Search Results (3,525)

The primary distinction between technical design and engineering design lies in the role of analysis and optimization. From its inception, descriptive geometry has supported military and engineering applications, and its graphical rules inherently reflect principles of optimization—similar to the core ideas of sparse representation and compressed sensing. This paper explores the geometric and mathematical significance of the center line in symmetrical objects and the axis of rotation in solids of revolution, framing these elements within the theory of sparse representation. It further establishes rigorous correspondences between geometric primitives—points, lines, planes, and symmetric solids—and their sparse representations in descriptive geometry. By re-examining traditional engineering drawing techniques from the perspective of optimization analysis, this study reveals the hidden mathematical logic embedded in geometric constructions. The findings not only support the deeper integration of mathematical reasoning in engineering education but also provide an intuitive framework for teaching abstract concepts such as sparsity and signal reconstruction. This work contributes to interdisciplinary understanding between descriptive geometry, mathematical modeling, and engineering pedagogy. Full article

Reference crop evapotranspiration (ETo) is a crucial component in calculating crop water requirements, and its accurate prediction is vital for effective agricultural water management and irrigation planning. Generally, the FAO Penman-Monteith 56 equation is recommended as the benchmark’s method for calculating Eto, but it requires extensive meteorological data—posing challenges in regions with sparse monitoring infrastructure. This review addresses a critical gap: the lack of systematic comparative analysis of machine learning (ML) methods for ETo estimation under data-limited conditions. We review 325 studies searched by Web of Science from 2001 to 2024, focusing on applications of machine learning models in ETo modeling and prediction. Then, this review evaluates these models regarding their characteristics, accuracy, and applicability, including artificial neural networks (ANN), support vector machines (SVM), ensemble learning (EL), and deep learning (DL). Crucially, EL models demonstrate superior stability and cost-effectiveness, with typical performance metrics of R² > 0.95 and RMSE ranging from 0.1 to 0.6 mm·d⁻¹. Notably, DL methods achieve the highest accuracy under conditions of data scarcity. Using only temperature data, they attain competitive performance (R² = 0.81, RMSE = 0.56 mm·d⁻¹). Additionally, we further synthesize optimal input variables, performance metrics, and domain-specific implementation guidelines. In summary, this study provides a comprehensive and up-to-date overview of machine learning methods for ETo modeling, thereby offering valuable insights for researchers in the field of evapotranspiration. Full article

Marine benthic organism detection (BOD) is essential for underwater robotics and seabed resource management but suffers from motion blur, perspective distortion, and background clutter in dynamic underwater environments. To address visual feature degradation and computational constraints, we, in this paper, introduce EMR-YOLO, a deep learning based multi-scale BOD method. To handle the diverse sizes and morphologies of benthic organisms, we propose an Efficient Detection Sparse Head (EDSHead), which combines a unified attention mechanism and dynamic sparse operators to enhance spatial modeling. For robust feature extraction under resource limitations, we design a lightweight Multi-Branch Fusion Downsampling (MBFDown) module that utilizes cross-stage feature fusion and multi-branch architecture to capture rich gradient information. Additionally, a Regional Two-Level Routing Attention (RTRA) mechanism is developed to mitigate background noise and sharpen focus on target regions. The experimental results demonstrate that EMR-YOLO achieves improvements of 2.33%, 1.50%, and 4.12% in AP, AP₅₀, and AP₇₅, respectively, outperforming state-of-the-art methods while maintaining efficiency. Full article

The generation of 360° video is gaining prominence in immersive media, virtual reality (VR), gaming projects, and the emerging metaverse. Traditional methods for panoramic content creation often rely on specialized hardware and dense video capture, which limits scalability and accessibility. Recent advances in generative artificial intelligence, particularly diffusion models and neural radiance fields (NeRFs), are examined in this research for their potential to generate immersive panoramic video content from minimal input, such as a sparse set of narrow-field-of-view (NFoV) images. To investigate this, a structured literature review of over 70 recent papers in panoramic image and video generation was conducted. We analyze key contributions from models such as 360DVD, Imagine360, and PanoDiff, focusing on their approaches to motion continuity, spatial realism, and conditional control. Our analysis highlights that achieving seamless motion continuity remains the primary challenge, as most current models struggle with temporal consistency when generating long sequences. Based on these findings, a research direction has been proposed that aims to generate 360° video from as few as 8–10 static NFoV inputs, drawing on techniques from image stitching, scene completion, and view bridging. This review also underscores the potential for creating scalable, data-efficient, and near-real-time panoramic video synthesis, while emphasizing the critical need to address temporal consistency for practical deployment. Full article

