Search Results (233)

Predicting the evolution of microstructure and field quantities under varying processing and loading conditions is a central challenge in computational materials science and metal additive manufacturing (AM). While deep learning (DL) methods offer ultra-fast prediction capabilities post-training, existing models often struggle with poor spatial and temporal extrapolation, high parameter burdens, and an inability to effectively integrate diverse conditioning parameters alongside high-dimensional input fields. To address these bottlenecks, we propose a novel conditional generative adversarial network (CPGAN), which is designed to seamlessly ingest both initial fields and governing condition parameters. The CPGAN framework offers three distinct advantages: (1) it accurately maps the combined effects of initial states and process conditions onto evolved fields; (2) it demonstrates robust extrapolation capabilities across diverse spatial and temporal scales, including the unique ability to natively generate high-resolution rectangular domains; and (3) it achieves superior predictive accuracy and training stability compared to standard convolutional baselines by effectively suppressing spurious artifacts. We validate CPGAN’s performance against rigorous physics-based ground truths across three representative engineering applications: porosity evolution in selective laser sintering (SLS), spatial distribution of 2D von Mises stress fields in solid structures, and the spatiotemporal evolution of grain growth. The results confirm that CPGAN is a highly adaptable and efficient surrogate model, capable of simulating continuous structural and morphological evolutions even when driven by highly non-uniform spatial or temporal kinetics. Full article

In characterizing unconventional reservoirs, conventional Digital Rock Physics (DRP) has long been constrained by three fundamental bottlenecks: the trade-off between imaging resolution and field of view, challenges in reconstructing multiscale pore topology, and the prohibitive computational cost of direct numerical simulation (DNS) at the pore scale. The deep integration of artificial intelligence and rock physics has given rise to a new paradigm—Intelligent Digital Rock Physics (IDRP). This paper provides a systematic review of the evolutionary trajectory of IDRP, with a focus on how machine learning is reshaping the end-to-end workflow from imaging and segmentation to reconstruction and simulation. First, we survey image super-resolution and 3D pore structure generation techniques based on convolutional neural networks (CNNs), generative adversarial networks (GANs), and diffusion models, elucidating their mechanisms for surpassing optical diffraction limits and incorporating macroscopic petrophysical constraints. Second, we outline algorithmic strategies for fusing multi-source heterogeneous data (e.g., Micro-CT and SEM) and representing dual-porosity or multi-continuum systems. Third, we critically examine the application of machine learning surrogates in single- and multiphase flow prediction, highlighting how physics-informed machine learning (PIML) and reinforcement learning (RL)—by embedding governing equations such as Navier–Stokes or Muskat–Leverett into loss functions—achieve both computational acceleration and physical consistency. We further identify key limitations of current IDRP approaches, including insufficient validation of generated topological realism, narrow generalization across lithologies, inadequate representation of dynamic wettability, and limited model interpretability. Finally, we propose a forward-looking roadmap centered on multimodal foundation models for rocks, coupled with neural operators and uncertainty quantification frameworks, emphasizing the critical pathways for translating IDRP into engineering digital twins for unconventional hydrocarbon development, coalbed methane production enhancement, Enhanced Geothermal Systems, and geological CO₂ storage. This review offers a comprehensive reference for researchers at the intersection of geophysics, rock mechanics, and artificial intelligence. Full article

