Search Results (1,787)

Forecasting short-term heavy precipitation is crucial for the early warning of disasters such as flash floods, landslides, and urban flooding. However, under complex topographic conditions, traditional numerical forecasts still fall short in capturing high-resolution heavy precipitation events, and conventional radar extrapolation methods struggle to accurately characterize the nonlinear evolution of weather systems during advection, deformation, and intensity adjustment processes. To address the challenge of short-term heavy rainfall forecasting in high-altitude, complex terrain, this paper proposes Nowcast with Flow-Net (Nwf-Net), a short-term precipitation forecasting framework that integrates deep learning with multi-source meteorological data. This framework consists of a Morphological Evolution Track Module (MET) and a Rainfall Intensity Correction Module (RIC) connected in series: the former combines upper-air wind fields with traditional optical flow algorithms to jointly characterize the displacement of and morphological changes in radar echoes; the latter utilizes a deep recurrent neural network to correct the intensity of forecast results, thereby enhancing the model’s ability to characterize the evolution of strong convective echoes. Experiments in the Alpine region demonstrate that Nwf-Net achieves CSI, HSS, and F1 scores of 0.392, 0.506, and 0.546, respectively, at 32 dBz. These results outperform those of traditional numerical models and some mainstream models, indicating that Nwf-Net can accurately capture multiscale severe convective information and consistently generate precise forecasts. Full article

Optical bistability is a nonlinear phenomenon enabling stable switching between two optical states and has important applications in optical communication and photonic neural networks (PNNs). However, conventional bistable devices often suffer from fabrication imperfections and scattering losses, which limit their robustness and dispersionless performance. In this study, we numerically investigate optical bistability from a one-dimensional photonic topological hypercrystal (PhH) composed of alternating hyperbolic metamaterials (HMMs) and dielectric layers. By designing a center-inversed symmetric layered PhH structure and introducing Kerr nonlinearity into the localized dielectric region of maximum electric field intensity at the inversion center, we achieve a robust, angle-insensitive optical bistability for TM polarization through phase variation compensation mechanism. When applied as a nonlinear activation function in PNNs, the bistable PhH exhibits performance comparable to conventional digital activation functions such as ReLU and Sigmoid in image-recognition tasks. Our work paves the way for integrating topological bistable devices into next-generation PNNs. Full article

A multimodal strategy for fall detection within the broader domain of human activity recognition is developed in this study. A fine-tuned Inflated 3D Convolutional Network model, trained in optical flow data derived from video inputs, achieves 92.70% accuracy in classifying fall-related events. Simultaneously, a Convolutional Neural Network–Bidirectional Long Short-Term Memory model incorporating attention mechanisms processes time-series sensor data, contributing to an ensemble performance of 97.87%. The integration of visual and sensor modalities illustrates a promising direction for developing reliable, real-time fall detection systems applicable in healthcare and assisted living environments. Full article

Digital management of modern railway bridges, a substantial part of high-speed railway networks, is often hindered by manual interpretation of construction drawings for Building Information Modeling (BIM). While individual technologies like optical character recognition (OCR) and neural networks are well-established, their generic application often fails on complex engineering documents. To address this, a domain-adaptive automatic recognition and semantic interpretation framework is proposed for railway bridge construction drawings. The novelty of this work lies in a specialized hybrid data fusion strategy that intelligently merges vector CAD file parsing with morphology-denoised OCR, resolving spatial and semantic conflicts. Furthermore, a back-propagation (BP) neural network is explicitly adapted to classify the extracted text into specific engineering categories, overcoming the challenges of dense layouts and overlapping symbols. Finally, the framework achieves end-to-end integration by transforming these semantic entities directly into structured, IFC-compatible BIM parameters. Evaluated on 250 real-world drawings, the framework achieved an average F1-score of 91.0% in semantic classification and improved processing efficiency by 6.5 times compared to manual methods. Moreover, 93.8% of the extracted entities achieved strict BIM parameter correctness, defined as seamless mapping to Revit IFC attributes without manual intervention. Full article

