M. Cristoforetti
YOU?
Author Swipe
View article: GPTCast: a weather language model for precipitation nowcasting
GPTCast: a weather language model for precipitation nowcasting Open
This work introduces GPTCast, a generative deep learning method for ensemble nowcasting of radar-based precipitation, inspired by advancements in large language models (LLMs). We employ a generative pre-trained transformer (GPT) model as a…
View article: Multispacecraft Observations of the 27 Day Periodicity in Galactic Protons from 2018 to 2019
Multispacecraft Observations of the 27 Day Periodicity in Galactic Protons from 2018 to 2019 Open
Galactic cosmic-ray (GCR) intensities exhibit recurrent variations caused by their passage through plasma interaction regions corotating with the Sun, with the ∼27 day periodicity being the most prominent one. Data collected by the High-En…
View article: AI reconstruction of European weather from the Euro-Atlantic regimes
AI reconstruction of European weather from the Euro-Atlantic regimes Open
We present a non-linear AI-model designed to reconstruct monthly mean anomalies of the European temperature and precipitation based on the Euro-Atlantic Weather regimes (WR) indices. WR represent recurrent, quasi-stationary, and persistent…
View article: Development of the power supply of HEPD-02 instrument on board CSES-02 satellite
Development of the power supply of HEPD-02 instrument on board CSES-02 satellite Open
The High Energy Particle Detector HEPD-02 is primarily devoted to observe fluxes of cosmic-ray electrons, protons and light nuclei, with kinetic energies in the range from less than 10 MeV to few hundreds MeV, either incoming or trapped in…
View article: Mopidip: a modular real-time pipeline for machinery diagnosis and prognosis based on deep learning algorithms
Mopidip: a modular real-time pipeline for machinery diagnosis and prognosis based on deep learning algorithms Open
Condition monitoring is a crucial process for ensuring industrial assets’ reliability and operational efficiency. In the age of the digital industry, Artificial Intelligence (AI)-based data-driven condition monitoring is proving extremely …
View article: Can AI be enabled to perform dynamical downscaling? A latent diffusion model to mimic kilometer-scale COSMO5.0_CLM9 simulations
Can AI be enabled to perform dynamical downscaling? A latent diffusion model to mimic kilometer-scale COSMO5.0_CLM9 simulations Open
Downscaling based on deep learning (DL) is a key application in Earth system modeling, enabling the generation of high-resolution fields from coarse numerical simulations at reduced computational costs compared to traditional regional mode…
View article: Machine Learning for Detecting Time-Transient Phenomena in the Ionosphere and Correlation with Seismo-Induced Events.
Machine Learning for Detecting Time-Transient Phenomena in the Ionosphere and Correlation with Seismo-Induced Events. Open
The ionosphere, a crucial interface between Earth’s atmosphere and space, demonstrates complex temporal dynamics influenced by both terrestrial and extraterrestrial factors. This research investigates the potential of detecting precu…
View article: Conditional Diffusion to Enhance Performance of Object Detection in Unbalanced Data Engineering Drawings
Conditional Diffusion to Enhance Performance of Object Detection in Unbalanced Data Engineering Drawings Open
To train deep learning models, it is necessary to have a large amount of data available, preferably with balanced classes. Models often struggle to achieve acceptable performance because unbalanced classes drastically reduce the model's ge…
View article: The Catalogue of Gamma-Ray Burst Observations by HEPD-01 in the 0.3–50 MeV Energy Range
The Catalogue of Gamma-Ray Burst Observations by HEPD-01 in the 0.3–50 MeV Energy Range Open
The High-Energy Particle Detector (HEPD-01) on board the China Seismo-Electromagnetic Satellite, located on a Sun-synchronous orbit at 500 km of altitude with an inclination of 97°, features a dedicated logic counting low-energy event rate…
View article: The Scintillation Counters of the High-Energy Particle Detector of the China Seismo-Electromagnetic (CSES-02) Satellite
The Scintillation Counters of the High-Energy Particle Detector of the China Seismo-Electromagnetic (CSES-02) Satellite Open
The High-Energy Particle Detector (HEPD-02) is one of the scientific payloads of the China Seismo-Electromagnetic Satellite (CSES-02). The HEPD-02’s main purpose is to characterize the particle environment in the Earth’s vicinity, identify…
View article: Multispacecraft Observations of Protons and Helium Nuclei in Some Solar Energetic Particle Events toward the Maximum of Cycle 25
Multispacecraft Observations of Protons and Helium Nuclei in Some Solar Energetic Particle Events toward the Maximum of Cycle 25 Open
The intricate behavior of particle acceleration and transport mechanisms complicates the overall efforts in formulating a comprehensive understanding of solar energetic particle (SEP) events; these efforts include observations of low-energ…
View article: Pretrained models for "GPTCast: a weather language model for precipitation nowcasting"
Pretrained models for "GPTCast: a weather language model for precipitation nowcasting" Open
Dataset for "GPTCast: a weather language model for precipitation nowcasting" Preprint: https://arxiv.org/abs/2407.02089 Code: https://github.com/DSIP-FBK/GPTCast Dataset: https://doi.org/10.5281/zenodo.13598348
View article: MoPiDiP: A Modular Real-Time Pipeline for Machinery Diagnosis and Prognosis Based on Deep Learning Algorithms
MoPiDiP: A Modular Real-Time Pipeline for Machinery Diagnosis and Prognosis Based on Deep Learning Algorithms Open
Condition monitoring is a crucial process for ensuring industrial assets' reliability and operational efficiency. In the age of the digital industry, AI-based data-driven condition monitoring is proving extremely effective in detectin…
View article: Can AI be enabled to dynamical downscaling? A Latent Diffusion Model to mimic km-scale COSMO5.0\_CLM9 simulations
