相关论文: Neural Networks as Effective Surrogate Models of R…
We present a novel machine learning-based approach to generate fast-executing virtual radiofrequency quadrupole (RFQ) particle accelerators using surrogate modelling. These could potentially be used as on-line feedback tools during beam…
Continuous developments in Additive Manufacturing (AM) technologies are opening opportunities in novel machining, and improving design alternatives for modern particle accelerator components. One of the most critical, complex, and delicate…
The ongoing development of quantum processors is driving breakthroughs in scientific discovery. Despite this progress, the formidable cost of fabricating large-scale quantum processors means they will remain rare for the foreseeable future,…
Radio-frequency quadrupole (RFQ) linear accelerators appeared on the accelerator scene in the late 1970s and have since revolutionized the domain of low-energy proton and ion acceleration. The RFQ makes the reliable production of…
For computational efficiency, surrogate models have been used to emulate mathematical simulators for physical or biological processes. High-speed simulation is crucial for conducting uncertainty quantification (UQ) when the simulation is…
Surrogate models of numerical relativity simulations of merging black holes provide the most accurate tools for gravitational-wave data analysis. Neural network-based surrogates promise evaluation speedups, but their accuracy relies on…
Surrogate models are ubiquitously used in industry and academia to efficiently approximate given black box functions. As state-of-the-art methods from classical machine learning frequently struggle to solve this problem accurately for the…
There are applications, which require MeV-range multiple-beams consisting of a large number of identical highly packed beamlets. The multiple-beam RFQ (MB-RFQ) arranged as a matrix array of longitudinal rod-electrodes is appropriate…
State-of-the-art computer codes for simulating real physical systems are often characterized by a vast number of input parameters. Performing uncertainty quantification (UQ) tasks with Monte Carlo (MC) methods is almost always infeasible…
Physics simulators are essential in science and engineering, enabling the analysis, control, and design of complex systems. In experimental sciences, they are increasingly used to automate experimental design, often via combinatorial search…
There is renewed interest in developing small modular reactors and micro-reactors. Innovation is necessary in both construction and operation methods of these reactors to be financially attractive. For operation, an area of interest is the…
This study investigates whether Physically Recurrent Neural Networks (PRNNs), a recent surrogate model for heterogeneous materials, trained on a micromodel with fixed material parameters, can maintain accuracy for varying material…
We present a framework for automatically structuring and training fast, approximate, deep neural surrogates of stochastic simulators. Unlike traditional approaches to surrogate modeling, our surrogates retain the interpretable structure and…
It is well known that the tuning of a long radio-frequency quadrupole accelerator is demanding. This study investigated how to realize efficient long RFQ accelerators with multiple shorter and independent cavities. From the RF point of…
Radio Frequency Quadrupole (RFQ) accelerators often need to face the challenges of space charge effects from high beam currents. This study investigated how to reach RFQ beam dynamics designs with not only high beam transmission and short…
The transition of the power grid requires new technologies and methodologies, which can only be developed and tested in simulations. Especially larger simulation setups with many levels of detail can become quite slow. Therefore, the number…
Neural networks are increasingly used in complex (data-driven) simulations as surrogates or for accelerating the computation of classical surrogates. In many applications physical constraints, such as mass or energy conservation, must be…
In many mechanistic medical, biological, physical and engineered spatiotemporal dynamic models the numerical solution of partial differential equations (PDEs) can make simulations impractically slow. Biological models require the…
Designing a high-quality plasma injector electron source driven by a laser beam relies on numerical parametric studies using particle-in-cell codes. The common input parameters to explore are laser characteristics, plasma species and…
High-performance scientific simulations, important for comprehension of complex systems, encounter computational challenges especially when exploring extensive parameter spaces. There has been an increasing interest in developing deep…