All issues

The paper presents a cascade model of a physically supported neural network designed to predict pressure drop in three-phase flow (oil, gas, water) in a pipe section with various angles of inclination. To overcome the constraints of existing empirical correlations and computation-intensive numerical modeling methods, we propose an architecture that decomposes the problem into three sequential physically interpretable subtasks: regression prediction of the fluid hold-up coefficient, fluid flow regime classification, and pressure gradient evaluation. Each subtask is solved by a separate fully connected neural network, the output of which is passed to the next model in the cascade. Training and testing of the proposed architecture was performed on an extensive synthetic dataset (8 · 10⁷ records) generated using a semi-empirical model. Verification is performed on independent experimental data. A comparative analysis with a single fully connected (non-cascade) neural network is made, and the sensitivity of the models is examined using Sobol and Borgonovo methods. The cascade model demonstrates superior accuracy and ensures high interpretability of results by providing intermediate physical parameters (fluid hold-up coefficient, flow regime). The developed model has low computational complexity, which allows it to be used in real-time systems and digital twins of hydraulic systems in the oil and gas industry.

The SAS program is the primary data processing tool for the YuMO small-angle neutron scattering spectrometer. The paper presents a retrospective analysis of its two-decade evolution, from a Fortran prototype to a modern software system. The analysis focuses on the architectural decisions that have ensured the program’s long-term viability and its ability to adapt to instrument upgrades.

The core solution was a modular architecture that abstracts the detector system. This enabled the seamless integration of data from two scattering detectors and, later, from a position-sensitive detector. A strict processing pipeline and a unified internal data representation formed the basis for physically grounded algorithms, including weighted merging of spectra, resolution-aware smoothing, and built-in statistical quality control. The program’s interfaces—a command line for batch processing and a graphical user interface for interactive work—are built upon a single computational core, ensuring result consistency and flexibility in use.

Long-term operation has confirmed that the underlying architectural principles naturally align with the key characteristics of international software quality standards, particularly those critical for long-term sustainability. Therefore, the development and evolution of SAS demonstrates a universal set of architectural principles that can serve as a foundation for building sustainable scientific software in related fields of experimental physics.

The short-term prediction of road traffic condition is one of the main tasks of transportation modelling. The main purpose of which are traffic control, reporting of accidents, avoiding traffic jams due to knowledge of traffic flow and subsequent transportation planning. A number of solutions exist — both model-driven and data driven had proven to be successful in capturing the dynamics of traffic flow. Nevertheless, most space-time models suffer from high mathematical complexity and low efficiency. Artificial Neural Networks, one of the prominent datadriven approaches, show promising performance in modelling the complexity of traffic flow. We present a neural network architecture for traffic flow prediction on a real-world road network graph. The model is based on the combination of a recurrent neural network and graph convolutional neural network. Where a recurrent neural network is used to model temporal dependencies, and a convolutional neural network is responsible for extracting spatial features from traffic. To make multiple few steps ahead predictions, the encoder-decoder architecture is used, which allows to reduce noise propagation due to inexact predictions. To model the complexity of traffic flow, we employ multilayered architecture. Deeper neural networks are more difficult to train. To speed up the training process, we use skip-connections between each layer, so that each layer teaches only the residual function with respect to the previous layer outputs. The resulting neural network was trained on raw data from traffic flow detectors from the US highway system with a resolution of 5 minutes. 3 metrics: mean absolute error, mean relative error, mean-square error were used to estimate the quality of the prediction. It was found that for all metrics the proposed model achieved lower prediction error than previously published models, such as Vector Auto Regression, LSTM and Graph Convolution GRU.

The reconstruction of charged particle trajectories in tracking detectors is a key problem in the analysis of experimental data for high energy and nuclear physics.

The amount of data in modern experiments is so large that classical tracking methods such as Kalman filter can not process them fast enough. To solve this problem, we have developed two neural network algorithms of track recognition, based on deep learning architectures, for local (track by track) and global (all tracks in an event) tracking in the GEM tracker of the BM@N experiment at JINR (Dubna). The advantage of deep neural networks is the ability to detect hidden nonlinear dependencies in data and the capability of parallel execution of underlying linear algebra operations.

In this work we generalize these algorithms to the cylindrical GEM inner tracker of BESIII experiment. The neural network model RDGraphNet for global track finding, based on the reverse directed graph, has been successfully adapted. After training on Monte Carlo data, testing showed encouraging results: recall of 98% and precision of 86% for track finding.