Foreign object intrusion in railway perimeter areas poses significant risks to train operation safety. To address the limitation of current visual detection technologies that overly focus on target identification while lacking quantitative risk assessment, this paper proposes a railway intrusion risk quantification method integrating track semantic segmentation and spatiotemporal features. An improved BiSeNetV2 network is employed to accurately extract track regions, while physical-constrained risk zones are constructed based on railway structure gauge standards. The lateral spatial distance of intruding objects is precisely calculated using track gauge prior knowledge. A lightweight detection architecture is designed, adopting ShuffleNetV2 as the backbone to reduce computational complexity, with an incorporated Dilated Transformer module to enhance global context awareness and sparse feature extraction, significantly improving detection accuracy for small-scale objects. The comprehensive risk assessment formula integrates object category weights, lateral risk coefficients in intrusion zones, longitudinal distance decay factors, and dynamic velocity compensation. Experimental results demonstrate that the proposed method achieves 84.9% mean average precision (mAP) on our proprietary dataset, outperforming baseline models by 3.3%. By combining lateral distance detection with multidimensional risk indicators, the method enables quantitative intrusion risk assessment and graded early warning, providing data-driven decision support for active train protection systems and substantially enhancing intelligent safety protection capabilities. Full article

Plant disease segmentation has achieved significant progress with the help of artificial intelligence. However, deploying high-accuracy segmentation models in resource-limited settings faces three key challenges, as follows: (A) Traditional dense attention mechanisms incur quadratic computational complexity growth (O($n^{2}d$)), rendering them ill-suited for low-power hardware. (B) Naturally sparse spatial distributions and large-scale variations in the lesions on leaves necessitate models that concurrently capture long-range dependencies and local details. (C) Complex backgrounds and variable lighting in field images often induce segmentation errors. To address these challenges, we propose Sparse-MoE-SAM, an efficient framework based on an enhanced Segment Anything Model (SAM). This deep learning framework integrates sparse attention mechanisms with a two-stage mixture of experts (MoE) decoder. The sparse attention dynamically activates key channels aligned with lesion sparsity patterns, reducing self-attention complexity while preserving long-range context. Stage 1 of the MoE decoder performs coarse-grained boundary localization; Stage 2 achieves fine-grained segmentation by leveraging specialized experts within the MoE, significantly enhancing edge discrimination accuracy. The expert repository—comprising standard convolutions, dilated convolutions, and depthwise separable convolutions—dynamically routes features through optimized processing paths based on input texture and lesion morphology. This enables robust segmentation across diverse leaf textures and plant developmental stages. Further, we design a sparse attention-enhanced Atrous Spatial Pyramid Pooling (ASPP) module to capture multi-scale contexts for both extensive lesions and small spots. Evaluations on three heterogeneous datasets (PlantVillage Extended, CVPPP, and our self-collected field images) show that Sparse-MoE-SAM achieves a mean Intersection-over-Union (mIoU) of 94.2%—surpassing standard SAM by 2.5 percentage points—while reducing computational costs by 23.7% compared to the original SAM baseline. The model also demonstrates balanced performance across disease classes and enhanced hardware compatibility. Our work validates that integrating sparse attention with MoE mechanisms sustains accuracy while drastically lowering computational demands, enabling the scalable deployment of plant disease segmentation models on mobile and edge devices. Full article

