Traditional Simulation Research Articles

A framework for flood inundation extraction based on microwave and optical remote sensing images

IntroductionEffective monitoring and evaluation of floodwaters are essential for disaster prevention and mitigation. The flood inundation range can be obtained by using traditional simulation methods, but these methods still have shortcomings. This work proposes an optimization method for traditional methods.MethodsThis study aims to introduce an effective solution for the rapid and accurate extraction of flood inundation areas, emphasizing the enhancement of extraction speed and dynamic monitoring throughout the flood event. The solution uses a normalized difference water index (NDWI), a refined threshold method, and a filtering process for microwave (radar) images. Sentinel-1 SAR (Synthetic Aperture Radar) and Sentinel-2 MSI (Multi-spectral Image) images served as the primary data sources. The Sentinel-2 images were preprocessed to extract pre-flood water bodies, while the Sentinel-1 SAR images were processed using the proposed filtering method to identify post-flood inundation areas.ResultsThe application and validation of this framework are demonstrated through the case of the 2020 flood event in Tongling, Anhui Province. The framework’s performance was validated through comparison with ground truth data, yielding high kappa accuracies of 98% for optical images and 89% for Synthetic Aperture Radar. The findings highlight the framework’s ability to capture high-accuracy changes in flood inundation areas and to characterize the dynamic process of flood inundation area changes.DiscussionThis study contributes to the field by enhancing the extraction speed and scope of water bodies from SAR images and improving the quality of microwave remote sensing data processing. It offers valuable insights for emergency rapid response and situational awareness in the context of extreme weather events and associated flood disasters.

Localized Heating Assisted Laser Shock Peening without Coating Enhances Mechanical Properties of Ti6Al4V Alloys

Room-temperature laser shock peening without coating (RT-LSPwoC) is the mainstream method for surface strengthening, yet it induces tensile residual stress on the surface during rapid heating and cooling. Warm LSPwoC, combining the benefits of dynamic strain aging and LSPwoC, exhibits higher performance than RT-LSPwoC. However, overall high-temperature is time- and resource-consuming, and it is prone to causing thermal stress relaxation during processing, making it unsuitable for large-scale applications. In this paper, a novel localized heating assisted LSPwoC (LHA-LSPwoC) method, utilizing a continuous wave laser for local heating, is proposed. Additionally, the deep physics-informed neural network model, embedded with physical formulas, is designed for process optimization. It enables rapid and accurate responses for an extensive number of cases (40 cases with an average deviation below 1%), overcoming the drawbacks of traditional numerical simulations that are time-consuming and difficult to efficiently handle numerous cases. Compared to RT-LSPwoC, LHA-LSPwoC samples have higher dislocation density and higher grain refinement, demonstrating higher hardness and residual stress, particularly superior fatigue performance. The mechanism of LHA-LSPwoC is discussed, and thermally coupled finite element simulations and molecular dynamics calculations are conducted to provide theoretical support. The proposed method is cost-effective and flexible, showing outstanding potential for industrial applications.

Spatiotemporal prediction of solidified dendrites based on convolutional long-short-term neural network

The formation and growth of dendrites during the solidification of metals are critical factors influencing material properties. Accurate prediction of dendritic growth morphology and evolution is of great significance for materials science research and industrial applications. Traditional simulation methods, such as the phase-field method, provide high-precision results but are computationally expensive and time-consuming. Recently, with the advancement of deep learning technology, data-driven approaches have shown great potential in materials science. This paper proposes the use of Convolutional Long-Short-Term Memory Network (ConvLSTM) to capture spatiotemporal dependencies for predicting the spatiotemporal evolution of dendritic solidification in materials. By training on historical data of dendritic growth, the ConvLSTM neural network model predicts the future growth morphology of the dendritic microstructure during solidification. The model accurately forecasts the future morphology and appearance of the microstructure. Case studies were conducted using a generated dataset of dendritic solidification simulations, and the results demonstrate that the ConvLSTM model effectively captures the complex dynamic characteristics of dendritic growth and provides high-precision prediction results. This offers new insights for material design and optimization.