The continued scaling of semiconductor devices at advanced technology nodes introduces significant challenges in maintaining performance, reliability, and design efficiency. This work presents a data-driven framework for the modeling and optimization of nanosheet (NS) and forksheet (FS) transistors using deep learning and Bayesian optimization. An extensive dataset is generated through LTSpice-based circuit simulations, enabling efficient exploration of the design space while incorporating key device parameters, including channel length, channel width, supply voltage, temperature, and threshold voltage, together with variability and noise effects. A deep neural network (DNN) is developed as a surrogate model to learn the nonlinear relationship between input parameters and transistor switching behavior, achieving strong predictive performance with a coefficient of determination ($R^2\approx 0.91$), mean absolute error (MAE $\approx 0.024$), and root mean square error (RMSE $\approx 0.031$) on unseen test data. To improve physical consistency, a bounded-output formulation is introduced to guarantee physically admissible voltage predictions, while device-level benchmarking is performed to assess agreement with expected transistor characteristics. The results demonstrate accurate modeling of transient behavior across the sampled operating conditions. Comparative analysis shows that NS devices achieve faster switching and lower propagation delay, whereas FS devices exhibit improved stability under certain conditions. Bayesian optimization is employed to efficiently explore the design space and identify high-performing transistor configurations without exhaustive simulation-based searches. The proposed framework provides a scalable and computationally efficient methodology for surrogate modeling, design-space exploration, and early-stage assessment of advanced transistor architectures. Full article

Fourier Neural Operators (FNOs) exhibit mode saturation on high-contrast inhomogeneous media, and recent multi-scale extensions (MscaleFNO) further worsen out-of-distribution (OOD) generalization. We introduce the Helmholtz Neural Operator (HNO), a physics-informed, FFT-free branch–trunk operator in the DeepONet family, with a hybrid SIREN+learnable-Fourier trunk and a dual-path rank-32 hypernetwork branch, with bounded multiplicative gating on per-mode coefficients. At a matched parameter count (∼1.05 M, five seeds), HNO achieves a 2.6× lower OOD generalization gap than FNO (19.6% vs. 50.6%, $p=1.7\times {10}^{-3}$, Cohen’s $d=5.1$), 5.1× lower than vanilla DeepONet (19.6% vs. 99.9%, $p=8.2\times {10}^{-3}$), and 6.0× lower than MscaleFNO (19.6% vs. 117.4%, $p=2.4\times {10}^{-6}$); MscaleFNO’s deficit grows at 4.2× more parameters, ruling out capacity starvation. HNO is 4.6×/16.4× faster than FNO/MscaleFNO and 64×–245× faster than multi-threaded FD-PML (MKL PARDISO, 12 cores; 183×–698× vs. single-thread scipy.spsolve), making it suitable as a forward surrogate inside many-query workflows. Absolute accuracy on extreme-contrast (15:1) OOD samples is limited (relative $L^2\approx 1$), so HNO is positioned as a many-query surrogate or warm start for refinement loops, not a stand-alone replacement for direct solvers. A scope limitation is that HNO underperforms FNO on elliptic Darcy Flow, confirming specialization for hyperbolic/wave equations rather than universal operator learning. Full article

Background/Objectives: Contrast-enhanced (CE) breast MRI is highly sensitive for evaluating breast cancer extent and response to neoadjuvant therapy (NAT) but requires intravenous administration of gadolinium-based contrast agents (GBCA), increasing cost, time, patient discomfort, and health concerns. This study explored the feasibility of reducing GBCA use in treatment monitoring using a deep learning (DL) model to synthesize CE-MRI from non-contrast MRI. Methods: This IRB-approved retrospective pilot study evaluated women with breast cancer enrolled in an ongoing trial using serial MRI to monitor NAT prior to surgery. A pre-trained DL model was used to synthesize CE-MRI from T1-, T2-, and diffusion-weighted MRI. Changes in tumor volume at early (post-1-cycle NAT) and mid-treatment were measured on synthetic and acquired CE-MRI. Performance for predicting residual cancer burden (RCB) class 0/1 was evaluated using AUC and compared with DeLong’s test. Results: 27 women were included in the study (median age, 47 years [range = 28–75]); 14 (52%) achieved RCB class 0 and six (22%) achieved class 1. Synthetic CE-MRI-derived tumor volumes showed strong correlation with those from acquired CE-MRI at pre-treatment ($\rho$ = 0.92, p < 0.001) and early treatment ($\rho$ = 0.83, p < 0.001), but lower agreement at mid-treatment ($\rho$ = 0.57, p = 0.002). Change in tumor volume on synthetic CE-MRI was numerically similar to acquired CE-MRI for predicting RCB class 0/1 vs. 2/3 at both early (AUC = 0.84 vs. 0.86, p = 0.83) and mid-treatment (AUC = 0.73 vs. 0.75, p = 0.80). Conclusions: Synthetic CE-MRI demonstrates preliminary feasibility as a non-contrast surrogate for predicting favorable outcomes (RCB class 0/1) in this pilot study, but inconsistencies in tumor volume measurement vs. acquired CE-MRI warrant further model refinement and validation. Full article

