ID: 2093
Presenting Author: David Carruthers
Session: 541 - EsIA and Permitting Improvements for Efficiency and Effectiveness: Lessons Learned
Status: pending
AI-based permitting in Lombardy, Umbria, and Puglia integrates ADMS and machine learning for predictive monitoring, aligned with DNSH and ESRS, paving the way for a national permitting platf
This presentation illustrates how Artificial Intelligence and machine learning are transforming environmental assessment and permitting processes toward a new paradigm of Permitting 5.0, based on transparency, predictive capability, and data-driven decision making.
The initiative draws on the regional experiences of Lombardy, Umbria, and Puglia, which have developed interoperable permitting systems integrating environmental, technical, and regulatory data to improve the efficiency and accountability of Environmental Impact Assessment (EIA), Strategic Environmental Assessment (SEA), and Integrated Environmental Authorization (IPPC).
A key innovation is the integration of the Atmospheric Dispersion Modelling System (ADMS) developed by CERC, combined with machine learning algorithms for predictive monitoring. This synergy enables the real-time correlation of emission sources, meteorological conditions, and receptor impacts, supporting adaptive management and feedback-based corrective actions (MBCA). It allows environmental authorities to anticipate deviations, optimize mitigation measures, and validate the effectiveness of interventions through quantitative, evidence-based methods.
These pilots converge into a unified, scalable model for national implementation of AI-based permitting, aligned with the Do No Significant Harm (DNSH) principle and European Sustainability Reporting Standards (ESRS). The approach represents a major step toward intelligent, transparent, and efficient environmental governance.
David Carruthers, PhD in Atmospheric Physics, is Technical Director at CERC, leading air dispersion modelling and applied research supporting governments and industry in air quality assessme
Coauthor 1: Martin Seaton
Coauthor 2: James O’Neill