Advanced Particle Classification in Space Calorimetry Using Transformer-Based and Gradient Boosting Models

Artificial intelligence has made remarkable progress across numerous domains, including physics, where machine learning and deep learning methods have become increasingly common. In high-energy physics, these approaches have significantly advanced tasks like event reconstruction, pattern recognition, and large-scale data analysis. The present study explores the application of machine learning techniques to the classification of electromagnetic and hadronic showers in space calorimeter experiments. Leveraging Monte Carlo simulations and a dedicated feature engineering, the findings demonstrate the strong potential of AI to improve classification performance in space calorimetry.