Search Results (566)

Dew constitutes a component of the near-surface water balance, but its large-scale fractal dynamical properties remain poorly documented across Africa. This study estimates dew amounts and investigates their fractal and multifractal behavior under African climatic conditions using gridded ERA5 datasets from 1993 to 2022. The Rescaled-Range (R/S) method, Multifractal Detrended Fluctuation Analysis (MFDFA), and the Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) algorithm are used. Hurst exponent (Hu) and the multifractal spectrum width (ω) are evaluated at daily and monthly scales over the full period and two sub-periods (1993–2007 and 2008–2022). The results reveal pronounced spatial heterogeneity in dew distribution. Daily mean amounts range between 0 and 0.18 mm, corresponding to annual accumulations reaching up to ~85 mm·yr⁻¹ in humid coastal, equatorial, and sub-equatorial regions, while remaining below 0.5 mm·yr⁻¹ in hyper-arid deserts. The continental mean annual amount is ~35.5 mm·yr⁻¹. The Hurst exponent exhibits values between zero and one, indicating region-dependent persistent and anti-persistent behaviors. This suggests that prediction schemes based on preceding values may be suitable for dew time series prediction in African regions exhibiting persistent characteristics. The multifractal spectrum width (ω), reaching values of up to 10, highlights strong scaling heterogeneity, particularly at the monthly timescale. These findings indicate that African dew dynamics exhibit significant long-range dependence and multifractal variability, providing new insights into the intrinsic temporal structure of dew and into appropriate approaches for its forecasting. Full article

Academic advising is fundamental to student success, yet the rapid integration of Artificial Intelligence (AI) and Machine Learning (ML) is fundamentally transforming the delivery of academic support. While predictive models and Recommendation Systems (RS) are becoming more accessible, the existing literature remains fragmented across diverse technical architectures and institutional objectives, preventing a clear understanding of the field’s evolution. In view of this, we present a Systematic Literature Review (SLR) of AI-driven academic advising, adhering to the PRISMA 2020 framework. We analyzed 27 peer-reviewed studies published between 2018 and 2025 to synthesize methodological trends and functional applications. Our findings reveal that while most systems prioritize pathway recommendations via classical ML or hybrid architectures, Early-Warning Systems (EWS) remain anchored in predictive classification. Furthermore, a nascent shift toward Generative AI (GenAI) indicates a move toward more interactive advising, though transparency and evaluation standards remain inconsistent. This review identifies a critical tension between algorithmic performance and institutional interpretability. We conclude by proposing a research agenda that emphasizes the need for cross-context validation and the development of socio-technical frameworks that integrate AI into existing higher education management structures. Full article

Soil respiration (Rs) plays a pivotal role in carbon cycling within semi-arid ecosystems. In our millet field experiment, we measured Rs, autotrophic respiration (Ra), heterotrophic respiration (Rh), water consumption (ET), yield (Y), water use efficiency (WUE), and key soil environmental properties to examine the effects of supplemental irrigation and selenium application on Rs dynamics and to clarify the controlling factors. The experiment was conducted from 2023 to 2024 with four treatments and three replicates per treatment each year. These treatments comprised conventional rainfed (CK), supplemental irrigation (SI, 50 mm), rainfed with Se addition (CS, 67.84 g·hm⁻²), and supplemental irrigation with Se addition (SIS). SI increased CO₂ emissions in the millet field, whereas selenium application (CS) suppressed them. Ra was the dominant component of Rs and was 1.03–4.01 times greater than Rh. SI and CS significantly affected cumulative CO₂ emissions through Ra (p < 0.05), whereas their effects on Rh were minor. The CS treatment resulted in the lowest cumulative CO₂ emissions at 4233 and 4009 g·m⁻² in 2023 and 2024, respectively. Diurnal variation patterns of Rs, Ra, and Rh differed across millet growth stages. Both supplemental irrigation and selenium application improved soil water retention, soil enzyme activity, and soil organic matter (SOM), and moderated soil temperature. Classification and Regression Tree (CART) algorithm analysis revealed that Ra was primarily driven by soil temperature, with a feature weight of 86.95% determined by CART based on machine learning, whereas Rh was mainly influenced by soil enzyme activity, with a feature weight of 76.11%. The CS treatment enhanced production while promoting emission mitigation. The combined SIS treatment achieved the highest WUE and maintained a lower Rs than SI. These findings suggest an environmentally sustainable management strategy for millet production in semi-arid regions. However, due to the limited number of parcels in this study, further field-scale validation and additional experimental research involving multiple levels of supplemental irrigation and Se addition are necessary. Full article

