Applying Artificial Intelligence to Astrophysics
MADELEinE (MAchine and DEep LEarning in Experiments) is a research program (PI: Antonio Pagliaro) that applies artificial intelligence to astrophysics and astroparticle physics. We develop machine and deep learning methods to analyse the large datasets produced by telescopes and particle detectors, with attention to making the resulting models interpretable and reproducible.
Our main effort is on Imaging Atmospheric Cherenkov Telescopes (IACTs), centred on the ASTRI-Horn telescope and the ASTRI Mini-Array. Here we address the core reconstruction problems — gamma/hadron separation, energy and direction reconstruction — combining the classical Hillas-parameter pipeline with temporal pixel information, ensemble learning and convolutional neural networks, with the goal of improving telescope sensitivity and supporting the discovery of new sources.
Within the JEM-EUSO program we apply deep learning to the infrared data from stratospheric balloon flights (EUSO-SPB1, EUSO-SPB2) and to the ultraviolet data from space (Mini-EUSO). The same methods extend to satellite data for atmospheric monitoring.
Alongside event reconstruction, the program develops methods in computer vision, time-series analysis and explainable AI, and applies the same quantitative, validation-focused approach to data-driven finance as a transfer domain.
The team brings together expertise in AI, astrophysics and computer science, and collaborates with researchers and institutions across these fields. We welcome collaborations and student projects — feel free to get in touch.
The research program is carried out partly within the framework of the National Centre for HPC, Big Data and Quantum Computing.
Contact person
Antonio Pagliaro
Team
Anna Anzalone
A. Alessio Compagnino
Giancarlo Cusumano
Antonino La Barbera
Valentina La Parola
Antonio Pagliaro
Pierluca Sangiorgi
Antonio Tutone
Recent MADELEinE Papers
- Cognitive Biases in Large Language Models: A Systematic Quantitative Assessment and Debiasing Analysis — Electronics 15, 2026
- Regime-Aware LightGBM for Stock Market Forecasting: A Validated Walk-Forward Framework with Statistical Rigor and Explainable AI Analysis — Electronics 15, 2026
- Cognitive Biases in Asset Pricing: An Empirical Analysis of the Alphabet Effect and Ticker Fluency in the US Market — Symmetry 18, 2026
- The Specialization of Intelligence in AI Horizons: Present Status and Visions for the Next Era — Appl. Sci. 15, 2025
- An Introduction to Machine Learning Methods for Fraud Detection — Appl. Sci. 15, 2025
- Artificial Intelligence vs. Efficient Markets: A Critical Reassessment of Predictive Models in the Big Data Era — Electronics 14, 2025
- Machine Learning-Enhanced Discrimination of Gamma-Ray and Hadron Events Using Temporal Features: An ASTRI Mini-Array Analysis — Appl. Sci. 15(7), 2025 (cover story)
- Advanced AI and Machine Learning Techniques for Time Series Analysis and Pattern Recognition — Appl. Sci. 15, 2025 (editorial)
- An Introduction to Machine and Deep Learning Methods for Cloud Masking Applications — Appl. Sci. 14, 2024
- AI in Experiments: Present Status and Future Prospects — Appl. Sci. 13, 2023
- Application of Machine Learning Ensemble Methods to ASTRI Mini-Array Cherenkov Event Reconstruction — Appl. Sci. 13(14), 2023
- Forecasting Significant Stock Market Price Changes Using Machine Learning: Extra Trees Classifier Leads — Electronics 12, 2023
- Application of Machine and Deep Learning Methods to the Analysis of IACTs Data — Springer (ISBN 978-3-030-65867-0), 2021