Related papers: Generative Artificial Intelligence for Air Shower …
The need for large-scale production of highly accurate simulated event samples for the extensive physics programme of the ATLAS experiment at the Large Hadron Collider motivates the development of new simulation techniques. Building on the…
Fast and accurate simulations of the non-linear evolution of the cosmic density field are a major component of many cosmological analyses, but the computational time and storage required to run them can be exceedingly large. For this…
Substantial amounts of air-shower simulations are needed to derive the instrument response for analyzing Imaging Air Cherenkov Telescope (IACT) data. This process is both computationally intensive and requires repetition under varying…
Seismic inverse modeling is a common method in reservoir prediction and it plays a vital role in the exploration and development of oil and gas. Conventional seismic inversion method is difficult to combine with complicated and abstract…
An efficient scheme for one-dimensional extensive air shower simulation and its implementation in the program CONEX are presented. Explicit Monte Carlo simulation of the high-energy part of hadronic and electromagnetic cascades in the…
To augment training data for machine learning models in Ground Penetrating Radar (GPR) data classification and identification, this thesis focuses on the generation of realistic GPR data using Generative Adversarial Networks. An innovative…
SENECA is a hybrid air shower simulation written by H. Drescher that utilizes both Monte Carlo simulation and cascade equations. By using the cascade equations only in the high energy portion of the shower, where the shower is inherently…
Despite continuous improvements, precipitation forecasts are still not as accurate and reliable as those of other meteorological variables. A major contributing factor to this is that several key processes affecting precipitation…
The deep learning framework is witnessing expansive growth into diverse applications such as biological systems, human cognition, robotics, and the social sciences, thanks to its immense ability to extract essential features from…
Recently, generative machine-learning models have gained popularity in physics, driven by the goal of improving the efficiency of Markov chain Monte Carlo techniques and of exploring their potential in capturing experimental data…
Simulating showers of particles in highly-granular calorimeters is a key frontier in the application of machine learning to particle physics. Achieving high accuracy and speed with generative machine learning models can enable them to…
We introduce a generative adversarial network (GAN) model to simulate the 3-dimensional Lagrangian motion of particles trapped in the recirculation zone of a buoyancy-opposed flame. The GAN model comprises a stochastic recurrent neural…
A new hybrid approach to air shower simulations is described. At highest energies, each particle is followed individually using the traditional Monte Carlo method; this initializes a system of cascade equations which are applicable for…
Accurate modelling of spectra produced by X-ray sources requires the use of Monte-Carlo simulations. These simulations need to evaluate physical processes, such as those occurring in accretion processes around compact objects by sampling a…
Recently an essential progress in development of physical models for cosmic ray induced ionization in the atmosphere is achieved. Basically, the models are full target, i.e. based on Monte Carlo simulation of an electromagnetic-muon-nucleon…
At high energy, cosmic rays can only be studied by measuring the extensive air showers they produce in the atmosphere of the Earth. Although the main features of air showers can be understood within a simple model of successive…
We show that Generative Adversarial Networks (GANs) may be fruitfully exploited to learn stochastic dynamics, surrogating traditional models while capturing thermal fluctuations. Specifically, we showcase the application to a…
To simulate the interaction of cosmic rays with the Earth atmosphere requires highly complex computational resources and several statistical techniques have been developed to simplify those calculations. It is common to implement the…
We present simulations performed with REAS2, a new Monte Carlo code for the calculation of geosynchrotron radio emission from extensive air showers. The code uses thoroughly tested time-domain radio emission routines in conjunction with a…
We propose a novel bootstrap procedure for dependent data based on Generative Adversarial networks (GANs). We show that the dynamics of common stationary time series processes can be learned by GANs and demonstrate that GANs trained on a…