Proposte Tesi
SERVIZI PER LA DIDATTICA
Home
Created with Raphaël 2.1.0
Servizi per gli studenti
Created with Raphaël 2.1.0
Proposte Tesi

Ricerca CERCA
  KEYWORD

Artificial intelligence for flood forecasting

Parole chiave AI, ARTIFICIAL INTELLIGENCE, ARTIFICIAL NEURAL NETWORK, DEEP LEARNING, DEEP NEURAL NETWORKS, FLOOD FORECAST, FORECAST, MACHINE LEARNING, TIME SERIES

Riferimenti EDOARDO PATTI

Riferimenti esterni Marco Castangia (marco.castangia@polito.it)

Gruppi di ricerca DAUIN - GR-06 - ELECTRONIC DESIGN AUTOMATION - EDA, ELECTRONIC DESIGN AUTOMATION - EDA, GR-06 - ELECTRONIC DESIGN AUTOMATION - EDA, ICT4SS - ICT FOR SMART SOCIETIES

Tipo tesi SPERIMENTALE

Descrizione 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.

Conoscenze richieste 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).


Scadenza validita proposta 08/01/2026      PROPONI LA TUA CANDIDATURA