Flood inundation modeling in low-gradient monsoon floodplains requires a physically consistent representation of rainfall–runoff–inundation processes. This study develops a hybrid modeling framework that integrates a coupled hydrological–hydraulic model (HEC-HMS–HEC-RAS) with a deep learning-based LSTM–U-Net surrogate to represent temporal hydrological memory and spatial inundation patterns. The framework is applied to the Upper Songkhram River Basin in northeastern Thailand, a storage-dominated floodplain strongly influenced by monsoon hydrology. The hydrological model demonstrated strong validation performance (NSE = 0.896, KGE = 0.827, R² = 0.909), while hydraulic simulations showed high spatial agreement with satellite-derived inundation maps (F1 = 0.876, Kappa = 0.873). Trained on hydraulically simulated discharge–inundation pairs, the LSTM–U-Net model successfully reproduced two-dimensional flood patterns across independent flood events (mean F1 = 0.838, IoU = 0.721), with prediction errors mainly occurring along shallow floodplain margins. Future projections under CMIP6 SSP2-4.5 and SSP5-8.5 indicate clear changes in flood-season discharge, with stronger increases under SSP5-8.5, whereas maximum inundation extent shows more moderate changes (≤21%), reflecting nonlinear floodplain response in low-gradient systems. The proposed framework preserves hydrological–hydraulic consistency while supporting future flood inundation projection, climate-informed flood risk assessment, and adaptation planning. Full article

As bridge infrastructure globally transitions from theoretical monitoring toward intelligent digital management, Machine Learning (ML) has emerged as a transformative tool for data-driven lifecycle decision-making. This study presents a systematic and critical review of ML applications across the entire bridge lifecycle, integrating a PRISMA-based scientometric analysis (2020–2025) with a rigorous technical synthesis of 3 major domains. The research reveals a clear hierarchy in deployment readiness; while Design & Optimization and Seismic Fragility Assessment have achieved “High” readiness by leveraging deep learning surrogates to achieve up to a 50-fold computational speedup over traditional simulations, Vibration-Based Damage Identification remains at a “Low–Medium” level due to environmental noise sensitivity and low Signal-to-Noise Ratios (SNR). Technical findings indicate that vision-based models (e.g., ViT, YOLOv8) show strong and promising performance for surface defect detection in controlled or semi-controlled settings, though broader field deployment remains constrained by lighting variability, dataset diversity, and validation at scale. In deterioration modeling and Remaining Useful Life (RUL) prediction, temporal architectures (e.g., LSTM) effectively capture non-linear trends, though operational risks such as “model drift” and “domain shift” in simulation-dependent models necessitate periodic retraining. This review identifies critical bottlenecks, including the “small data” paradox and the “black-box” dilemma. The work concludes by outlining a strategic roadmap centered on Physics-Informed Neural Networks (PINNs), Federated Learning for cross-agency collaboration, and Explainable AI (XAI) to foster professional trust in safety-critical infrastructure management. Full article