Can AI be enabled to dynamical downscaling? A Latent Diffusion Model to mimic km-scale COSMO5.0\_CLM9 simulations Open
Downscaling techniques are one of the most prominent applications of Deep Learning (DL) in Earth System Modeling. A robust DL downscaling model can generate high-resolution fields from coarse-scale numerical model simulations, saving the t…
View article: Nowcasting of extreme precipitation events: performance assessment of Generative Deep Learning methods
Nowcasting of extreme precipitation events: performance assessment of Generative Deep Learning methods Open
Radar-based precipitation nowcasting is one of the most prominent applications of deep learning (DL) in weather forecasting. The accurate forecast of extreme precipitation events remains a significant challenge for deep learning models, pr…
View article: Can AI be enabled to dynamical downscaling? Training Deep Generative Models to downscale ERA5 to high-resolution COSMO-CLM dynamical reanalyses over Italy 
Can AI be enabled to dynamical downscaling? Training Deep Generative Models to downscale ERA5 to high-resolution COSMO-CLM dynamical reanalyses over Italy  Open
Downscaling techniques are one of the most prominent applications of Deep Learning (DL) in Earth System Modeling. A robust DL downscaling model can generate high-resolution fields from coarse-scale numerical model simulations, saving the t…
View article: Pipeline for performance evaluation of flavour tagging dedicated Graph Neural Network algorithms
Pipeline for performance evaluation of flavour tagging dedicated Graph Neural Network algorithms Open
Machine Learning is a rapidly expanding field with a wide range of applications in science. In the field of physics, the Large Hadron Collider, the world's largest particle accelerator, utilizes Neural Networks for various tasks, including…
View article: Author Correction: Evidence of an upper ionospheric electric field perturbation correlated with a gamma ray burst
Author Correction: Evidence of an upper ionospheric electric field perturbation correlated with a gamma ray burst Open
Correction to: Nature Communications, published online 14 November 2023 In this article the author name Mauro Lolli was incorrectly written as Marco Lolli. The original article has been corrected.
View article: Gamma-Ray Burst Observations by the High-Energy Particle Detector on board the China Seismo-Electromagnetic Satellite between 2019 and 2021
Gamma-Ray Burst Observations by the High-Energy Particle Detector on board the China Seismo-Electromagnetic Satellite between 2019 and 2021 Open
In this paper we report the detection of five strong gamma-ray bursts (GRBs) by the High-Energy Particle Detector (HEPD-01) mounted on board the China Seismo-Electromagnetic Satellite, operational since 2018 on a Sun-synchronous polar orbi…
View article: Pipeline for performance evaluation of flavour tagging dedicated Graph Neural Network algorithms
Pipeline for performance evaluation of flavour tagging dedicated Graph Neural Network algorithms Open
Machine Learning is a rapidly expanding field with a wide range of applications in science. In the field of physics, the Large Hadron Collider, the world's largest particle accelerator, utilizes Neural Networks for various tasks, including…
View article: Gamma-Ray Burst observations by the high-energy charged particle detector on board the CSES-01 satellite between 2019 and 2021
Gamma-Ray Burst observations by the high-energy charged particle detector on board the CSES-01 satellite between 2019 and 2021 Open
In this paper we report the detection of five strong Gamma-Ray Bursts (GRBs) by the High-Energy Particle Detector (HEPD-01) mounted on board the China Seismo-Electromagnetic Satellite (CSES-01), operational since 2018 on a Sun-synchronous …
View article: Electron Signal Induced by GRB 221009A on Charged Particle Telescopes of POES and MetOp Satellites
Electron Signal Induced by GRB 221009A on Charged Particle Telescopes of POES and MetOp Satellites Open
GRB 221009A is a long gamma-ray burst among the most energetic and nearest ( z = 0.151) detected so far. The energy fluence of the burst was so large to cause ionization of the upper layers of Earth’s atmosphere and also observable signals…
View article: Automated feature selection procedure for particle jet classification
Automated feature selection procedure for particle jet classification Open
The high dimensionality of the data produced in high-energy physics experiments makes the use of machine learning algorithms, such as neural networks, necessary to improve the performance of reconstruction and classification of the analyze…
View article: Constraining Deep Neural Network classifiers’ systematic uncertainty via input feature space reduction
Constraining Deep Neural Network classifiers’ systematic uncertainty via input feature space reduction Open
In this work, we show how using a sub-optimal set of input features can lead to higher systematic uncertainty associated with Deep Neural Network classifier predictions. For this study, we considered the case of highly boosted di-jet reson…
View article: Time Dependence of 50–250 MeV Galactic Cosmic-Ray Protons between Solar Cycles 24 and 25, Measured by the High-energy Particle Detector on board the CSES-01 Satellite
Time Dependence of 50–250 MeV Galactic Cosmic-Ray Protons between Solar Cycles 24 and 25, Measured by the High-energy Particle Detector on board the CSES-01 Satellite Open
Time-dependent energy spectra of galactic cosmic rays (GCRs) carry crucial information regarding their origin and propagation throughout the interstellar environment. When observed at the Earth, after traversing the interplanetary medium, …
View article: Observation of Anomalous Electron Fluxes Induced by GRB221009A on CSES-01 Low-energy Charged Particle Detector
Observation of Anomalous Electron Fluxes Induced by GRB221009A on CSES-01 Low-energy Charged Particle Detector Open
High-energy, long gamma-ray bursts (GRBs) can be generated by the core collapse of massive stars at the end of their lives. When they happen in the close-by universe they can be exceptionally bright, as seen from the Earth in the case of t…