Forest fires not only destroy vegetation and directly decrease forested areas, but they also significantly impair forest stand structures and habitat conditions, ultimately leading to imbalances within the entire forest ecosystem. Therefore, accurate forest fire detection is critical for ecological safety and for protecting lives and property. However, existing algorithms often struggle with detecting flames and smoke in complex scenarios like sparse smoke, weak flames, or vegetation occlusion, and their high computational costs hinder practical deployment. To cope with it, this paper introduces F3-YOLO, a robust and fast forest fire detection model based on YOLOv12. F3-YOLO introduces conditionally parameterized convolution (CondConv) to enhance representational capacity without incurring a substantial increase in computational cost, improving fire detection in complex backgrounds. Additionally, a frequency domain-based self-attention solver (FSAS) is integrated to combine high-frequency and high-contrast information, thus better handling real-world detection scenarios involving both small distant targets in aerial imagery and large nearby targets on the ground. To provide more stable structural cues, we propose the Focaler Minimum Point Distance Intersection over Union Loss (FMPDIoU), which helps the model capture irregular and blurred boundaries caused by vegetation occlusion or flame jitter and smoke dispersion. To enable efficient deployment on edge devices, we also apply structured pruning to reduce computational overhead. Compared to YOLOv12 and other mainstream methods, F3-YOLO achieves superior accuracy and robustness, attaining the highest mAP@50 of 68.5% among all compared methods on the dataset while requiring only 5.4 GFLOPs of computational cost and maintaining a compact parameter count of 2.6 M, demonstrating exceptional efficiency and effectiveness. These attributes make it a reliable, low-latency solution well-suited for real-time forest fire early warning systems. Full article

In urban construction, the efficient demolition of concrete structures imposes high-precision requirements on blasting technology. The mesoscopic evolution mechanism of concrete blasting damage is the key to optimizing blasting parameters. In this study, a numerical model of concrete blasting is established using Particle Flow Code (PFC). By comparing it with an experimental model containing a blast hole and a horizontal single fissure, the rationality and reliability of the model in simulating blasting damage evolution are verified. On this basis, four groups of control variable schemes are designed (concrete particle size distribution, aggregate content, prefabricated fissure inclination angle, and fissure length) to systematically explore the effects of mesoscopic structures and macroscopic defects on blasting damage. The results show that larger concrete particles make it easier for damage cracks to avoid large particles, forming sparse and irregular crack networks. A higher aggregate content enhances the “obstruction-guidance” effect of aggregate distribution on damage. When the aggregate content is 40%, the vertical damage expansion is the most prominent, reaching up to 3.05 cm. Fissure inclination angle affects the damage direction by guiding the propagation path of stress waves. Fissures inclined at 30°~60° serve as preferential damage channels, while 90° vertical fissures make vertical damage more significant. An increased fissure length expands the damage range, and the damage degree is the highest for a 40 mm long fissure, being 1.29 times that of a 30 mm fissure. The research results reveal the mesoscopic evolution laws of concrete blasting damage, providing a theoretical basis for the optimization of engineering blasting parameters and safety control. Full article

Accurate wave forecasting under typhoon conditions is essential for coastal safety in the Pearl River Estuary. This study explores the use of Random Forest (RF) and Long Short-Term Memory (LSTM) models to predict significant wave heights, using SWAN-simulated data from 87 historical typhoon events. Ten representative typhoons were reserved for independent testing. Results show that the LSTM model outperforms RF in 3 h forecasts, achieving a lower mean RMSE and higher R², particularly in capturing wave peaks under highly dynamic conditions. For 6 h forecasts, both models exhibit decreased accuracy, with RF performing slightly better in stable scenarios, while LSTM remains more responsive in complex wave evolution. Generalization tests at three nearby stations demonstrate that both models, especially LSTM, retain strong predictive skill beyond the training location. These findings highlight the potential of combining numerical wave models with machine learning for short-term, data-driven wave forecasting in typhoon-prone and observation-sparse regions. The study also points to future improvements through integration of wind field predictors, model updating strategies, and ensemble meteorological data. Full article