Effects of immersive virtual reality simulation–based maternity nursing education: A randomized controlled trial

BackgroundWe investigated the impact of an immersive virtual reality (IVR)-based scenario simulation education program as an alternative to traditional maternity nursing practicums. MethodA simulation maternity nursing class at Wonkwang University in South Korea was conducted with 59 junior nursing students (experimental group = 30, control group = 29). This randomized controlled trial evaluated the effects of the IVR simulation on students’ knowledge, satisfaction, self-efficacy, and confidence in delivering nursing care. We conducted data collection from September 2021 to February 2022. SPSS version 25.0 was used for data analysis. ResultsBoth groups’ most common previous-semester grade was B, followed by A and C. In the experimental group, 17 participants reported high or very high satisfaction, and 12 in the control group reported high satisfaction. The groups showed significant differences in knowledge (p = .024), satisfaction (p < .001), self-efficacy (p = .018), and confidence (p < .001) in normal vaginal delivery nursing care. ConclusionsCompared to traditional simulation, IVR simulation can enhance maternity nursing students’ knowledge, satisfaction, self-efficacy, and confidence.

Proposing a novel organic bench model utilizing vegetable to enhance basic vitiligo surgery skills

This organic model can help develop essential skills required for vitiligo surgery in an affordable and sustainable manner. This study introduces an organic bench model using vegetables to teach and learn vitiligo surgery techniques. By using cucumbers , various techniques of dermabrasion and skin grafting were practiced. The model offers a versatile, cost-effective alternative to traditional simulators, enhancing practical skill acquisition.

Bayesian Inference for Long Memory Stochastic Volatility Models

We explore the application of integrated nested Laplace approximations for the Bayesian estimation of stochastic volatility models characterized by long memory. The logarithmic variance persistence in these models is represented by a Fractional Gaussian Noise process, which we approximate as a linear combination of independent first-order autoregressive processes, lending itself to a Gaussian Markov Random Field representation. Our results from Monte Carlo experiments indicate that this approach exhibits small sample properties akin to those of Markov Chain Monte Carlo estimators. Additionally, it offers the advantages of reduced computational complexity and the mitigation of posterior convergence issues. We employ this methodology to estimate volatility dependency patterns for both the SP&amp;500 index and major cryptocurrencies. We thoroughly assess the in-sample fit and extend our analysis to the construction of out-of-sample forecasts. Furthermore, we propose multi-factor extensions and apply this method to estimate volatility measurements from high-frequency data, underscoring its exceptional computational efficiency. Our simulation results demonstrate that the INLA methodology achieves comparable accuracy to traditional MCMC methods for estimating latent parameters and volatilities in LMSV models. The proposed model extensions show strong in-sample fit and out-of-sample forecast performance, highlighting the versatility of the INLA approach. This method is particularly advantageous in high-frequency contexts, where the computational demands of traditional posterior simulations are often prohibitive.

Recent Trends in Proxy Model Development for Well Placement Optimization Employing Machine Learning Techniques

Well placement optimization refers to the identification of optimal locations for wells (producers and injectors) to maximize net present value (NPV) and oil recovery. It is a complex challenge in all phases of production (primary, secondary and tertiary) of a reservoir. Reservoir simulation is primarily used to solve this intricate task by analyzing numerous scenarios with varied well locations to determine the optimum location that maximizes the targeted objective functions (e.g., NPV and oil recovery). Proxy models are a computationally less expensive alternative to traditional reservoir simulation techniques since they approximate complex simulations with simpler models. Previous review papers have focused on analyzing various optimization algorithms and techniques for well placement. This article explores various types of proxy models that are the most suitable for well placement optimization due their discrete and nonlinear natures and focuses on recent advances in the area. Proxy models in this article are sub-divided into two primary classes, namely data-driven models and reduced order models (ROMs). The data-driven models include statistical- and machine learning (ML)-based approximations of nonlinear problems. The second class, i.e., a ROM, uses proper orthogonal decomposition (POD) methods to reduce the dimensionality of the problem. This paper introduces various subcategories within these two proxy model classes and presents the successful applications from the well placement optimization literature. Finally, the potential of integrating a data-driven approach with ROM techniques to develop more computationally efficient proxy models for well placement optimization is also discussed. This article is intended to serve as a comprehensive review of the latest proxy model techniques for the well placement optimization problem. In conclusion, while proxy models have their own challenges, their ability to significantly reduce the complexity of the well placement optimization process for huge reservoir simulation areas makes them extremely appealing. With active research and development occurring in this area, proxy models are poised to play an increasingly central role in oil and gas well placement optimization.

TPepPro: a deep learning model for predicting peptide-protein interactions.

