Machine Learning model driven prediction of the initial geometry in Heavy-Ion Collision experiments

TL;DR

This paper demonstrates that supervised machine learning methods can accurately predict initial geometry properties in heavy-ion collision experiments across different models, significantly improving accuracy especially for central collisions.

Contribution

The study systematically compares multiple ML algorithms and sampling methods, achieving multi-fold accuracy improvements in predicting impact parameter, eccentricity, and participant eccentricity across three collision models.

Findings

ML models significantly improve impact parameter prediction accuracy.

Including impact parameter as a feature enhances eccentricity prediction.

Prediction accuracy varies with collision centrality, with notable improvements for central collisions.

Abstract

We demonstrate high prediction accuracy of three important properties that determine the initial geometry of the heavy-ion collision (HIC) experiments by using supervised Machine Learning (ML) methods. These properties are the impact parameter, the eccentricity and the participant eccentricity. Though ML techniques have been used previously to determine the impact parameter of these collisions, we study multiple ML algorithms, their error spectrum, and sampling methods using exhaustive parameter scans and ablation studies to determine a combination of efficient algorithm and tuned training set that gives multi-fold improvement in accuracy for all three different heavy-ion collision models. The three models chosen are a transport model, a hydrodynamic model and a hybrid model. The motivation of using three different heavy-ion collision models was to show that even if the model is trained using a transport model, it gives accurate results for a hydrodynamic model as well as a hybrid model. We show that the accuracy of the impact parameter prediction depends on the centrality of the collision. With the standard application of ML training methods, prediction accuracy is considerable low for central collisions. Our method increases this accuracy by multiple folds. We also show that the eccentricity prediction accuracy can be improved by inclusion of the impact parameter as a feature in all these algorithms. We discuss how the errors can be minimized and the accuracy can be improved to a great extent in all the ranges of impact parameter and eccentricity predictions.