Forest disturbance is a major driver shaping the structure and function of plantation ecosystems. Current research predominantly focuses on single forest types or landscape scales. However, species-level fine-scale assessments of disturbance dynamics are still scarce. In this study, we investigated Chinese fir (Cunninghamia lanceolata), Armand pine (Pinus armandii), and Yunnan pine (Pinus yunnanensis) plantations in the mountainous eastern Yunnan Plateau. We developed a Spatial Coupling Framework of Disturbance Legacy (SC-DL) to systematically elucidate the spatial associations between contemporary species distribution patterns and historical disturbance regimes. Using the Google Earth Engine (GEE) platform, we reconstructed pixel-level disturbance trajectories by integrating long-term Landsat time series (1993–2024) and applying the LandTrendr algorithm. By fusing multi-source remote sensing features (Sentinel-1/2) with terrain factors, employing RFE, and performing a multi-model comparison, we generated 10 m-resolution species distribution maps for 2024. Spatial overlay analysis quantified the cumulative proportion of the historically disturbed area and the spatial aggregation patterns of historical disturbances within current species ranges. Key results include the following: (1) The model predicting disturbance year achieved high accuracy (R² = 0.95, RMSE = 2.02 years, MAE = 1.15 years). The total disturbed area from 1993 to 2024 was 872.7 km², exhibiting three distinct phases. (2) The random forest (RF) model outperformed other classifiers, achieving an overall accuracy (OA) of 95.17% and a Kappa coefficient (K) of 0.93. Elevation was identified as the most discriminative feature. (3) Significant spatial differentiation in disturbance types emerged: anthropogenic disturbances (e.g., logging and reforestation/afforestation) dominated (63.1% of total disturbed area), primarily concentrated within Chinese fir zones (constituting 70.2% of disturbances within this species’ range). Natural disturbances accounted for 36.9% of the total, with fire dominating within the Yunnan pine range (79.3% of natural disturbances in this zone) and drought prevailing in the Armand pine range (71.3% of natural disturbances in this zone). (4) Cumulative disturbance characteristics differed markedly among species zones: Chinese fir zones exhibited the highest cumulative proportion of disturbed area (42.6%), with strong spatial aggregation. Yunnan pine zones followed (36.5%), exhibiting disturbances linearly distributed along dry–hot valleys. Armand pine zones showed the lowest proportion (20.9%), characterized by sparse disturbances within fragmented, high-altitude habitats. These spatial patterns reflect the combined controls of topographic adaptation, management intensity, and environmental stress. Our findings establish a scientific basis for identifying disturbance-prone areas and inform the development of differentiated precision management strategies for plantations. Full article

To address the challenges of narrow peak characteristics and low signal-to-noise ratio (SNR) detection in Laser-Induced Breakdown Spectroscopy (LIBS), in this paper, we combine the Sparse Bayesian Learning–Baseline Correction (SBL-BC) algorithm with residual skewness monitoring to propose a spectral estimation method tailored for LIBS. In LIBS spectra, discrete peaks are susceptible to baseline fluctuations and noise, while the Gaussian dictionary modeling and fixed convergence criterion of the existing SBL-BC lead to the inaccurate characterization of narrow peaks and high computational complexity. To overcome these limitations, we introduce a residual skewness dynamic tracking mechanism to mitigate residual negative skewness accumulation caused by positivity constraints under high noise levels, preventing traditional convergence criterion failure. Simultaneously, by eliminating the dictionary matrix and directly modeling the spectral peak vector, we transform matrix operations into vector computations, better aligning with LIBS’s narrow peak features and high-channel-count processing requirements. Through simulated and real spectral experiments, the results demonstrate that this method outperforms the SBL-BC algorithm in terms of spectral peak fitting accuracy, computational speed, and convergence performance across various SNRs. It effectively separates spectral peaks, baseline, and noise, providing a reliable approach for both quantitative and qualitative analysis of LIBS spectra. Full article

The Third Pole region, particularly the Hindu–Kush–Himalaya (HKH), is highly prone to lightning, causing thousands of fatalities annually. Skillful prediction and timely communication are essential for mitigating lightning-related losses in such observationally data-sparse regions. Therefore, this study evaluates kilometer-scale ICON-CLM-simulated atmospheric variables using six machine learning (ML) models to detect lightning activity over the Third Pole. Results from the ensemble boosting ML models show that ICON-CLM simulated variables such as relative humidity (RH), vorticity (vor), 2m temperature (t_2m), and surface pressure (sfc_pres) among a total of 25 variables allow better spatial and temporal prediction of lightning activities, achieving a Probability of Detection (POD) of ∼0.65. The Lightning Potential Index (LPI) and the product of convective available potential energy (CAPE) and precipitation (prec_con), referred to as CP (i.e., CP = CAPE × precipitation), serve as key physics aware predictors, maintaining a high Probability of Detection (POD) of ∼0.62 with a 1–2 h lead time. Sensitivity analyses additionally using climatological lightning data showed that while ML models maintain comparable accuracy and POD, climatology primarily supports broad spatial patterns rather than fine-scale prediction improvements. As LPI and CP reflect cloud microphysics and atmospheric stability, their inclusion, along with spatiotemporal averaging and climatology, offers slightly lower, yet comparable, predictive skill to that achieved by aggregating 25 atmospheric predictors. Model evaluation using the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) highlights XGBoost as the best-performing diagnostic classification (yes/no lightning) model across all six ML tested configurations. Full article