Peptides and their derivatives hold potential as therapeutic agents. The rising interest in developing peptide drugs is evidenced by increasing approval rates by the FDA of USA. To identify the most potential peptides, study on peptide-protein interactions presents a very important approach but poses considerable technical challenges. In experimental aspects, the transient nature of peptide-protein interactions (PepPIs) and the high flexibility of peptides contribute to elevated costs and inefficiency. Traditional docking and molecular dynamics simulation methods require substantial computational resources, and the predictive accuracy of their results remain unsatisfactory. To address this gap, we proposed TPepPro, a Transformer-based model for PepPI prediction. We trained TPepPro on a dataset of 19,187 pairs of peptide-protein complexes with both sequential and structural features. TPepPro utilizes a strategy that combines local protein sequence feature extraction with global protein structure feature extraction. Moreover, TPepPro optimizes the architecture of structural featuring neural network in BN-ReLU arrangement, which notably reduced the amount of computing resources required for peptide-protein interactions prediction. According to comparison analysis, the accuracy reached 0.855 in TPepPro, achieving an 8.1% improvement compared to the second-best model TAGPPI. TPepPro achieved an AUC of 0.922, surpassing the second-best model TAGPPI with 0.844. Moreover, the newly developed TPepPro identify certain PepPIs that can be validated according to previous experimental evidence, thus indicating the efficiency of TPepPro to detect high potential PepPIs that would be helpful for amino acid drug applications. The source code of TPepPro is available at https://github.com/wanglabhku/TPepPro. Supplementary data are available at Bioinformatics online.\.

Drone Photogrammetry-based Wind Field Simulation for Climate Adaptation in Urban Environments

Addressing climate change issues is one of the most important tasks within the United Nations Sustainable Development Goals. Accurate and efficient simulation of wind fields within cities is essential for climate adaptation. Traditional simplified geometric model-based wind flow simulation can lead to significant errors, affecting the ability to develop effective urban climate strategies. This study addresses this limitation by introducing a novel workflow that leverages drone photogrammetry, deep learning, and geometric complexity quantification to create highly detailed 3D models of in-use building clusters within cities. These models are subsequently used for computational fluid dynamics simulations to accurately predict urban wind fields. The proposed method was validated on three real-world building clusters. Compared to traditional footprint extrusion models, the proposed method demonstrates an average error reduction of 29.2% in large eddy simulation cases and 17.6% in steady Reynolds-averaged Navier-Stokes equations cases. Meanwhile, the proposed model improved computational efficiency by an average of 33.7% in large eddy simulations compared to the flashy oblique photography model. The proposed method provides a balanced model of accuracy and efficiency for urban flow simulations. It has the potential to be incorporated into computational fluid dynamics best practice guidelines, thereby promoting the development of climate-resilient cities.

Optoelectronic performance prediction of HgCdTe homojunction photodetector in long wave infrared spectral region using traditional simulations and machine learning models

This research explores the design of an infrared (IR) photodetector using mercury cadmium telluride (Hg1–xCdxTe). It proposes two- and three-dimensional homojunction models based on p+-Hg0.7783Cd0.2217Te/n–-Hg0.7783Cd0.2217Te, focusing on applications in the long-wavelength infrared range. The photodetector’s performance is analyzed using Silvaco ATLAS TCAD software and compared with analytical calculations based on drift-diffusion, tunneling, and Chu’s approximation techniques. Optimized for operation at 10.6 μm wavelength under liquid nitrogen temperature, the proposed photodetector demonstrates promising optoelectronic characteristics including the dark current density of 0.20 mA/cm2, photocurrent density of 4.98 A/cm2, and photocurrent density-to-dark current density ratio of 2.46 × 104, a 3-dB cut-off frequency of 104 GHz, a rise time of 0.8 ps, quantum efficiency of 58.30 %, peak photocurrent responsivity of 4.98 A/W, specific detectivity of 3.96 × 1011 cmHz1/2/W, and noise equivalent power of 2.52 × 10–16 W/Hz1/2 indicating its potential for low-noise, high-frequency and fast-switching applications. The study also incorporates machine learning regression models to validate simulation results and provide a predictive framework for performance optimization, evaluating these models using various statistical metrics. This comprehensive approach demonstrates the synergy between advanced materials science and computational techniques in developing next-generation optoelectronic devices. By combining theoretical modeling, simulation, and machine learning, the research highlights the potential to accelerate progress in IR detection technology and enhance device performance and efficiency. This multidisciplinary methodology could serve as a model for future studies in optoelectronics, illustrating how advanced materials and computational methods can be utilized to enhance device capabilities.