The correct classification of retinal lesions in retinal fundus images is important for supporting the analysis of diabetic retinopathy and age-related macular degeneration. State-of-the-art methods for this task are often based on black-box deep learning architectures that, despite their high performance, pose significant interpretability challenges, incur high computational costs, and lack computational interpretability at the feature-decision level. In this paper, a method based on surrogate-optimized features extracted by regular expressions is proposed for the classification of two retinal lesion categories (Drusen and Cotton Wool Spots). The method uses a compact and computationally interpretable row-by-row and column-by-column regular expression feature extractor together with a two-phase surrogate search over its discrete hyperparameters. Across 100 independent stratified executions under the repeated patch-level benchmark, the proposed method achieved a mean MCC of $0.7829\pm 0.0448$, a mean accuracy of $0.9008\pm 0.0217$, and a mean F1 score of $0.8529\pm 0.0294$. The best execution reached an MCC of $0.8433$, an accuracy of $0.9286$, and a macro F1 score of $0.8966$, which was the highest result among the evaluated baselines within that same benchmark. Additional source–image disjoint grouped analyses were carried out as leakage-aware robustness checks under stricter source–image separation and to examine validation overfitting. Together, these analyses support the usefulness of the compact run-based descriptor under the present experimental conditions, while indicating that the two-phase search should be interpreted as a practical hyperparameter selection heuristic rather than as a statistically superior search strategy. Full article

Accurate service performance evaluation of reinforced concrete (RC) beam structures is crucial for ensuring structural safety and guiding maintenance decisions. However, current practice primarily relies on qualitative visual inspections that fail to quantitatively link apparent defects to internal mechanical behavior. To address this, a novel evaluation framework fusing apparent crack features with static and dynamic responses is proposed. A context-aware grid-based deep learning model (CGDL-Crack) is developed that combines transfer learning with skeleton extraction, achieving crack localization with a maximum validation AP of 96.4% under complex backgrounds. Based on large-scale parametric finite element simulations and Sobol global sensitivity analysis, key state indicators—including static reaction forces, modal frequencies, and crack widths—are identified, and an artificial neural network (ANN) surrogate model is constructed to map multi-source monitoring data to material constitutive parameters. Full-process failure tests on 17 RC beams demonstrate that crack width follows bilinear growth and remains sensitive after stiffness indices saturate. The updated FE model accurately predicts ultimate bearing capacity, demonstrating the effectiveness of the proposed framework and its application potential for RC beam-type components in bridge and building engineering. Full article

A coupled multi-stage learning framework is presented for joint bit error rate (BER) prediction and beam angle optimization in massive multiple-input multiple-output (MIMO) systems under a controlled simulation protocol. Unlike purely sequential benchmarking pipelines, the proposed method jointly coordinates BER prediction and beam-angle selection through a shared latent representation, an uncertainty-guided refinement mechanism, a cross-stage consistency loss and alternating optimization. Ten diverse approaches are systematically evaluated across two task-specific stages: Stage 1 examines six classical and adapted methods for BER prediction, including polynomial regression and deep unfolding networks; Stage 2 investigates four machine-learning and generative adversarial network (GAN)-based approaches for angle optimization, including conditional GANs and the proposed Direct-Angle neural network. Stage 3 couples the best-performing methods into a unified hybrid architecture through a shared encoder, explicit consistency regularization and alternating cross-stage updates, thereby producing an integrated beamforming decision strategy rather than an independent cascade. It is shown through the evaluation that the coupled hybrid framework achieves 96.0% overall angle-selection accuracy, a mean BER of $8.0\times {10}^{-5}$ and 100% BER tolerance compliance within $\pm 3$ dB. In this framework, a differentiable BER surrogate initialized from a second-degree polynomial-regression teacher is coupled with the proposed Direct-Angle-NN for angle optimization. Relative to the strongest reimplemented literature baseline under the same controlled simulation assumptions, a 33.3% reduction in mean BER is achieved. Ablation experiments show that the coupling mechanism provides a modest but consistent improvement over the decoupled sequential baseline, increasing angle-selection accuracy from 93.5% to 96.0% and reducing mean BER from $1.05\times {10}^{-4}$ to $8.0\times {10}^{-5}$; the shared encoder accounts for the largest part of this gain while the consistency loss adds 0.6 percentage points. These results indicate that the shared encoder, consistency regularization and uncertainty-guided refinement improve the final beamforming decision, although the gain should be interpreted as incremental rather than as a large architectural breakthrough. A spectral efficiency of 38.0 bps/Hz and an energy efficiency of 0.466 Gbps/W are achieved with a power consumption of only 32.6 W. The theoretical discussion is presented as an analytical characterization of BER sensitivity, complemented by a computational-complexity assessment and empirical convergence diagnostics for the alternating optimization, rather than as a formal optimality proof. The effectiveness of the framework across multiple performance metrics is supported by Monte Carlo simulations, while the limitations of the current setup, including perfect CSI, uncoded QPSK, ideal hardware assumptions and a fixed beam codebook, are explicitly discussed. The complete simulation framework, including code and trained models, can be made available by the corresponding author upon reasonable request to facilitate reproducible research in massive MIMO optimization. Full article

