OUTFIT: Crowdsourced Data Feeding Noise Maps in Digital Twins

In the realm of urban management, Digital Twins (DTs) have recently shown their potential to improve planning and sustainability. The OUTFIT PRIN 2022 project aims to optimize data streams to dynamically render Road Traffic Noise (RTN) in an urban DT model, incorporating both noise levels and citizens' perceptions. In this paper, we introduce OUTFIT and propose the methodology aimed at providing a set of tools to assist policymakers in addressing noise issues and promoting actions for improving the well-being of the citizenship. The project, aligned with Mission 1 of the Italian National Recovery and Resilience Plan (PNRR) and Horizon Europe priorities, focuses on mobility, energy, urban infrastructure, circular economy, and behavioral change. OUTFIT also aims at building a traffic-related database from crowdsourced data for developing a reliable RTN model input to start. This follows an optimization of the data streams for dynamic traffic data processing and 3D noise rendering in order to create a DT model which integrates noise, traffic, and complaints data, with a particular focus on efficient monitoring and orchestration of edge resources. In addition to the definition of a validated method for deriving traffic flows and RTN, a 3D DT with dynamic noise rendering and a set of APIs to enable the interoperability of OUTFIT system's open data will be developed as well.