Real-time path planning for Unmanned Surface Vehicles (USVs) in complex marine environments remains challenging due to unstructured environments, ocean current disturbances, and dynamic obstacles. This paper proposes an improved Hybrid Safety and Reward-Sensitive Twin Delayed Deep Deterministic Policy Gradient (H_RS_TD3) algorithm and constructs a high-fidelity simulation environment based on GEBCO bathymetric data and CMEMS ocean current data. The path planning problem is formulated as a Markov Decision Process (MDP), where the state space incorporates multi-beam radar perception, ocean current disturbances, and relative goal information, while the action space outputs continuous thrust and rudder commands subject to vehicle dynamics constraints. The proposed framework integrates a risk-aware hybrid safety decision architecture, a Trajectory Predictor Network (TPN), a Curvature-driven Advantage-based Prioritized Experience Replay (CDA-PER) mechanism, and an uncertainty-aware conservative Q-learning strategy to enhance navigation safety, sample efficiency, and policy stability. Comprehensive simulations demonstrate that, compared with baseline deep reinforcement learning methods, the proposed approach achieves faster convergence, improved stability, and competitive path efficiency while consistently maintaining sufficient obstacle clearance and millisecond-level inference latency, validating its effectiveness and practical feasibility for safe USV navigation in realistic dynamic marine environments. Full article

Global climate change is increasing extreme rainfall events, and severe floods are becoming more frequent. Flood storage and detention basins (FSDBs) are an important part of the flood control system in China. They play a key role in regional flood emergency response and regulation. Therefore, accurate simulation of flood evolution after the activation of FSDBs is urgently needed. This study proposes a high-accuracy flood evolution simulation method that combines terrain clustering and physical propagation constraints. We first build a 2 m resolution digital elevation model (DEM) using GF-7 stereo imagery and laser altimetry data. We then introduce an improved superpixel segmentation algorithm (TSLIC). This method reduces the number of computational units while preserving key micro-topographic features. It groups high-resolution grids into terrain units with similar elevation characteristics and continuous spatial structure. Based on these terrain units, we develop a flood evolution model called RS-CFPM. The model combines flow velocity estimated from the Manning equation with flood propagation speed derived from radar remote sensing. It uses a water balance framework and includes a propagation time delay constraint. This design helps overcome the limitation of traditional static inundation methods that ignore flood travel time. We apply the proposed method to simulate the flood inundation process during the “23·7” extreme basin-scale flood event in the Haihe River Basin. Comparison with multi-temporal radar observations shows that the errors of simulated water level and inundation extent in the Dongdian FSDB are both within 10%. The computational efficiency is also improved by more than 60% compared with traditional methods. This study provides a new approach for rapid and accurate simulation of flood inundation processes in FSDBs under emergency conditions. The method can support flood emergency operation and decision-making. Full article

Remote sensing (RS) images, characterized by their large size and rich texture, require algorithms capable of effectively integrating both global and local features for compression. However, existing Learned Image Compression (LIC) approaches face distinct bottlenecks. While Transformer-based architectures typically suffer from heavy computational loads, standard State Space Models (SSMs) often incur prohibitive memory costs when processing high-resolution inputs. To address these limitations, we propose MambaLIC, a novel RS image compression network that integrates the efficient long-range modeling of SSMs with the local modeling ability of CNNs. In this paper, we introduce an innovative Remote Sensing State Space Model (RS-SSM) module, which combines visual SSM with dynamic convolution for remote sensing image compression. This integration facilitates effective interaction between local and global information, thereby enhancing the performance of RS image compression. Furthermore, we propose an SSM attention-based (SSA-based) spatial-channel context model for better entropy modeling. Compared to Transformer-CNN mixed architectures, MambaLIC reduces computational complexity by 63.9% and achieves superior rate-distortion (RD) performance. Consequently, compared to the latest SS2D-based method MambaIC, MambaLIC achieves substantial efficiency gains, saving 78.8% in memory usage. Experimental results demonstrate that MambaLIC achieves state-of-the-art (SOTA) performance, outperforming VVC (VTM-17.0) by 14.22%, 18.48%, and 17.47% in BD-rate on UC-Merced, LoveDA, and xView datasets, respectively. Full article