This study presents a systematic review of Artificial Intelligence (AI) in vehicular bridge engineering, covering design, monitoring, and lifecycle decision support. The objective is to identify, classify, and critically analyze the main AI methods applied across the bridge lifecycle, including Machine Learning (ML), Deep Learning (DL), Artificial Neural Networks (ANNs), and Optimization Algorithms (OAs). The review follows the PRISMA 2020 framework to ensure transparency and reproducibility, considering publications from 2018 to 2026. The results show that AI applications span the entire bridge lifecycle; however, current research is predominantly concentrated in Structural Health Monitoring (SHM), damage detection, inspection, and predictive maintenance, while design-oriented applications—such as optimization, surrogate modeling, and structural analysis—remain comparatively less developed. Importantly, SHM data serve as a key input for data-driven modeling, enabling design optimization, reliability assessment, and lifecycle decision support. Classical ML methods remain effective for structured datasets, whereas DL models, particularly convolutional and recurrent neural networks, dominate image-based and time-series applications. In addition, hybrid physics-informed AI approaches are emerging to improve model reliability and interpretability. The review also identifies key challenges, including data quality limitations, lack of standardized methodologies, limited integration with engineering design codes, and barriers related to trust, expertise, and regulatory frameworks. Overall, the findings highlight a shift toward integrated digital frameworks, including digital twins and multimodal data fusion, to support more reliable monitoring and lifecycle decision-making. This study provides a comprehensive synthesis of current developments and outlines future research directions toward more resilient and intelligent bridge infrastructure systems. Full article

The optimisation design of agricultural machinery is shifting from offline, experience-driven engineering towards adaptive, data-driven, and closed-loop intelligent optimisation. Conventional approaches based on computer-aided engineering (CAE), empirical testing, mathematical modelling, and static multi-objective optimisation have provided an important engineering foundation, but they remain limited under unstructured field conditions involving soil heterogeneity, crop variability, climatic disturbance, and nonlinear machinery–environment interactions. This review systematically examines the evolution of intelligent optimisation design for agricultural machinery from conventional simulation-based methods to artificial intelligence (AI)- and digital twin (DT)-enabled paradigms. First, mathematical modelling, response surface methodology, discrete element method (DEM), computational fluid dynamics (CFD), multi-body dynamics (MBD), heuristic algorithms, and early AI-assisted surrogate optimisation are reviewed to clarify their contributions and limitations. Second, frontier enabling technologies are analysed, including agriculture-specific large models, generative AI, lightweight edge intelligence, deep reinforcement learning (DRL), embodied AI, federated learning (FL), and privacy-preserving computing. Third, system-level applications integrating DT and AI are discussed, with emphasis on full-lifecycle machinery optimisation, device–edge–cloud collaborative control, multi-agent fleet coordination, predictive maintenance, and Agriculture 5.0-oriented intelligent equipment systems. Key deployment bottlenecks are further identified, including sim-to-real inconsistency, virtual–physical mismatch in DTs, edge-side trade-offs among accuracy, latency, energy consumption, and cost, insufficient validation standards, and economic adoption barriers. Finally, a 2025–2030 roadmap is proposed, highlighting large-model–DT closed loops, control biomimetics, green low-carbon optimisation, and trustworthy human–machine symbiosis for sustainable Agriculture 5.0. Full article

