Деркач Денис Александрович

Reinforcement learning for accelerator beamline control: A simulation-based approach

2026 · ARTICLE · en

Particle accelerators play a pivotal role in advancing scientific research, yet optimizing beamline configurations to maximize particle transmission remains a labor-intensive task requiring expert intervention. In this work, we introduce reinforcement learning for accelerator beamline control (RLABC), a Python-based library that reframes beamline optimization as a reinforcement learning (RL) problem. Leveraging the Elegant simulation framework, RLABC automates the creation of an RL environment from standard lattice and command files, enabling sequential tuning of magnets to minimize particle losses. We define a comprehensive state representation capturing beam statistics, actions for adjusting magnet parameters, and a reward function focused on transmission efficiency. Employing the deep deterministic policy gradient (DDPG) algorithm, we demonstrate RLABC’s efficacy on two beamlines, achieving transmission rates of 94% and 91%, comparable to expert manual optimizations. This approach bridges accelerator physics and machine learning, offering a versatile tool for physicists and RL researchers alike to streamline beamline tuning.

Online Neural Networks for Change-Point Detection

2026 · ARTICLE · en

Moments when a time series changes its behavior are called change points. Occurrence of change point implies that the state of the system is altered and its timely detection might help to prevent unwanted consequences. In this paper, we present two change-point detection approaches based on neural networks and online learning. These algorithms demonstrate linear computational complexity and are suitable for change-point detection in large time series. We compare them with the best known algorithms on various synthetic and real world data sets. Experiments show that the proposed methods outperform known approaches. We also prove the convergence of the algorithms to the optimal solutions and describe conditions rendering current approach more powerful than offline one.

The Ratan Active Region Patches (RARPs) database: A new database of solar active region radio signatures from the RATAN-600 telescope

2026 · ARTICLE · en

Solar flares and coronal mass ejections, originating from solar active regions (ARs), are the primary drivers of space weather and can disrupt technological systems. Forecasting efforts heavily rely on photospheric magnetic field data from the Space-weather HMI Active Region Patch (SHARPs) data products. However, the crucial energy release occurs higher in the solar corona. Radio observations from instruments like the RATAN-600 telescope directly probe this region, but their scientific use has been hindered by a lack of standardized and accessible data products. To address this gap, we have developed the Ratan Active Region Patches (RARPs) database, a new public resource of multi-frequency radio spectra for solar ARs. Generated using RATANSunPy software, RARPs provides the first standardized radio counterpart to magnetic field archives. The database contains over 160,000 calibrated AR observations from 2009 to 2025, each including 3–18 GHz spectra and rich metadata. We demonstrate the scientific utility of this database by using machine learning to forecast solar flares. The radio spectra are first compressed into low-dimensional embedded features using an autoencoder, which are then used as predictors in baseline logistic regression classifiers. We compare the predictive power of these embedded RARPs features with that of the 18 SHARPs magnetic field parameters provided in the SHARPs data product headers. Our results show that while SHARPs data provides superior flare discrimination, the radio signatures in RARPs possess clear predictive potential and, for M-class and above flares, yield lower Brier Scores and positive Brier Skill Scores relative to SHARPs, indicating more accurate probabilistic forecasts for these events. This establishes radio data as a valuable and complementary information source. The RARPs database significantly lowers the barrier for researchers to incorporate radio diagnostics into their work. By making these coronal signatures readily available, our work enables new multi-wavelength investigations into the physics of ARs and strengthens the foundation for developing more accurate space weather forecasting models

Database of tensile test results of carbon fibers impregnated with thermoplastic polymer.

2026 в печати · ARTICLE · en

В данном исследовании представлен исчерпывающий набор экспериментальных данных, направленных на выявление механизмов и закономерностей, определяющих деформационное поведение композитов, армированных непрерывными углеродными волокнами (УВ) на основе термопластичных полимеров. В работе описаны методы извлечения данных, которые впоследствии могут быть использованы для оптимизации механических свойств таких структур с помощью моделей нейронных сетей. В данной статье рассматривается термопластичный полимер полисульфон (ПСУ) марки Ultrason S 2010, который использовался в качестве матричного материала для композитов, а в качестве армирующих волокон использовались высокопрочные волокна Toray T700SC. Образцы композита в виде стержней диаметром 1 мм были получены путем пропитки волокон раствором полисульфона в N-метил-2-пирролидоне с последующим удалением растворителя. Собранный набор данных содержит более 600 результатов испытаний на растяжение, включая диаграммы нагрузка-деформация для различных условий испытаний, данные о механизмах разрушения образцов и изображения микроструктуры образцов в поперечном и продольном сечениях, полученные с помощью сканирующего электронного микроскопа (СЭМ). Этот набор данных будет полезен для разработки моделей машинного обучения.

