A. V. Plotnikov, D. A. Oleynik, L. R. Romanychev, N. V. Greben
{"title":"Workflow Management System for SPD Online Filter","authors":"A. V. Plotnikov, D. A. Oleynik, L. R. Romanychev, N. V. Greben","doi":"10.1134/S1063779626700395","DOIUrl":"10.1134/S1063779626700395","url":null,"abstract":"<p>The article demonstrates the implementation of the Workflow Management System (WfMS) for the high-performance computing system for primary processing of SPD physical experiment data—SPD Online Filter. The capabilities of each WfMS microservice are shown and the key points of the system creation are identified. The paper also defines further plans for upgrading the system.</p>","PeriodicalId":729,"journal":{"name":"Physics of Particles and Nuclei","volume":"57 4","pages":"645 - 647"},"PeriodicalIF":0.5,"publicationDate":"2026-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148496711","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Using Federated Learning to Solve the Problem of Determining Coastlines on Satellite Images","authors":"I. I. Kurochkin, D. S. Matyash, A. I. Prun","doi":"10.1134/S1063779626700231","DOIUrl":"10.1134/S1063779626700231","url":null,"abstract":"<p>The task of determining the coastline from satellite images is reduced to the task of segmentation. DeepResUnet and TransUnet deep neural network models were selected. Landsat8 with images of rivers and bays in Russia was chosen as the dataset. Computational experiments were conducted to train two models on one node (deep learning), on multiple nodes (distributed deep learning and federated learning). The results of solving the problem of determining the coastline both on a single node and on a distributed system are presented. For experiments on federated learning, various methods of data separation between nodes of a distributed system have been identified. Data separation between nodes is proposed, both according to the geographical location of the satellite image and randomly. A comparative analysis of the results of federated learning with various methods of data distribution is discussed.</p>","PeriodicalId":729,"journal":{"name":"Physics of Particles and Nuclei","volume":"57 4","pages":"597 - 599"},"PeriodicalIF":0.5,"publicationDate":"2026-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148496664","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yu. N. Skulskiy, E. N. Cheremisina, E. F. Kirov, E. Yu. Kirpicheva, E. M. Mazhitova, Yu. Yu. Medvedeva, A. V. Nechaevsky, S. V. Potemkina, D. S. Sidorov, N. A. Tokareva
{"title":"Adaptive Automated Response System for Virtual Computer Lab and LMS Moodle Using LLM, RAG, and Serverless Architecture","authors":"Yu. N. Skulskiy, E. N. Cheremisina, E. F. Kirov, E. Yu. Kirpicheva, E. M. Mazhitova, Yu. Yu. Medvedeva, A. V. Nechaevsky, S. V. Potemkina, D. S. Sidorov, N. A. Tokareva","doi":"10.1134/S1063779626700176","DOIUrl":"10.1134/S1063779626700176","url":null,"abstract":"<p>An adaptive automated response system for Virtual Computer Lab and LMS Moodle is presented, leveraging Retrieval-Augmented Generation (RAG), a fine-tuned Llama (or Gemma, Qwen, etc.) model, and serverless architecture. Integrated with Moodle and Supabase, it delivers context-aware responses tailored to user roles (student, instructor, administrator). A self-learning mechanism driven by feedback enhances response accuracy and reducing technical support workload. An interactive interface with custom widgets improves user experience.</p>","PeriodicalId":729,"journal":{"name":"Physics of Particles and Nuclei","volume":"57 4","pages":"578 - 580"},"PeriodicalIF":0.5,"publicationDate":"2026-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148496635","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
E. I. Alexandrov, I. N. Alexandrov, D. Barberis, A. V. Yakovlev
{"title":"Methods for Automating Error Handling in the Event Picking Service of the ATLAS Experiment","authors":"E. I. Alexandrov, I. N. Alexandrov, D. Barberis, A. V. Yakovlev","doi":"10.1134/S1063779626700309","DOIUrl":"10.1134/S1063779626700309","url":null,"abstract":"<p>The ATLAS EventIndex is the complete catalogue of all ATLAS real and simulated events, keeping the references to all permanent files that contain a given event in any processing stage. The Event Picking Service (EPS) automates the procedure of finding the locations of large numbers of events, extracting and collecting them into separate files. It supports different formats of events and has an elastic workflow for different input data. This article describes the different types of errors that occur while performing different workflows and threads. It also describes methods for automating the processing of such errors to ensure the stability and uninterrupted operation of the service.</p>","PeriodicalId":729,"journal":{"name":"Physics of Particles and Nuclei","volume":"57 4","pages":"619 - 621"},"PeriodicalIF":0.5,"publicationDate":"2026-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148496666","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Strategies for Multidisciplinary Workflow Scheduling and Resource Management in Cloud Computing","authors":"V. V. Toporkov, D. M. Yemelyanov, A. N. Bulkhak","doi":"10.1134/S1063779626700073","DOIUrl":"10.1134/S1063779626700073","url":null,"abstract":"<p>In this work, we propose and investigate multifactor strategies for managing the execution and scheduling of knowledge-intensive applications such as CyberShake, Epigenomics, SIPHT, Montage, LIGO, on cloud platforms “Workflow as a Service” (WaaS). A comprehensive solution to the problem of running applications in the WaaS model is considered using various criteria and optimization scenarios based on a cyclic scheme. The proposed scheme allows supporting a set of technologies and management tools for the execution of interdisciplinary knowledge-intensive applications on WaaS platforms.</p>","PeriodicalId":729,"journal":{"name":"Physics of Particles and Nuclei","volume":"57 4","pages":"544 - 548"},"PeriodicalIF":0.5,"publicationDate":"2026-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148496670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Sh. Petrosyan, A. K. Kiryanov, D. A. Oleynik, A. S. Konak, N. G. Monakov, F. V. Shuvalov