Camera rotation estimation is a key component in video stabilization and motion analysis. In many practical scenarios, inertial measurements are unavailable or temporally unreliable, while classical geometric pipelines degrade under blur, low texture, and low illumination. This paper investigates whether substantially downsampled optical flow can retain sufficient structure for accurate frame-to-frame rotation regression. We present VisualRNet, a lightweight rotation-specific visual regression framework trained with cross-modal IMU supervision. Our design uses coordinate-aware feature encoding, depthwise separable convolutions, lightweight attention, and a compact 6D rotation head to model the spatial structure of rotational flow fields. On Deep-FVS, VisualRNet achieves a mean rotation error of 0.3151${}^{\circ }$ on the test set. The VisualRNet regression head contains 7.7 K parameters, 0.002 GFLOPs, and runs at 729 FPS, while the full pipeline with the FastFlowNetv2 frontend contains 1.374 M parameters, 7.194 GFLOPs, and runs at approximately 113 FPS. A cross-camera adaptation experiment on TUM VI further indicates that the learned motion representation can be aligned to a new camera system with limited calibration data. These results support low-resolution optical flow as a practical input for visual rotation estimation and suggest particular value in stabilization-oriented and cost-sensitive applications where approximate rotational trend matters more than full scene geometry. Full article

While superdeterministic and fractal spacetime models offer compelling alternative perspectives on quantum foundations, the simulation and validation of effective wave dynamics in such non-differentiable, deterministic settings remain computationally and theoretically challenging. To address this, a framework built around the Fractional Nonlinear Klein–Gordon Equation (FNKGE), defined through the spectral fractional Laplacian, was developed. This equation was solved and benchmarked through a comparative study between Physics-Informed Neural Networks (PINNs) with Fourier features and Physics-Informed Graph Neural Networks (PI-GNNs). Additionally, detection patterns were simulated via deterministic agents, and theoretical links between fractal geometry, computational irreducibility, and deviations from statistical independence were formalized. Regarding the computational evaluation, superior accuracy was achieved by the PI-GNNs, yielding a mean relative error of $0.5\%$ ($\overline{ϵ}=0.005$), alongside faster convergence and a more well-conditioned Hessian spectrum compared to PINNs. Crucially, a continuous power-law decay ($S\left(k_y\right)\sim k_y^{-1.8}$) was revealed by the spectral analysis of the simulated detection patterns, confirming the emergence of classical optical caustics rather than discrete quantum-interference peaks. Furthermore, a modified dispersion relation that accurately predicts linear instability regimes was derived, and specific boundary artifacts in non-periodic domains were identified. Taken together, the FNKGE is validated by these results as a viable effective model for fractal wave phenomenology and as a robust benchmark for physics-informed learning architectures. Full article

Accurate estimation of curvature radius from interference fringes is critical in optical metrology and precision manufacturing. Conventional interferogram analytical approaches often require manual intervention and are sensitive to fringe variations related to noise and environmental vibrations. To address these limitations, we combine an improved Twyman–Green interferometer with different artificial intelligence (AI) deep learning models and utilize a self-developed MATLAB analysis program to propose a non-destructive and rapid measurement system for optical coating substrates. The proposed AI-assisted Twyman–Green interferometric system differs fundamentally from conventional wavefront sensing techniques in both principle and implementation. This paper utilizes the Twyman–Green interferometer to generate interference fringe datasets on B270 glass and sapphire substrates, and employs convolutional neural network (CNN), ResNet-18, and VGG-16 models for training and evaluation. The proposed method integrates image enhancement, fringe pattern clustering, and analysis and validation based on fast Fourier transform (FFT). Experimental results show that ResNet-18 outperforms other models, with a mean absolute percentage error of 5.44% on sapphire substrates and 3.40% on B270 glass substrates. These findings highlight the effectiveness and robustness of deep learning models, especially residual networks, in automatic ROC prediction for optical measurement applications. Full article

Traditional satellite-derived bathymetry (SDB) often suffers from systematic optical path distortions due to the neglect of seafloor slope effects, leading to significant accuracy degradation in high-gradient coastal areas. This study proposes a Slope-Aware Physics-Informed Neural Network (SA-PINN) framework that synergistically utilizes ICESat-2 bathymetric photons and Sentinel-2 multispectral imagery. The core innovation involves a slope-aware operator, integrated into the radiative transfer-based physics loss function, which explicitly rectifies directional optical path deviations induced by seafloor inclination. By fusing physical mechanisms with data-driven features, the model utilizes a seven-dimensional feature space comprising four spectral bands, two directional slope components, and prior depth. Applications at Culebra, Maui, and Molokai demonstrate that SA-PINN significantly outperforms the Stumpf model, Random Forest, and standard CNNs, achieving root mean square errors (RMSE) of 1.36 m, 2.91 m, and 1.34 m, respectively. Ablation studies confirm that SA-PINN reduces RMSE by up to 37% compared to CNN in complex regions with slopes exceeding 10°, ensuring superior physical consistency and spatial continuity. This research provides a robust, in situ-free automated solution for high-resolution bathymetric mapping in remote and steep coastal environments globally. Full article