Generative models and seq2seq techniques for the flash-simulation of the LHCb experiment

2025 · ARTICLE · en

Simulating detector and reconstruction effects on physics quantities is crucial for data analysis, but it is coming unsustainably costly for the upcoming HEP experiments. The most radical approach to speed-up detector simulation is Flash Simulation, as proposed by the LHCb collaboration in Lamarr, a software package implementing a novel simulation paradigm relying on Deep Generative Models and Seq2seq attention-driven techniques to deliver simulated samples. Thanks to its modular layout, Lamarr provides analysis-level quantities by applying a pipeline of machine learning-based modules that properly transforms the information resulting from physics generators. Good agreement is observed by comparing key reconstructed quantities obtained with Lamarr against those from the existing detailed Geant4-based simulation. Lamarr has been designated with dual capabilities: it can function as a stand-alone simulation framework, while also being seamlessly integrated into the LHCb simulation software.

Optimization of the Accelerator Control by Reinforcement Learning: A Simulation-Based Approach

2025 · ARTICLE · en

Optimizing accelerator control is a critical challenge in experimental particle physics, requiring significant manual effort and resource expenditure. Traditional tuning methods are often time-consuming and reliant on expert input, highlighting the need for more efficient approaches. This study aims to create a simulation-based framework integrated with Reinforcement Learning (RL) to address these challenges. Using \texttt{Elegant} as the simulation backend, we developed a Python wrapper that simplifies the interaction between RL algorithms and accelerator simulations, enabling seamless input management, simulation execution, and output analysis. The proposed RL framework acts as a co-pilot for physicists, offering intelligent suggestions to enhance beamline performance, reduce tuning time, and improve operational efficiency. As a proof of concept, we demonstrate the application of our RL approach to an accelerator control problem and highlight the improvements in efficiency and performance achieved through our methodology. We discuss how the integration of simulation tools with a Python-based RL framework provides a powerful resource for the accelerator physics community, showcasing the potential of machine learning in optimizing complex physical systems.

Application of Physics-Informed Neural Networks for Solving the Inverse Advection-Diffusion Problem to Localize Pollution Sources

2025 · PREPRINT · en

2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

2025 · BOOK · en

Distilling Normalizing Flows

2025 · CHAPTER · en

Explicit density learners are becoming an increasingly popular technique for generative models because of their ability to better model probability distributions. They have advantages over Generative Adversarial Networks due to their ability to perform density estimation and having exact latent-variable inference. This has many advantages, including: being able to simply interpolate, calculate sample likelihood, and analyze the probability distribution. The downside of these models is that they are often more difficult to train and have lower sampling quality. Normalizing flows are explicit density models, that use composable bijective functions to turn an intractable probability function into a tractable one. In this work, we present novel knowledge distillation techniques to increase sampling quality and density estimation of smaller student normalizing flows. We seek to study the capacity of knowledge distillation in Compositional Normalizing Flows to understand the benefits and weaknesses provided by these architectures. Normalizing flows have unique properties that allow for a non-traditional forms of knowledge transfer, where we can transfer that knowledge within intermediate layers. We find that through this distillation, we can make students significantly smaller while making substantial performance gains over a non-distilled student. With smaller models there is a proportionally increased throughput as this is dependent upon the number of bijectors, and thus parameters, in the network.

Global analysis of charm mixing parameters and determination of the CKM angle gamma

2025 · ARTICLE · en

We present an updated global analysis of beauty decays sensitive to the angle γ of the Cabibbo-Kobayashi-Maskawa matrix and of D-meson mixing data in the framework of approximate universality for charm mixing. We extract the fundamental theoretical parameters determining absorptive and dispersive contributions to D meson mixing and CP violation, together with the angle γ. The results for the charm mixing parameters are x12≃x=(0.402±0.044)% and y12≃y=(0.627±0.021)%, while the two CP-violating phases are given by φM2=(1.9±1.6)∘ and φΓ2=(2.7±1.6)∘. The angle γ is found to be γ=(66.0±2.5)∘.