Optimization method for predicting coal reservoir fractures in the Laochang area of Eastern Yunnan using paleotectonic stress inversion

IntroductionCoal reservoir fractures serve as critical storage spaces and migration pathways for coalbed methane (CBM), significantly influencing CBM enrichment. The characteristics of coal reservoir fracture development can be obtained using traditional simulation methods, but these still have shortcomings. This work presents an optimization approach for the traditional method.MethodsThis study introduces an optimization approach for traditional methods with two novel contributions. This study integrates the simulation of tectonic stress fields with fracture prediction, using surface sandstone fractures as constraints to reconstruct the paleostress field of the coal seam, while also accounting for the influence of coal thickness on fracture development to calculate fracture density.ResultsThe predicted fracture density results were validated against measured values from the Bailongshan mine and Xiongdong coal mine with a relative error of approximately 12%, suggesting a reasonable degree of reliability.DiscussionBased on the results of the fracture simulation predictions, it is believed that the coal seam fracture density in the study area is mostly 10–20 lines/m and that the sweet spot for CBM development is located in the Yuwang block.

Prediction of Temperature Distribution on an Aircraft Hot-Air Anti-Icing Surface by ROM and Neural Networks

To address the inefficiencies and time-consuming nature of traditional hot-air anti-icing system designs, reduced-order models (ROMs) and machine learning techniques are introduced to predict anti-icing surface temperature distributions. Two models, AlexNet combined with Proper Orthogonal Decomposition (POD-AlexNet) and multi-CNNs with GRU (MCG), are proposed by comparing several classic neural networks. Design variables of the hot-air anti-icing cavity are used as inputs of the two models, and the corresponding surface temperature distribution data serve as outputs, and then the performance of these models is evaluated on the test set. The POD-AlexNet model achieves a mean prediction accuracy of over 95%, while the MCG model reaches 96.97%. Furthermore, the proposed model demonstrates a prediction time of no more than 5.5 ms for individual temperature samples. The proposed models not only provide faster predictions of anti-icing surface temperature distributions than traditional numerical simulation methods but also ensure acceptable accuracy, which supports the design of aircraft hot-air anti-icing systems based on optimization methods such as genetic algorithms.

Calculating linear and nonlinear multi-ensemble slow collective variables for protein folding.

Traditional molecular dynamics simulation of biomolecules suffers from the conformational sampling problem. It is often difficult to produce enough valid data for post analysis such as free energy calculation and transition path construction. To improve the sampling, one practical solution is putting an adaptive bias potential on some predefined collective variables. The quality of collective variables strongly affects the sampling ability of a molecule in the simulation. In the past, collective variables were built with the sampling data at a constant temperature. This is insufficient because of the same sampling problem. In this work, we apply the standard weighted histogram analysis method to calculate the multi-ensemble averages of pairs of time-lagged features for the construction of both linear and nonlinear slow collective variables. Compared to previous single-ensemble methods, the presented method produces averages with much smaller statistical uncertainties. The generated collective variables help a peptide and a miniprotein fold to their near-native states in a short simulation time period. By using the method, enhanced sampling simulations could be more effective and productive.

Atomistic Modeling of Natural Gas Desulfurization Process Using Task-Specific Deep Eutectic Solvents Supported by Graphene Oxide.

This study employs Density Functional Theory (DFT) calculations and traditional all-atom Molecular Dynamics (MD) simulations to reveal atomistic insights into a task-specific Deep Eutectic Solvent (DES) supported by graphene oxide with the aim of mimicking its application in the natural gas desulfurization process. The DES, composed of N,N,N',N'-tetramthyl-1,6-hexane diamine acetate (TMHDAAc) and methyldiethanolamine (MDEA) supported by graphene oxide, demonstrates improved efficiency in removing hydrogen sulfide from methane. Optimized structure and HOMO-LUMO orbital analyses reveal the distinct spatial arrangements and interactions between hydrogen sulfide, methane, and DES components, highlighting the efficacy of the DES in facilitating the separation of hydrogen sulfide from methane through DFT calculations. The radial distribution function (RDF) and interaction energies, as determined by traditional all-atom MD simulations, provide insights into the specificity and strength of the interactions between the DES components supported by graphene oxide and hydrogen sulfide. Importantly, the stability of the DES structure supported by graphene oxide is maintained after mixing with the fuel, ensuring its robustness and suitability for prolonged desulfurization processes, as evidenced by traditional all-atom MD simulation results. These findings offer crucial insights into the molecular-level mechanisms underlying the desulfurization of natural gas, guiding the design and optimization of task-specific DESs supported by graphene oxide for sustainable and efficient natural gas purification.

