Estimating Elliptic Flow Coefficient in Heavy Ion Collisions using Deep Learning

Machine learning techniques have been employed for the high energy physics community since the early 80s to deal with a broad spectrum of problems. This work explores the prospects of using deep learning techniques to estimate elliptic flow (<math display="inline"><msub><mi>v</mi><mn>2</mn></msub></math>) in heavy-ion collisions at the RHIC and LHC energies. A novel method is developed to process the input observables from particle kinematic information. The proposed deep neural network (DNN) model is trained with Pb-Pb collisions at <math display="inline"><msqrt><msub><mi>s</mi><mrow><mi>NN</mi></mrow></msub></msqrt><mo>=</mo><mn>5.02</mn><mtext> </mtext><mtext> </mtext><mi>TeV</mi></math> minimum bias events simulated with a multiphase transport model. The predictions from the machine learning technique are compared to both simulation and experiment. The deep learning model seems to preserve the centrality and energy dependence of <math display="inline"><msub><mi>v</mi><mn>2</mn></msub></math> for the LHC and RHIC energies. The DNN model is also quite successful in predicting the <math display="inline"><msub><mi>p</mi><mi mathvariant="normal">T</mi></msub></math> dependence of <math display="inline"><msub><mi>v</mi><mn>2</mn></msub></math>. When subjected to event simulation with additional noise, the proposed DNN model still keeps the robustness and prediction accuracy intact up to a reasonable extent.