Small object detection in UAV aerial imagery presents significant challenges due to scale variations, sparse feature representation, and complex backgrounds. To address these issues, this paper focuses on practical engineering improvements to the existing YOLOv8s framework, rather than proposing a fundamentally new algorithm. We introduce MultiScaleConv-YOLO (MSConv-YOLO), an enhanced model that integrates well-established techniques to improve detection performance for small targets. Specifically, the proposed approach introduces three key improvements: (1) a MultiScaleConv (MSConv) module that combines depthwise separable and dilated convolutions with varying dilation rates, enhancing multi-scale feature extraction while maintaining efficiency; (2) the replacement of CIoU with WIoU v3 as the bounding box regression loss, which incorporates a dynamic non-monotonic focusing mechanism to improve localization for small targets; and (3) the addition of a high-resolution detection head in the neck–head structure, leveraging FPN and PAN to preserve fine-grained features and ensure full-scale coverage. Experimental results on the VisDrone2019 dataset show that MSConv-YOLO outperforms the baseline YOLOv8s by achieving a 6.9% improvement in mAP@0.5 and a 6.3% gain in recall. Ablation studies further validate the complementary impact of each enhancement. This paper presents practical and effective engineering enhancements to small object detection in UAV scenarios, offering an improved solution without introducing entirely new theoretical constructs. Future work will focus on lightweight deployment and adaptation to more complex environments. Full article

The accurate assessment of soil fertility is critical for guiding nutrient management and promoting sustainable agriculture in semi-arid agroecosystems. In this study, a machine learning-based Soil Fertility Index (SFI) model was developed using regularized regression techniques to evaluate fertility across a dryland maize-growing region in southeastern Türkiye. A total of 64 composite soil samples were collected from the Batman Plain, characterized by alkaline and salinity-prone conditions. Five soil chemical indicators, electrical conductivity (EC), pH, organic matter (OM), zinc (Zn), and iron (Fe), were selected for SFI estimation using a standardized rating approach. The dataset was randomly split into training (80%) and test (20%) subsets to calibrate and validate the models. Ridge, Lasso, and Elastic Net regression models were employed to predict SFI and assess variable importance. Among these, the Lasso model achieved the highest predictive accuracy on test data (R² = 0.746, RMSE = 0.060), retaining only EC and Zn as significant predictors. Ridge and Elastic Net captured OM and pH, though their contributions were minimal (|β| < 0.01). Spatial predictions showed moderate alignment with observed SFI values (range: 0.48–0.76), but all models underestimated high-fertility zones (>0.69), likely due to coefficient shrinkage. Despite its simplicity, the Lasso model offered superior interpretability and spatial resolution. The results reveal the potential of interpretable machine learning for supporting sustainable, site-specific fertility assessment and informed nutrient management in data-scarce and environmentally vulnerable regions. Full article

The Chinese sturgeon (Acipenser sinensis), a critically endangered anadromous fish species, spends over 90% of its life cycle in marine habitats, yet research on its marine ecology and habitat requirements is limited due to sparse data. To address this, we integrated satellite remote sensing with ecological modeling to assess spatiotemporal dynamics in marine habitat suitability across China’s continental shelf (2003–2020). Nine key habitat factors were derived from multi-source remote sensing data and inverted transparency algorithms. Species occurrence data were coupled with the Maximum Entropy (MaxEnt) model to evaluate habitat preferences and seasonal shifts. Results revealed distinct environmental preferences: shallow depths (≤20 m), sea surface and bottom temperature (10–30 °C and 10–25 °C), salinity (10–35‰), transparency (0.40–3.00 m), eastward and northward seawater velocity (−0.20–0.15 m/s and −0.20–0.20 m/s), moderate productivity (1000–3000 mg/m²), and zooplankton carbon (0.20–6.00 g/m²). Habitat factor importance varied seasonally—salinity, depth, and net primary productivity dominated in spring; bottom temperature and productivity in summer/autumn; salinity and transparency in winter. Spatially, high-suitability areas peaked in autumn (70% total suitable habitat), concentrating near the Yangtze Estuary, northern Jiangsu coast, and Zhoushan Archipelago. This study emphasizes the need to prioritize these areas for protection and inform proliferation and release schemes for Chinese sturgeon. It also demonstrates the efficacy of remote sensing for mapping essential habitats of migratory megafauna in complex coastal ecosystems and provides actionable insights for targeted conservation strategies. Full article