This study presents an intercomparison of planetary boundary layer height (PBLH) estimates derived from three distinct approaches: the Morphological Image Processing Approach (MIPA) algorithm applied to ground-based lidar measurements, European Centre for Medium-Range Weather Forecasts (ECMWF) Reanalysis 5th Generation (ERA5) and Modern-Era Retrospective Analysis for Research and Applications Version 2 (MERRA-2) reanalysis model outputs, and radiosonde (RS) observations, this latter being taken as reference. The intercomparison was conducted during three measurement episodes, encompassing a total of 153 h (6 days), as part of the Boundary Layer Extensive Campaign with muLti-instrumentaL Analysis (BELLA), carried out in spring and early summer 2024 at the CNR-IMAA Atmospheric Observatory (CIAO) in southern Italy (40.60N, 15.72E). The study provides insights into the performance and reliability of these PBLH estimation approaches under diverse atmospheric scenarios. Visual and statistical analyses of selected case studies indicate that MIPA often tracked the aerosol layering structure and diurnal PBLH evolution more closely than ERA5 and MERRA-2, particularly during convective growth and evening transitions. On the other hand, it is found that ERA5 provides more accurate estimates of the nighttime PBLH, where MIPA shows poor nighttime estimation capabilities. Quantitative comparison against radiosonde data reveals that MIPA reaches a weighted root mean square error ($RMS{E}_w$) of $380\pm 41$ m with a coefficient of determination ($R^2$) of $0.68\pm 0.16$, while ERA5 shows an $RMS{E}_w$ of $292\pm 72$ m and an $R^2$ of $0.81\pm 0.11$; and MERRA-2 shows an $RMS{E}_w$ of $631\pm 124$ m and an $R^2$ of $0.34\pm 0.21$. By combining MIPA daytime and ERA5 nighttime PBLH, the overall results are improved, obtaining an $R^2=0.86\pm 0.08$ and an $RMS{E}_w$ of $213\pm 40$ m. This intercomparison highlights the strengths and limitations of each method and demonstrates the benefits of combining complementary PBLH retrieval techniques. The findings contribute to refining boundary layer monitoring methodologies and provide guidance for operational atmospheric observation networks. Full article

Synthetic aperture radar (SAR) serves as a prominent remote sensing (RS) technology, permitting continuous maritime surveillance regardless of weather or time. Although deep learning-based detectors have achieved promising results in SAR imagery, the majority of current algorithms rely on axis-aligned bounding boxes, which are insufficient for accurately representing arbitrarily oriented ships, especially under speckle noise, complex coastal clutter, and real-time deployment constraints. To address this limitation, we propose a YOLO-based oriented ship detector (YOSDet). Specifically, a dynamic aggregation module (DAM) is incorporated into the backbone to enhance feature representation against non-stationary backscattering. An objective-guided detection head (OGDH) is developed to decouple classification and localization, complemented by a localization quality estimator (LQE) to calibrate classification confidence by mitigating the impact of scattering center shifts. Comparative evaluations conducted on three public SAR ship detection benchmarks validate the effectiveness of YOSDet. The proposed model outperforms existing detectors, achieving $mAP$ scores of 96.8%, 88.5%, and 67.3% on the SSDD+, HRSID, and SRSDD-v1.0 datasets, respectively. Furthermore, the consistency of our approach in both nearshore and offshore environments is confirmed through rigorous quantitative and qualitative assessments. Full article