{"title":"SPD Offline Computing Software Architecture and Current Status","authors":"A. Sh. Petrosyan, A. K. Kiryanov, D. A. Oleynik, A. S. Konak, N. G. Monakov, F. V. Shuvalov","doi":"10.1134/S1063779626700310","DOIUrl":"10.1134/S1063779626700310","url":null,"abstract":"<p>In order to meet the needs of the physical groups of the SPD experiment, which is under construction at JINR, a set of systems and services is being developed that ensure the orderly storage and processing of experimental data both on JINR resources and on the resources of institutes belonging to the SPD collaboration, and, in general, form a distributed computing environment for the experiment. The distributed computing environment is in trial operation, but full-fledged data processing chains are already running in it.</p>","PeriodicalId":729,"journal":{"name":"Physics of Particles and Nuclei","volume":"57 4","pages":"622 - 623"},"PeriodicalIF":0.5,"publicationDate":"2026-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148496720","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Anticipating Data Demand in HEP: A Transformer Approach","authors":"M. A. Grigorieva, N. N. Popova, M. V. Shubin","doi":"10.1134/S1063779626700450","DOIUrl":"10.1134/S1063779626700450","url":null,"abstract":"<p>Modern high-energy physics (HEP) experiments generate and store vast volumes of data, which users access through complex and irregular patterns. Efficient data management in such environments requires accurate forecasting of dataset popularity to optimize storage, caching, and data distribution strategies. In this work, we propose an approach for predicting future dataset access patterns using transformer-based deep learning models. By leveraging historical logs of user interactions with HEP datasets, our method captures temporal dependences and contextual signals to forecast both short- and medium-term data demand.</p>","PeriodicalId":729,"journal":{"name":"Physics of Particles and Nuclei","volume":"57 4","pages":"665 - 667"},"PeriodicalIF":0.5,"publicationDate":"2026-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148496573","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
E. I. Alexandrov, I. N. Alexandrov, A. I. Chebotov, I. A. Filozova, K. V. Gertsenberger, N. A. Ilin, A. A. Moshkin, I. S. Pelevanyuk, I. A. Romanov, G. V. Shestakova
{"title":"Software Complex for Distributed Data Processing during Run 9 of the BM@N Experiment","authors":"E. I. Alexandrov, I. N. Alexandrov, A. I. Chebotov, I. A. Filozova, K. V. Gertsenberger, N. A. Ilin, A. A. Moshkin, I. S. Pelevanyuk, I. A. Romanov, G. V. Shestakova","doi":"10.1134/S1063779626700024","DOIUrl":"10.1134/S1063779626700024","url":null,"abstract":"<p>Modern physics experiments on particle collisions cannot operate without sophisticated software used at all stages of the work, including the design of the setup, control of the operation of the subsystems, data collection, online and offline processing, and physics analysis. This also holds true for the fixed target experiment, BM@N, operating and taking data at the NICA complex in JINR. Since 2015, eight BM@N Runs, including the latest, physics one, have been conducted, and Run 9 with xenon ion beams is scheduled in the coming months. The paper presents a set of software systems and services developed to automate data processing and storing on distributed platforms during BM@N Run 9. The computing software necessary for the event data processing is also noted.</p>","PeriodicalId":729,"journal":{"name":"Physics of Particles and Nuclei","volume":"57 4","pages":"522 - 526"},"PeriodicalIF":0.5,"publicationDate":"2026-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148496628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Distributed Computing Infrastructure for the SPD Experiment","authors":"A. K. Kiryanov, D. A. Oleynik, A. Sh. Petrosyan","doi":"10.1134/S1063779626700103","DOIUrl":"10.1134/S1063779626700103","url":null,"abstract":"<p>The SPD experiment at the NICA collider involves not only the processing of multiple petabytes of data per year obtained from the detector, but also the production of similar amounts of data as part of the modeling of physical processes and expected signals from the front-end electronics. Because of this, the SPD experiment relies heavily on distributed computing for offline data storage and processing. This article provides the preliminary steps to build a distributed computing infrastructure for the SPD experiment, including the network backbone, storage and computing facilities at participating parties, their software components and configuration along with some higher-level software components necessary for the smooth operation of such infrastructure.</p>","PeriodicalId":729,"journal":{"name":"Physics of Particles and Nuclei","volume":"57 4","pages":"557 - 559"},"PeriodicalIF":0.5,"publicationDate":"2026-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148496629","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
E. I. Alexandrov, I. N. Alexandrov, A. I. Chebotov, K. V. Gertsenberger
{"title":"Design of the Data Quality Monitoring System for the BM@N Experiment","authors":"E. I. Alexandrov, I. N. Alexandrov, A. I. Chebotov, K. V. Gertsenberger","doi":"10.1134/S1063779626700280","DOIUrl":"10.1134/S1063779626700280","url":null,"abstract":"<p>The paper presents the design of the Data Quality Monitoring (DQM) system for the BM@N experiment of the NICA project, including a description of the system’s objectives, a brief overview of similar systems that operate in the CERN LHC experiments, and general approaches to creating the systems. The system architecture, object model, and database scheme are presented, and the structure of the configuration files that will be used for fine-tuning the work of the DQM is described.</p>","PeriodicalId":729,"journal":{"name":"Physics of Particles and Nuclei","volume":"57 4","pages":"612 - 615"},"PeriodicalIF":0.5,"publicationDate":"2026-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148496631","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}