Digital twin technology is rapidly gaining traction in the semiconductor industry for its ability to model manufacturing processes, including packaging engineering, to monitor and optimise performance cost-effectively. This paper focuses on two key areas of development. The first part explores the potential of digital design and additive manufacturing to produce high-performance, compact thermal management solutions that significantly reduce device junction temperatures and enhance operational efficiency. The second part presents the development of surrogate models to predict junction temperatures of electronic packages under varying operating and geometrical conditions. These models, trained using deep learning, were integrated into a user-friendly COMSOL Multiphysics application builder version 6.3. The proposed digital twin framework enables fast and accurate full-thermal field predictions in comparison to conventional 3D finite element simulations. Full article

Designing ultra-high-performance concrete (UHPC) mixtures requires balancing multiple, often conflicting, performance criteria, particularly mechanical strength and rheological behavior. However, the limited availability of publicly accessible datasets containing synchronized multi-property measurements, together with cross-source heterogeneity, poses a major challenge for robust data-driven modeling under small-sample conditions. To address this issue, this study proposes an integrated framework combining cross-source data harmonization, Variational Autoencoder (VAE)-based latent-space augmentation, multi-output deep learning, interpretability analysis, and Genetic Algorithm (GA)-driven inverse design. A dataset comprising 139 valid UHPC records was curated from 22 peer-reviewed studies and expanded to 2780 samples through VAE-based augmentation. Using the augmented dataset, a multi-output deep neural network was developed to jointly predict compressive strength, flexural strength, yield stress, and plastic viscosity. On the independent test set, the model achieved R² values of 0.8601, 0.9212, 0.8464, and 0.6603, respectively. Comparative benchmarks and augmentation ablation analyses further showed that VAE-based augmentation consistently improved predictive performance and generalization, especially under small-sample conditions. SHAP and partial dependence analyses identified curing age, steel fiber content, water-to-binder ratio, and superplasticizer dosage as the dominant factors governing UHPC performance. Finally, the trained surrogate model was coupled with a GA for multi-objective inverse optimization, and experimental validation of three candidate mixtures confirmed good agreement between predicted and measured values. This study provides a transparent and engineering-oriented methodology for the integrated prediction, interpretation, and optimization of UHPC mixtures. Full article

The aerodynamic performance of compressor stators critically affects aircraft engine efficiency, yet traditional CFD-based evaluation and optimization suffer from high computational cost. This study addresses this gap by developing deep learning surrogate models to predict total pressure loss coefficient and outlet flow angle deviation for compressor stator vanes, using two geometric parameters—stagger angle ${\beta }_y$, leading-edge radius ratio R_rle, and one operational parameter, attack angle α. A high-fidelity dataset of 1701 cases was generated via automated CFD simulations using the transitional SST k-ω model. Among evaluated models—including standard CNN, CBAM-CNN, SS-CNN, and CNN-Transformer, SS-CNN achieved the highest accuracy, reducing mean absolute percentage error from 3.56% to 2.03% for loss and from 1.49% to 1.11% for outlet angle, with substantial computational savings. These surrogate models were integrated into a multi-objective optimization framework. The optimized vane, featuring a reduced leading-edge radius ratio within a stable stagger range, reduced total pressure loss by 2.38% (from 0.0570 to 0.0556) at the design attack angle of −2.83°, while the outlet angle deviation decreased from 0.439° to 0.066° (85% reduction), with the outlet angle improvement concentrated near the design condition. This work demonstrates a systematic, data-driven pipeline combining parametric modeling, automated simulation, deep learning-based prediction, and rapid optimization, offering an efficient solution for intelligent compressor blade design. Full article