Object detection in optical remote sensing imagery has emerged as a crucial task in computer vision, with applications ranging between environmental monitoring to disaster management, precision agriculture, and urban planning. This review systematically examines current methodologies, categorising them into four principal approaches: (1) template matching-based methods, which leverage predefined patterns for object identification; (2) knowledge-based methods, which incorporate geometric and contextual information to enhance detection accuracy; (3) object-based image analysis (OBIA), which segments images into meaningful objects using spectral and spatial properties; (4) machine learning-based methods, particularly deep convolutional neural networks (CNNs), which have revolutionised the field through automatic feature learning. Each methodology’s performance characteristics, computational requirements, and suitability for different remote sensing applications are analysed. Our systematic review, following PRISMA guidelines, analysed 189 studies published from 2010 to 2025, of which 73 provided quantitative results on standard benchmarks. The three most critical challenges identified are as follows: (1) annotation bottleneck, as dense bounding box labelling of remote sensing imagery remains highly labour-intensive for deep learning approaches, (2) extreme scale variation spanning 2–3 orders of magnitude within single scenes, and (3) domain adaptation failures when models encounter new geographic regions or sensor characteristics. This review identifies critical research gaps and proposes prioritised future directions, emphasising foundation models for zero-shot detection, efficient architectures for resource-constrained deployment, and standardised benchmarks with size-specific metrics. The analysis provides practitioners with evidence-based decision frameworks for method selection and researchers with a roadmap for advancing object detection in remote sensing applications. Full article

The integration of Selective Laser Melting (SLM) into high-end manufacturing necessitates robust machine-condition monitoring and subsystem fault classification to navigate the intricate coupling and dynamic transients inherent in these systems. Current diagnostic frameworks often struggle to decouple high-dimensional state variables or track their underlying temporal evolution. To overcome these bottlenecks, this paper develops a spatiotemporal deep learning architecture by coupling Convolutional Neural Networks (CNNs) with Long Short-Term Memory (LSTM) units. This hybrid approach leverages CNNs to distill multi-dimensional spatial features from subsystem sensor arrays, while LSTMs interpret the sequential dependencies critical for identifying systemic drifts. The proposed framework was validated using an extensive industrial dataset comprising over 310,000 temporal samples across seven critical SLM subsystems, including optical, cooling, and energy units. We systematically investigated three data-handling strategies—feature weighting, balancing, and distribution-based synthesis—to optimize the model’s sensitivity to rare-event anomalies. Benchmarking across six architectural variants reveals that a specific CNN × 3 + LSTM × 1 configuration yields superior diagnostic fidelity, achieving a classification accuracy of 98.81%. Visualization of the feature space confirms high inter-class separability, demonstrating the model’s ability to isolate faults within complex manufacturing cycles. This research offers a scalable paradigm for the intelligent monitoring of SLM equipment and provides a technical benchmark for equipment health management and predictive maintenance in advanced additive manufacturing. Full article

Aiming to address the problems of low accuracy in coal–rock identification during coal mining, which lead to energy waste and safety hazards, a high-precision coal–rock medium identification method combining terahertz time-domain spectroscopy technology and multiple machine learning algorithms is proposed. By preparing coal–rock samples with a gradient change in coal content, terahertz time-domain spectroscopy data of coal–rock mixed media are collected, and optical parameters such as the refractive index and absorption coefficient are extracted. Principal component analysis is used to reduce the dimensionality of the terahertz data, and machine learning algorithms such as support vector machine, least squares support vector machine, artificial neural networks, and random forests are adopted for classification and identification. The study found that terahertz waves are more sensitive to coal–rock media in the 0.7–1.3 THz frequency band, and that the refractive index and absorption coefficient of coal–rock mixed media are significantly positively correlated with coal content within the range of 0–30%. After feature extraction and K-fold cross-validation, the random forest model achieved a coal–rock classification accuracy of over 96% on the test set, significantly outperforming other comparison algorithms. The research verifies the efficiency and practicality of terahertz technology combined with multiple machine learning algorithms in coal–rock identification, providing a new method for fields such as mineral separation. This method has, to a certain extent, broken through the accuracy bottleneck of traditional coal–rock identification technologies within its applicable range, providing a new solution for real-time detection of coal–rock interfaces and is expected to further reduce the risks of ineffective mining and roof accidents in the future. Full article

