Lorenzo Michieletto
Papers
1
Total Citations
3
H-Index
1
About
Lorenzo Michieletto is a researcher whose work sits at the intersection of environmental monitoring and advanced machine learning, with a particular focus on aquatic robotics. His key research areas include water quality prediction, hybrid aerial-underwater robotic systems, and the development of robust deep learning models for challenging, real-world datasets. Michieletto’s most notable contribution is his work on a dissolved oxygen (DO) prediction model, detailed in his highly cited 2020 paper, "Investigation of water quality using transfer learning, phased LSTM and correntropy loss." This study directly supports the Hybrid Aerial Underwater Robotics System (HAUCS) project by tackling the critical problem of predicting water quality from small, incomplete datasets—a common hurdle in environmental science. By ingeniously combining transfer learning, a phased Long Short-Term Memory (LSTM) network, and a correntropy loss function, he developed a robust solution that overcomes data scarcity and missing values. This work has garnered significant attention, earning 3 citations and establishing a foundation for more reliable, data-driven environmental monitoring. Michieletto’s research is essential reading for students and researchers interested in the practical application of AI to solve pressing ecological challenges, particularly in aquaculture and autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1