A Digital Twin Approach to Assessing Post-Monsoon Air Quality Impacts of Agricultural Stubble Burning in Delhi

This study presents a comprehensive digital twin framework to quantify, simulate, and mitigate the post-monsoon air quality impacts of agricultural stubble burning in Delhi. Leveraging high-resolution sensor data, and machine learning models, the digital twin reveals the real-time variability of PM2.5 and CO concentrations, characterized by severe daily and hourly spikes that consistently breach health safety thresholds and align with peak residue burning events. Scenario analyses demonstrate that targeted interventions such as advanced crop residue management, traffic regulation, and dynamic public health advisories can substantially reduce pollution exposure and associated hospitalizations. Policy recommendations emphasize inter-state coordination, expanded financial incentives, and the deployment of open-access sensor networks to enable adaptive management. The results underscore the transformative potential of digital twin technology for predicting pollution episodes, guiding intervention strategies, and safeguarding public health. Future research should extend this approach to personal exposure monitoring, integrate additional urban variables, and advance collaborative AI-driven forecasting, creating a robust foundation for sustainable air quality management in India’s most vulnerable urban centers.