AI and satellites against environmental crimes: detecting illegal waste dumping with 90 per cent accuracy
image: Last April, the PERIVALLON project partners gathered in Soave (Verona) for a general meeting to assess technological progress and coordinate upcoming activities. On this occasion, two pilot demonstrations were conducted at the Monte Calvarina training and exercise centre, coordinated by ARPA Lombardia and the SAFE Foundation. The tests allowed the evaluation of AI solutions developed by the Politecnico di Milano’s team to analyse satellite images and images captured by drone flyovers. Different types of waste were successfully identified (and removed) in both trials.
Credit: Politecnico di Milano
Milan, 15 July 2025 - Detecting illegal waste dumping with 90 per cent accuracy using Artificial Intelligence and satellites. This is groundbreaking technology developed by Politecnico di Milano, and is already operational in several European countries. A system that speeds up environmental investigations, enhancing efforts to tackle the ecomafia and protect the land.
Illegal waste management is on the rise across the European Union and represents one of the most profitable activities for organised crime. The recent ruling of the European Court of Human Rights on the “Terra dei Fuochi”, which condemned Italy for failing to protect its population from toxic fires, highlights the urgent need for more effective tools to prevent and combat these crimes.
A team of researchers from the Politecnico di Milano’s Department of Electronics, Information and Bioengineering (DEIB) has developed an advanced system for analysing satellite imagery, capable of identifying illegal dumping sites and unauthorised waste disposal with more than 90 per cent accuracy.
The PERIVALLON project, funded under the Horizon Europe programme, involves 24 partners from 12 EU and non-EU countries, including the SAFE Foundation, ARPA Lombardia, and the Carabinieri Environmental Unit. Thanks to partnerships with environmental authorities and law enforcement agencies, this technology is being used for large-scale land monitoring.
At the heart of this innovation is the use of neural networks and advanced algorithms to analyse satellite images and detect hazardous waste deposits hidden in urban, industrial, and agricultural areas. One of the project's key tools is the public AerialWaste dataset (https://aerialwaste.org), the first of its kind globally, which has already been downloaded more than 6,500 times by international researchers.
A pilot study conducted with ARPA Lombardia in more than 100 municipalities showed that Artificial Intelligence drastically reduces investigation times, enabling faster intervention and preventing irreversible damage to ecosystems and public health.
Piero Fraternali and Giacomo Boracchi, from the Politecnico di Milano’s Department of Electronics, Information and Bioengineering (DEIB), said: "Thanks to Artificial Intelligence and satellite image analysis, we can detect signs of environmental crime on a large scale, quickly and accurately. These tools mark a paradigm shift, enabling systematic regional monitoring to support law enforcement and environmental agencies."
Systematic regional monitoring through frequent, large-scale analysis is a major step forward in fighting environmental crime. Tools like this provide a practical response to preventing future ecological disasters.
These new technologies enhance the investigative capabilities of law enforcement and ensure greater transparency and accountability in waste management, supporting more effective prevention and enforcement efforts.
Last April, the PERIVALLON project partners gathered in Soave (Verona) for a general meeting to assess technological progress and coordinate upcoming activities. On this occasion, two pilot demonstrations were conducted at the Monte Calvarina training and exercise centre, coordinated by ARPA Lombardia and the SAFE Foundation. The tests allowed the evaluation of AI solutions developed by the Politecnico di Milano’s team to analyse satellite images and images captured by drone flyovers. Different types of waste were successfully identified (and removed) in both trials.
The PERIVALLON consortium brings together security institutions, environmental bodies and internationally renowned universities. Alongside Politecnico di Milano, partners include the European Union Satellite Centre (EU SatCen), Centre for Research & Technology Hellas (CERTH), Centre for Security Studies (KEMEA), University of Vienna, University of Applied Sciences for Public Administration and Legal Affairs of Bavaria, Swedish Police Authority, Hellenic Police, Carabinieri Corps, General Inspectorate of the Romanian Border Police, Ministry of Environment and Energy of Greece, General Inspectorate of Police of the Ministry of Internal Affairs of the Republic of Moldova, Regional Environmental Protection Agency of Lombardy (ARPA Lombardia), and SAFE Foundation.