Precipitation forecasting is essential for disaster prevention, water resource management, and socio-economic resilience. The field has evolved from numerical weather prediction (NWP) and optical-flow-based methods toward data-driven deep learning approaches that can exploit larger observational datasets and model complex nonlinear relationships. Against this background, this study evaluates multi-station temporal forecasting models within a single-year, station-based proof-of-concept benchmark under unified data conditions. We adapt the Transformer and Informer architectures to this meteorological setting, rigorously preprocess the AWS dataset to avoid data leakage, and select predictive variables using complementary linear and nonlinear relevance criteria. Model performance is assessed using continuous and categorical precipitation metrics, including the Critical Success Index (CSI). The results show that the Informer outperforms the recurrent neural network (RNN) baselines and achieves the lowest mean MAE and RMSE together with the highest mean CSI among the evaluated models while using substantially fewer parameters than the standard Transformer. However, its sample-wise absolute error distribution remains statistically comparable to that of the standard Transformer. Overall, this study establishes a single-year, station-based proof-of-concept benchmark for comparing architectures in very-short-term (1–5 h ahead) precipitation forecasting. Full article

With the increasing application of novel glass materials in the field of optics, traditional empirical and trial-and-error approaches to glass development are gradually becoming insufficient to meet escalating performance demands. In this study, we propose a neural network-based machine learning method for the design of advanced fluoride glass materials. Predictive models for density and refractive index were first developed based on online fluoride glass datasets. Moreover, SHapley Additive exPlanations (SHAP) analysis was adopted to uncover the quantitative composition-property relationship. Then, the well-trained model was employed for inverse design, identifying specific compositions that fulfill desired properties in terms of density and refractive index. Finally, several recommended compositions were experimentally validated and the measured density and refractive index matched well with the corresponding input values, thereby confirming the effectiveness of the proposed method in designing new fluoride glass materials. Full article

Electrical Impedance Tomography (EIT) is a promising non-invasive sensing technique, yet its practical application in resource-constrained environments is often limited by the high computational cost of inverse image reconstruction. To address this challenge, we focus on specific sensing objectives rather than full image recovery. In this study, we propose a lightweight, task-oriented inference framework for object localization in EIT that bypasses the need to solve computationally expensive inverse reconstruction problems. This approach addresses the high computational demands and hardware complexity of conventional iterative methods, which often hinder real-time monitoring in resource-constrained edge computing environments. Training datasets were generated via finite element method (FEM) simulations for Opposite and Adjacent current injection configurations. A feedforward neural network was developed to independently estimate the radial and angular object positions as probability distributions. Our systematic evaluation revealed that the localization performance depends on the injection configuration and model depth; notably, the Opposite method achieved perfect classification accuracy (1.00) for radial estimation with an optimized architecture of four hidden layers, whereas the Adjacent method exhibited higher ambiguity. Results quantitatively evaluated using the Wasserstein distance show that the Opposite configuration produces more localized, unimodal probability distributions than the Adjacent configuration by utilizing current fields that traverse the entire domain. Compared with existing image-based reconstruction methods, including the conventional electrical impedance tomography and diffuse optical tomography reconstruction software (EIDORS ver.3.12), the proposed framework reduced energy consumption from 3.09 to 0.96 Wh, demonstrating an approximately 70% improvement in energy efficiency while maintaining a high localization accuracy without the need for iterative Jacobian updates. This task-oriented framework enables reliable, high-speed, and energy-efficient localization, making it well-suited for low-power EIT applications in mobile and embedded sensor systems. Full article

Nanophotonics, an interdisciplinary field merging nanotechnology and photonics, has enabled transformative advancements across diverse sectors, including green energy, biomedicine, and optical computing. This review comprehensively examines recent progress in nanophotonic principles and applications, highlighting key innovations in material design, device engineering, and system integration. In renewable energy, nanophotonics allows the use of light-trapping nanostructures and spectral control in perovskite solar cells, concentrating solar power systems, and thermophotovoltaics. This has significantly enhanced solar conversion efficiencies, approaching theoretical limits. In biosensing, nanophotonic platforms achieve unprecedented sensitivity in detecting biomolecules, pathogens, and pollutants, enabling real-time diagnostics and environmental monitoring. Medical applications leverage tailored light–matter interactions for precision photothermal therapy, image-guided surgery, and early disease detection. Furthermore, nanophotonics underpins next-generation optical neural networks and neuromorphic computing, offering ultrafast, energy-efficient alternatives to von Neumann architectures. Despite rapid growth, challenges in scalability, fabrication costs, and material stability persist. Future advancements will rely on novel materials, AI-driven design optimization, and multidisciplinary approaches to enable scalable, low-cost deployment. This review summarizes recent progress and highlights future trends, including novel material systems, multidisciplinary approaches, and enhanced computational capabilities, paving the way for transformative applications in this rapidly evolving field. Full article