The local neural network model TrackNETv2 was also adapted to BESIII CGEM successfully. Since the tracker has only three detecting layers, an additional neuro-classifier to filter out false tracks have been introduced. Preliminary tests demonstrated the recall value at the first stage of 99%. After applying the neuro-classifier, the precision was 77% with a slight decrease of the recall to 94%. This result can be improved after the further model optimization.

We suggested some approaches for solving image processing tasks in the decision support system (DSS) of the Center for Automated Recording of Administrative Offenses of the Road Traffic (CARAO). The main task of this system is to assist the operator in obtaining accurate information about the vehicle registration plate and the vehicle brand/model based on images obtained from the photo and video recording systems. We suggested the approach for vehicle registration plate recognition and brand/model classification on the images based on modern neural network models. LPRNet neural network model supplemented by Spatial Transformer Layer was used to recognize the vehicle registration plate. The ResNeXt-101-32x8d neural network model was used to classify for vehicle brand/model. We suggested the approach to construct the training set for the neural network of vehicle registration plate recognition. The approach is based on computer vision methods and machine learning algorithms. The SIFT algorithm was used to detect and describe local features on images with the vehicle registration plate. DBSCAN clustering was used to detect and delete outliers in such local features. The accuracy of vehicle registration plate recognition was 96% on the testing set. We suggested the approach to improve the efficiency of using the ResNeXt-101-32x8d model at additional training and classification stages. The approach is based on the new architecture of convolutional neural networks with “freezing” weight coefficients of convolutional layers, an additional convolutional layer for parallelizing the classification process, and a set of binary classifiers at the output. This approach significantly reduced the time of additional training of neural network when new vehicle brand/model classification was needed. The final accuracy of vehicle brand/model classification was 99% on the testing set. The proposed approaches were tested and implemented in the DSS of the CARAO of the Republic of Tatarstan.

The article presents a technology for building clinical decision support systems (CDSS) based on service containers using Docker and a web interface that runs directly in the browser without installing specialized software on workstation of a clinician. A modular architecture is proposed in which each application module is packaged as an independent service container combining a lightweight web server, a user interface, and computational components for medical image processing. Communication between the browser and the server side is implemented via a persistent bidirectional WebSocket connection with binary message serialization (MessagePack), which provides low latency and efficient transfer of large data. For local storage of images and analysis of results, browser facilities (IndexedDB with the Dexie.js wrapper) are used to speed up repeated data access. Three-dimensional visualization and basic operations with DICOM data are implemented with Three.js and AMI.js: this toolchain supports the integration of interactive elements arising from the task context (annotations, landmarks, markers, 3D models) into volumetric medical images.

Server components and functional modules are assembled as a set of interacting containers managed by Docker. The paper discusses the choice of base images, approaches to minimizing containers down to runtime-only executables without external utilities, and the organization of multi-stage builds with a dedicated build container. It describes a hub service that launches application containers on user request, performs request proxying, manages sessions, and switches a container from shared to exclusive mode at the start of computations. Examples of application modules are provided (fractional flow reserve estimation, quantitative flow ratio computation, aortic valve closure modeling), along with the integration of a React-based interface with a three-dimensional scene, a versioning policy, automated reproducibility checks, and the deployment procedure on the target platform.

It is demonstrated that containerization ensures portability and reproducibility of the software environment, dependency isolation and scalability, while the browser-based interface provides accessibility, reduced infrastructure requirements, and interactive real-time visualization of medical data. Technical limitations are noted (dependence on versions of visualization libraries and data formats) together with practical mitigation measures.

The numerical methods used to simulate the evolution of hydrodynamic systems require the considerable use of computational resources thus limiting the number of possible simulations. The data-driven simulation technique is one promising approach to the development of heuristic models, which may speed up the study of such models. In this approach, machine learning methods are used to tune the weights of an artificial neural network that predicts the state of a physical system at a given point in time based on initial conditions. This article describes an original neural network architecture and a novel multi-stage training procedure which create a heuristic model of a two-phase flow in a heterogeneous porous medium. The neural network-based model predicts the states of the grid cells at an arbitrary timestep (within the known constraints), taking in only the initial conditions: the properties of the heterogeneous permeability of the medium and the location of sources and sinks. The proposed model requires orders of magnitude less processor time in comparison with the classical numerical method, which served as a criterion for evaluating the effectiveness of the trained model. The proposed architecture includes a number of subnets trained in various combinations on several datasets. The techniques of adversarial training and weight transfer are utilized.

