| KEYWORD |
GR-06 - ELECTRONIC DESIGN AUTOMATION - EDA
Artificial intelligence for flood forecasting
keywords AI, ARTIFICIAL INTELLIGENCE, ARTIFICIAL NEURAL NETWORK, DEEP LEARNING, DEEP NEURAL NETWORKS, FLOOD FORECAST, FORECAST, MACHINE LEARNING, TIME SERIES
Reference persons EDOARDO PATTI
External reference persons Marco Castangia (marco.castangia@polito.it)
Research Groups DAUIN - GR-06 - ELECTRONIC DESIGN AUTOMATION - EDA, ELECTRONIC DESIGN AUTOMATION - EDA, GR-06 - ELECTRONIC DESIGN AUTOMATION - EDA, ICT4SS - ICT FOR SMART SOCIETIES
Thesis type EXPERIMENTAL
Description The aim of the thesis is to study new AI-based methods to forecast extreme flood events in the vicinity of rivers in the national territory. The purpose of using AI in this context is to provide less computationally intensive solutions to assist existing methods based on physical simulations. The proposed models will exploit large amounts of historical data from ground sensors and meteorological satellites to provide more accurate forecasts than existing methods, thus advancing the current state of the art in this field. During the thesis, the student will learn to process data from multiple modalities including images and time series. Furthermore, the student will implement advanced machine learning models such as convolutional neural networks, recurrent neural networks, transformers and graph neural networks. The thesis promises to have a high impact thanks to our collaboration with regional environmental protection agencies, which will assist us in the data collection and model validation phases.
Required skills The student must have the following technical skills (in order of importance) to successfully carry out the thesis work:
- Good knowledge of the Python programming language;
- Experience with relevant Python libraries (e.g., pandas, numpy, PyTorch);
- Good knowledge of typical machine learning pipelines (training and validation);
- Some knowledge of the main deep learning architectures (CNN, LSTM, transformers).
Deadline 08/01/2026
PROPONI LA TUA CANDIDATURA