisions. When integrated with climate projections, DL-based optimization can provide anticipatory adjustments to address long-term climate uncertainties such as extreme weather events, energy demand surges, and shifts in resource availability. This PhD research problem focuses on the use of DL to design and optimize modular water-treatment systems as a simulation case study. By integrating climate data into DL models, the study aims to develop systems that maximize energy efficiency, operational reliability, and resilience to environmental variability. This approach establishes a framework for climate-justified optimization, equipping process industries to meet sustainability goals while adapting to an unpredictable future. Background required: Bachelors or Masters degree in Chemical Engineering, Mechanical Engineering, Energy Engineering, or related areas. A strong interest in mathematical modelling and knowledge of deep learning is desirable.
“Elevating Horizons Through Discovery and Ingenuity”