When modeling turbulent flows in practical applications, it is often necessary to carry out a series of calculations of bodies of similar topology. For example, bodies that differ in the shape of the fairing. The use of convolutional neural networks allows to reduce the number of calculations in a series, restoring some of them based on calculations already performed. The paper proposes a method that allows to apply a convolutional neural network regardless of the method of constructing a computational mesh. To do this, the flow field is reinterpolated to a uniform mesh along with the body itself. The geometry of the body is set using the signed distance function and masking. The restoration of the flow field based on part of the calculations for similar geometries is carried out using a neural network of the UNet type with a spatial attention mechanism. The resolution of the nearwall region, which is a critical condition for turbulent modeling, is based on the equations obtained in the nearwall domain decomposition method.

A demonstration of the method is given for the case of a flow around a rounded plate by a turbulent air flow with different rounding at fixed parameters of the incoming flow with the Reynolds number $Re = 10^5$ and the Mach number $M = 0.15$. Since flows with such parameters of the incoming flow can be considered incompressible, only the velocity components are studied directly. The flow fields, velocity and friction profiles obtained by the surrogate model and numerically are compared. The analysis is carried out both on the plate and on the rounding. The simulation results confirm the prospects of the proposed approach. In particular, it was shown that even if the model is used at the maximum permissible limits of its applicability, friction can be obtained with an accuracy of up to 90%. The work also analyzes the constructed architecture of the neural network. The obtained surrogate model is compared with alternative models based on a variational autoencoder or the principal component analysis using radial basis functions. Based on this comparison, the advantages of the proposed method are demonstrated.

Dam safety assessment increasingly relies on continuous monitoring of hydrometeorological variables; however, identifying early-stage instability remains challenging due to complex spatio-temporal interactions and highly imbalanced failure observations. This study proposes a deep learning framework based on a Convolutional Bidirectional Gated Recurrent Unit (CNN–BiGRU) architecture to learn spatio-temporal precursors of dam instability from multivariate hydrometeorological time series. The convolutional component extracts localized temporal patterns associated with short-term fluctuations, while the bidirectional recurrent structure captures long-range dependencies and evolving dynamics preceding critical states.

The proposed model is evaluated on a real-world dam monitoring dataset comprising multiple water-level, meteorological, and derived dynamic indicators. To address class imbalance, a cost-sensitive training strategy using class weighting is adopted without synthetic oversampling. Experimental results demonstrate strong predictive performance, achieving an accuracy of 0.961, precision of 0.901, recall of 0.757, and an F1-score of 0.823. The model further attains a ROC-AUC of 0.907 and a PR-AUC of 0.819, indicating robust discrimination capability under imbalanced conditions.

Feature importance analysis reveals that short- and medium-term water level variability, including rolling standard deviation, volatility, and multi-scale gradients, play a dominant role in characterizing pre-instability behavior, providing physically interpretable insights into dam response dynamics. The findings suggest that the CNN–BiGRU framework effectively captures meaningful spatio-temporal precursors and offers a reliable data-driven tool for supporting dam safety monitoring and decision-making under real operational conditions.

A hybrid cluster implies the use of computational devices with radically different architectures. Usually, these are conventional CPU architecture (e.g. x86_64) and GPU architecture (e. g. NVIDIA CUDA). Creating and exploiting such a cluster requires some experience: in order to harness all computational power of the described system and get substantial speedup for computational tasks many factors should be taken into account. These factors consist of hardware characteristics (e.g. network infrastructure, a type of data storage, GPU architecture) as well as software stack (e.g. MPI implementation, GPGPU libraries). So, in order to run scientific applications GPU capabilities, software features, task size and other factors should be considered.

This report discusses opportunities and problems of hybrid computations. Some statistics from tests programs and applications runs will be demonstrated. The main focus of interest is open source applications (e. g. OpenFOAM) that support GPGPU (with some parts rewritten to use GPGPU directly or by replacing libraries).

There are several approaches to organize heterogeneous computations for different GPU architectures out of which CUDA library and OpenCL framework are compared. CUDA library is becoming quite typical for hybrid systems with NVIDIA cards, but OpenCL offers portability opportunities which can be a determinant factor when choosing framework for development. We also put emphasis on multi-GPU systems that are often used to build hybrid clusters. Calculations were performed on a hybrid cluster of SPbU computing center.