Three-Dimensional Micromechanical Simulation and Evaluation of High-Toughness Ultra-Thin Friction Course with X-Ray Computed Tomography

As a novel pavement wear layer material, the micromechanical mechanisms of High-toughness Ultra-thin Friction Course (HUFC) have not been fully elucidated. This paper presents a new method for the three-dimensional micromechanical simulation of high-toughness asphalt mixtures based on a viscoelastic parameter calibration model. X-ray Computerized Tomography (CT) was employed to scan samples of high-toughness asphalt mixtures to obtain detailed information on the internal structure (aggregate, fine aggregate matrix FAM and voids), and a three-dimensional micromechanical model was constructed based on the real-scale distribution of these components. Aggregates in the high-toughness asphalt mixture were modeled as elastic bodies, while FAM was treated as a viscoelastic material characterized by the Burgers model. Using the Boltzmann linear superposition principle and Laplace transform theory, the viscoelastic properties of FAM were converted into Prony parameters recognizable by finite element software, and the viscoelastic parameters were calibrated. Micromechanical simulations were conducted for three different gradings of high-toughness asphalt mixtures, and the results show that the predicted deformation closely matched the measured deformation. This method accurately reflects the deformation characteristics of different gradings of high-toughness asphalt mixtures, overcoming the limitations of traditional numerical simulations based on homogeneous material models. It represents an advancement and refinement of micromechanical simulation methods for high-toughness asphalt mixtures.

Bus Network Adjustment Pre-Evaluation Based on Biometric Recognition and Travel Spatio-Temporal Deduction

A critical component of bus network adjustment is the accurate prediction of potential risks, such as the likelihood of complaints from passengers. Traditional simulation methods, however, face limitations in identifying passengers and understanding how their travel patterns may change. To address this issue, a pre-evaluation method has been developed, leveraging the spatial distribution of bus networks and the spatio-temporal behavior of passengers. The method includes stage of travel demand analysis, accessible path set calculation, passenger assignment, and evaluation of key indicators. First, we explore the actual passengers’ origin and destination (OD) stop from bus card (or passenger Code) payment data and biometric recognition data, with the OD as one of the main input parameters. Second, a digital bus network model is constructed to represent the logical and spatial relationships between routes and stops. Upon inputting bus line adjustment parameters, these relationships allow for the precise and automatic identification of the affected areas, as well as the calculation of accessible paths of each OD pair. Third, the factors influencing passengers’ path selection are analyzed, and a predictive model is built to estimate post-adjustment path choices. A genetic algorithm is employed to optimize the model’s weights. Finally, various metrics, such as changes in travel routes and ride times, are analyzed by integrating passenger profiles. The proposed method was tested on the case of the Guangzhou 543 route adjustment. Results show that the accuracy of the number of predicted trips after adjustment is 89.6%, and the predicted flow of each associated bus line is also consistent with the actual situation. The main reason for the error is that the path selection has a certain level of irrationality, which stems from the fact that the proportion of passengers who choose the minimum cost path for direct travel is about 65%, while the proportion of one-transfer passengers is only about 50%. Overall, the proposed algorithm can quantitatively analyze the impact of rigid travel groups, occasional travel groups, elderly groups, and other groups that are prone to making complaints in response to bus line adjustment.

Accelerating Numerical Simulations of CO2 Geological Storage in Deep Saline Aquifers via Machine-Learning-Driven Grid Block Classification

The accurate prediction of pressure and saturation distribution during the simulation of CO2 injection into saline aquifers is essential for the successful implementation of carbon sequestration projects. Traditional numerical simulations, while reliable, are computationally expensive. Machine learning (ML) has emerged as a promising tool to accelerate these simulations; however, challenges remain in effectively capturing complex reservoir dynamics, particularly in regions experiencing rapid changes in pressure and saturation. This article addresses the challenges by introducing a fully automated, data-driven ML classifier that distinguishes between regions of fast and slow variation within the reservoir. Firstly, we demonstrate the variability in pressure across different reservoir grid blocks using a simple brine injection and production scenario, highlighting the limitations of conventional acceleration approaches. Subsequently, the proposed methodology leverages ML proxies to rapidly and accurately predict the behavior of slow-varying regions in CO2 injection simulations, while traditional iterative methods are reserved for fast-varying areas. The results show that this hybrid approach significantly reduces the computational load without compromising on accuracy. This provides a more efficient and scalable solution for modeling CO2 storage in saline aquifers.

