Projects

Energy GNoME

The Energy-GNoME project leverages Artificial Intelligence to revolutionize materials science, providing a database of over 33,000 promising energy materials identified from 380,000 novel stable crystals. Utilizing Machine Learning and Deep Learning, the project mitigates cross-domain data bias and predicts critical properties for thermoelectric materials, battery cathodes, and perovskites. Energy-GNoME serves as a powerful tool to streamline experimental and computational efforts, advancing discoveries in energy generation, storage, and conversion.

Advanced Materials Energy Materials Materials Science Artificial Intelligence Machine Learning Deep Learning Computational Chemistry Dataset Thermoelectric Battery Perovskite

Python Jupyter PyTorch

Python

2

Sistemi a combustione (EN: Combustion systems)

This repository enhances our "Sistemi a Combustione" (English: Combustion Systems) master's course by providing Jupyter notebooks to educate students in utilizing Python for engineering tasks. It demonstrates how advanced Machine Learning (ML) and Deep Learning (DL) tools can be effectively applied in engineering problems. Specifically, we showcase examples of applications for Fully Connected Neural Networks (FCNN), Convolutional Neural Networks (CNN), and Reinforcement Learning (RL).

Lectures Machine Learning Deep Learning Energy Combustion Engineering

Python Jupyter TensorFlow Colab

Enhancing the ReaxFF

This repository contains the protocol (presented as Jupyter notebooks) used for retraining the ReaxFF force field for the inorganic compound LiF.

Python Battery Jupyter Molecular Dynamics Density Functional Theory Reaxff

Python Jupyter

5

Enhancing the ReaxFF DFT database

This repository contains the database used for retraining the ReaxFF force field for the inorganic compound LiF.

Python Database Battery Jupyter Molecular Dynamics Density Functional Theory Reaxff

Python Jupyter ASE

4

SEI Builder

This app is an ASE-base workflow used to reproduce a rational initial SEI morphology at the atomic scale by stochastically placing the crystal grains of the inorganic salts formed during the SEI's reaction.

LIBs SEI MD ASE

Python Jupyter

Python

11

Energy storage

With this repository our "Energy Storage" master's course now offers Jupyter notebooks to teach students how to use Python for engineering analysis and simulate Lithium-Ion batteries (LIB) using models like Pseudo 2-Dimensional (P2D). Students gain hands-on experience to understand battery physics and apply it to real-world engineering problems. These user-friendly notebooks help students improve coding skills and prepare for a successful career in Energy Engineering.

Lectures Energy Storage Engineering LIB

Python Jupyter Colab

7

Applicazioni Energetiche dei Materiali

A series of Jupyter notebooks for the "Applicazioni Energetiche dei Materiali" (Energy Applications of Materials) master's course that equip students with the necessary tools to perform big-data analyses and utilize machine learning algorithms to search for optimal materials for energy devices. By using these notebooks, students can gain hands-on experience in conducting data-driven research that can lead to breakthroughs in energy-related fields

Lectures Energy Engineering ML

Python Jupyter Colab

2