Via Marco Biagi 5 – 73100 Lecce, Italy
(+39) 0832 1902411
Gabriele Accarino obtained his Master’s degree in Computer Engineering at the University of Salento with honours, presenting a thesis entitled: “On the use of Deep Learning in the Climate Change domain”. The thesis concerns the use of Artificial Neural Networks, in particular Long-Short Term Memory (LSTM) networks for time series prediction by addressing a case study in the context of Climate Change.
In November 2018, he started the PhD course in Data Science at the Department of Biological and Environmental Sciences and Technologies (DiSTeBA) of the University of Salento and, since May 2018, he has been collaborating with the Advanced Scientific Computing (ASC) division and the Scientific Data Management and Learning (SDML) group of the Euro-Mediterranean Center on Climate Change (CMCC). In particular, his research focuses on Machine Learning and Deep Learning algorithms and Big Data management with a particular application to the climate context.
Furthermore, he is looking for a possible Hybrid Modeling approach that involves the use of predictive algorithms to approximate computationally expensive code kernels of the climate model and Machine Learning techniques to emulate Climatic Downscaling models. Recently, his research is also involving issues concerning Climate Change and Conflicts and in particular the development of a framework for the detection of conflict situations. The Leonardo Company awarded him with the Leonardo Innovation Award 2018 for the Ph.D. category, evaluating his research project entitled: “Anima: An Artificial Intelligence tool for Migration Analysis and projections” that uses Artificial Neural Networks to predict the trend of migrants’ processes and to identify the most likely countries of origin and arrival in the medium-long term.
LATEST PUBLICATIONS
- End-to-End Workflows for Climate Science: Integrating HPC Simulations, Big Data Processing, and Machine Learning
- An ensemble machine learning approach for tropical cyclone localization and tracking from ERA5 reanalysis data
- An Artificial Neural Network-based approach for predicting the COVID-19 daily effective reproduction number Rt in Italy
- The effect of known and unknown confounders on the relationship between air pollution and Covid-19 mortality in Italy: A sensitivity analysis of an ecological study based on the E-value
- MSG-GAN-SD: A Multi-Scale Gradients GAN for Statistical Downscaling of 2-Meter Temperature over the EURO-CORDEX Domain
- Limits of Compartmental Models and New Opportunities for Machine Learning: A Case Study to Forecast the Second Wave of COVID-19 Hospitalizations in Lombardy, Italy
- A multi-model architecture based on Long-Short Term Memory neural networks for multi-step sea level forecasting
- Assessing correlations between short-term exposure to atmospheric pollutants and COVID-19 spread in all Italian territorial areas