Search

Cosmic muon imaging technology is increasingly being applied in various fields. However, simulating cosmic muons typically requires the rapid generation of a large number of muons and tracking their complex trajectories through intricate structures. This process is highly computationally demanding and consumes significant CPU time. To address these challenges, we introduce DeepMuon, an innovative deep learning model designed to efficiently and accurately generate cosmic muon distributions. In our approach, we employ the inverse Box-Cox transformation to reduce the kurtosis of the muon energy distribution, making it more statistically manageable for the model to learn. Additionally, we utilize the Sliced Wasserstein Distance (SWD) as a loss function to ensure precise simulation of the high-dimensional distributions of cosmic muons. We also demonstrate that DeepMuon can accurately learn muon distribution patterns from a limited set of data, enabling it to simulate real-world cosmic muon distributions as captured by detectors. Compared to traditional tools like CRY, DeepMuon significantly increases the speed of muon generation at sea level. Furthermore, we have developed a pipeline using DeepMuon that directly simulates muon distributions in underwater environments, dramatically accelerating simulations for underwater muon radiography and tomography. For more details on our open-source project, please visit https://github.com/wangab0/deepmuon.

High-energy physics experiments rely heavily on precise measurements of energy and momentum, yet face significant challenges due to detector limitations, calibration errors, and the intrinsic nature of particle interactions. Traditional unfolding techniques have been employed to correct for these distortions, yet they often suffer from model dependency and stability issues. We present a novel method, SwdFold, which utilizes the principles of optimal transport to provide a robust, model-independent framework to estimate the probability density ratio for data unfolding. It not only unfold the toy experimental event by reweighted simulated data distributions closely with true distributions but also maintains the integrity of physical features across various observables. We can expect it can enable more reliable predictions and comprehensive analyses as a high precision reweighting and unfolding tool in high-energy physics.

In the field of modern high-energy physics research, there is a growing emphasis on utilizing deep learning techniques to optimize event simulation, thereby expanding the statistical sample size for more accurate physical analysis. Traditional simulation methods often encounter challenges when dealing with complex physical processes and high-dimensional data distributions, resulting in slow performance. To overcome these limitations, we propose a solution based on deep learning with the sliced Wasserstein distance as the loss function. Our method shows its ability on high precision and large-scale simulations, and demonstrates its effectiveness in handling complex physical processes. By employing an advanced transformer learning architecture, we initiate the learning process from a Monte Carlo sample, and generate high-dimensional data while preserving all original distribution features. The generated data samples have passed the consistence test, that is developed to calculate the confidence of the high-dimentional distributions of the generated data samples through permutation tests. This fast simulation strategy, enabled by deep learning, holds significant potential not only for increasing sample sizes and reducing statistical uncertainties but also for applications in numerical integration, which is crucial in partial wave analysis, high-precision sample checks, and other related fields. It opens up new possibilities for improving event simulation in high-energy physics research.