Digital Innovation to Accelerate the iMplementation Of Nature-based solutions for Decentralized wastewater treatment

Nature-based solutions (NBS) for wastewater treatment (WWT) are important technologies for climate change mitigation and water reuse practice. While stand-alone numerical models exist for such NBS, none are capable of the integration planning and upscaling in urban water management tools. Therefore, model development and integration need to be addressed by a holistic approach, combining detailed process-based models to provide in-depth understanding, machine-learning approaches based on available data as support, and surrogate models for the final upscaling, planning tools and stakeholder discussions. In this project we will set up a framework in order to UPGRADE (Objective 1) CONNECT (Objective 2) and UPSCALE (Objective 3) the existing non-coherent modelling approaches for NBS in WWT. UPGRADE aims to expand the current process-based model description by incorporating new features: (i) total suspended solid transport and biosolid accumulation, (ii) pathogen transport and removal, and (iii) new soluble pollutants transport and degradation. CONNECT couples the process-based models with a machine-learning model trained with available data from 20 experiments. UPSCALE consists in upscaling the two former modelling approach using surrogate models to enable coupling with urban water management tools, and the development of a stand-alone application for engineering purposes. The resulting framework will support the development and implementation of future models.