Cold Gas Subgrid Model (CGSM): a two-fluid framework for modelling unresolved cold gas in galaxy simulations

ABSTRACT The cold ($\sim 10^{4}\, {\rm K}$) component of the circumgalactic medium (CGM) accounts for a significant fraction of all galactic baryons. However, using current galaxy-scale simulations to determine the origin and evolution of cold CGM gas poses a significant challenge, since it is computationally infeasible to directly simulate a galactic halo alongside the sub-pc scales that are crucial for understanding the interactions between cold CGM gas and the surrounding ‘hot’ medium. In this work, we introduce a new approach: the Cold Gas Subgrid Model (CGSM), which models unresolved cold gas as a second fluid in addition to the standard ‘normal’ gas fluid. The CGSM tracks the total mass density and bulk momentum of unresolved cold gas, deriving the properties of its unresolved cloudlets from the resolved gas phase. The interactions between the subgrid cold fluid and the resolved fluid are modelled by prescriptions from high-resolution simulations of ‘cloud crushing’ and thermal instability. Through a series of idealized tests, we demonstrate the CGSM’s ability to overcome the resolution limitations of traditional hydrodynamics simulations, successfully capturing the correct cold gas mass, its spatial distribution, and the time-scales for cloud destruction and growth. We discuss the implications of using this model in cosmological simulations to more accurately represent the microphysics that govern the galactic baryon cycle.

Utilizing machine learning and molecular dynamics for enhanced drug delivery in nanoparticle systems

Materials data science and machine learning (ML) are pivotal in advancing cancer treatment strategies beyond traditional methods like chemotherapy. Nanotherapeutics, which merge nanotechnology with targeted drug delivery, exemplify this advancement by offering improved precision and reduced side effects in cancer therapy. The development of these nanotherapeutic agents depends critically on understanding nanoparticle (NP) properties and their biological interactions, often analyzed through molecular dynamics (MD) simulations. This study enhances these analyses by integrating ML with MD simulations, significantly improving both prediction accuracy and computational efficiency. We introduce a comprehensive three-stage methodology for predicting the solvent-accessible surface area (SASA) of NPs, which is crucial for their therapeutic efficacy. The process involves training an ML model to forecast the many-body tensor representation (MBTR) for future time steps, applying data augmentation to increase dataset realism, and refining the SASA predictor with both augmented and original data. Results demonstrate that our methodology can predict SASA values 299 time steps ahead with a 40-fold speed improvement and a 25% accuracy increase over existing methods. Importantly, it provides a 300-fold increase in computational speed compared to traditional simulation techniques, offering substantial cost and time savings for nanotherapeutic research and development.

Fast prediction of compressor flow field based on a deep attention symmetrical neural network

Accurate and rapid prediction of compressor performance and key flow characteristics is critical for digital design, digital twin modeling, and virtual–real interaction. However, the traditional methods of obtaining flow field parameters by solving the Navier–Stokes equations are computationally intensive and time-consuming. To establish a digital twin model of the flow field in a transonic three-stage axial compressor, this study proposes a novel data-driven deep attention symmetric neural network for fast reconstruction of the flow field at different blade rows and spanwise positions. The network integrates a vision transformer (ViT) and a symmetric convolutional neural network (SCNN). The ViT extracts geometric features from the blade passages. The SCNN is used for deeper extraction of input features such as boundary conditions and flow coordinates, enabling precise flow field predictions. Results indicate that the trained model can efficiently and accurately reconstruct the internal flow field of the compressor in 0.5 s, capturing phenomena such as flow separation and wake. Compared with traditional numerical simulations, the current model offers significant advantages in computational speed, delivering a three-order magnitude speedup compared to computational fluid dynamics simulations. It shows strong potential for engineering applications and provides robust support for building digital twin models in turbomachinery flow fields.