Speaker
Description
Deep learning (DL) is one of the most popular machine learning frameworks in the high-energy physics community and has been applied to solve numerous problems for decades. The ability of the DL models to learn unique patterns and correlations from data to map highly complex non-linear functions is a matter of interest. Such features of the DL model could be used to explore the hidden physics laws that govern particle production, anisotropic flow, spectra, etc., in heavy-ion collisions. This work sheds light on the possible use of the DL techniques such as the feed-forward deep neural network (DNN) based estimator to predict the elliptic flow ($v_2$) in heavy-ion collisions at RHIC and LHC energies. A novel method is proposed to feed the track-level information as input to the DNN model. The model is trained with Pb-Pb collisions at $\sqrt{s_{\rm NN}} = 5.02$ TeV minimum bias simulated events with a multi-phase transport model (AMPT). All charged hadrons are used for the training. The trained model is successfully applied to estimate the centrality dependence of $v_2$ for both LHC and RHIC energies. The proposed model is quite successful in predicting the transverse momentum ($p_{\rm T}$) dependence of $v_2$ as well. Further extension of the work is being performed to look into the elliptic flow of pions, kaons, and protons at these energies using the proposed DNN model. Some of the scaling properties are also explored. A noise sensitivity test is performed to estimate the systematic uncertainty of this method. Results of the DNN estimator are compared to both simulation and experiment, which concludes the robustness and prediction accuracy of the model.
Reference:
Neelkamal Mallick, Suraj Prasad, Aditya Nath Mishra, Raghunath Sahoo, and Gergely G\'abor Barnaf\"oldi, Phys.Rev.D \textbf{105}, 114022 (2022).
| Session | Heavy Ions and QCD |
|---|
