Towards Data-Driven Methods for Decarbonizing Reverse Osmosis Desalination

Desalination, when combined with energy-efficient operations and clean energy, has significant potential to address water security, resilience, and costs. Energy demands of desali-nation must be met, yet current inefficiencies increase costs, and the use of non-renewable sources exacerbates climate change. This research seeks to fill these gaps by advancing integrated water-energy system decarbonization, using data from multiple U.S. desalination plants while defining optimization functions and constraints to reduce energy costs and carbon emissions. A framework is designed for the optimal sizing of grid-connected hybrid renewable energy and storage systems using Artificial Intelligence algorithms to utilize at least 50% renewables.