The purpose of the project is to identify the presence of anomalous chemical components along the coast of Paola lake area, in Sabaudia (LT). The analysis campaign has been based on an integrated use of technologies, to detect and trace eventual contamination phenomena. Several devices have been used, relying on Machine Learning algorithm site identification. Every aspect has been tailored for this specific use case.
Location
SABAUDIA, ITALY
Involved technologies
Aerial and underwater robots in swarming
Sensors
Artificial Intelligence
Satellite images from Copernicus, Sentinel
Analysis method for thermal images post-elaboration
The first surveys have been made with a smart drone with a thermal camera payload, to obtain thermal anomalies and possible spots of water matter with autonomous flight, in accordance with current law dispositions) thanks to customized software developed by H4R. The drone equipped with neural networks to master flight and obstacle avoidance. Thermal disturbances have been detected in the vicinity of the lake in areas of interest at different times, collecting thermal images with a high level of supervision. A series of high quality drone videos were the first indicators of possible anomalous contamination in the lake.
After aerial surveys, chemical composition analysis has been conducted. Results showed contamination abnormalities in some organic components such as nitrites.
In the sites where chemical anomalies were detected a further investigation has been done with underwater robots with video and sensors, in order to characterize and identify organic discharge pipes. Unfortunately, no algae and suspended material were present, which would have guaranteed more significative data.
We then moved to satellite image analysis: we processed them according to customized requirements, so that to reach the expected results. On this basis we were able to build up a dedicated analysis model, which gave us the ability to provide an expert judgment on all the mentioned technological architecture. This guaranteed H4R the opportunity to win an ESA call with “Move Thick Start Artificial Intelligence”.
It is important that the project is being developed.