National forest inventory (NFI) data are often collected over a 5-year or 10-year period, meaning some are already outdated by the time the complete results are available. This study assesses changes in growing stock volume (GSV, m³/ha) using hybrid estimation supported by Sentinel-2 metrics. It focuses on constructing a model for estimating the change in GSV using NFI plot data and bitemporal remotely sensed auxiliary data, where such data are available for both points in time ($t_1\mathrm{a}\mathrm{n}\mathrm{d}{t}_2$), and unitemporal data for which remotely sensed auxiliary data are available only for $t_2$. A machine-learning approach based on the random forests (RFs) algorithm was used to predict plot-level GSV change. The original data for $t_2$ and $t_3$ were first used to evaluate the accuracy of the change prediction at the plot level, after which the predicted changes were applied to update the plot-level GSV to predict plot-level GSV at $t_3$, which was then assessed against the observed plot-level GSV at $t_3$. Predicted change was assessed with the Mean Average Annual Volume Change (MAAVC) method, representing the average annual change in GSV over a given period. The results indicate that at the plot level, the bitemporal model produced GSV change estimates with low accuracy (R² = 0.26, RMSE = 4.06 m³/ha, and MAE = 3.26 m³/ha), while the unitemporal model achieved R² = 0.40, RMSE = 3.64 m³/ha, and MAE = 2.65 m³/ha when predicting the $t_1-t_2$ GSV change. Using the predicted change to predict plot-level GSV at $t_3$, the MAAVC based on field data yielded R² = 0.91 and RMSE = 45.11 m³/ha, while the RS unitemporal yielded R² = 0.73 and RMSE = 83.79 m³/ha, and the bitemporal yielded R² = 0.72 and RMSE = 83.61 m³/ha. Mean population GSV at $t_3$, estimated from the RF models, was 254.61 and 255.19 m³/ha for the unitemporal and bitemporal models, respectively. Monte Carlo simulations with a novel stopping criterion were then used to estimate total standard errors, which were 10.48 and 10.40 m³/ha for the unitemporal and bitemporal models, respectively, incorporating both model prediction uncertainty and sampling variability. A test of significance revealed a significant effect of the proposed method on the estimated mean population GSV at $t_3$ (p < 0.001). Conclusively, MAAVC and spatiotemporal RS methods provide a robust framework for predicting GSV at $t_3$ using Estonian NFI and Sentinel-2 data. Full article

Background: This study evaluated morphological and functional differences among eyes with retinitis pigmentosa (RP) classified according to fundus autofluorescence (FAF) patterns. Methods: A total of 146 eyes from 73 patients with RP were analysed. Based on FAF imaging, eyes were classified as having regular hyperautofluorescent rings (n = 23), irregular rings (n = 76), or absent rings (n = 47). Participants underwent best-corrected visual acuity (BCVA), contrast sensitivity, 10–2 and 30–2 static perimetry, multifocal electroretinography (mfERG), and optical coherence tomography (OCT). FAF morphometrics included ring diameters and area. Results: Eyes with a regular FAF ring demonstrated significantly better visual function than those with irregular or absent rings, including higher BCVA (p < 0.001 and p = 0.001) and greater contrast sensitivity (both p < 0.001). The mfERG amplitude density in the first ring was higher in regular than irregular FAF patterns (p = 0.034). Eyes with irregular FAF showed more advanced visual field loss, with lower mean deviation on 10–2 (p = 0.042) and 30–2 perimetry (p = 0.027). In the regular-ring group, the ellipsoid zone was predominantly intact (p = 0.012). The hyperautofluorescent ring area correlated positively with mfERG amplitude density in the first and second rings (Rs = +0.573, p = 0.016; Rs = +0.736, p = 0.001) and with macular volume (Rs = +0.667, p = 0.003). Conclusions: FAF patterns reflect central retinal functional and structural impairment in RP. Therefore, incorporating FAF imaging into the diagnostic algorithm is valuable for monitoring disease progression. Full article

To address the computational-efficiency bottlenecks of Hybrid A* and its bidirectional variant in long-distance parking and narrow-slot scenarios, an improved bidirectional Hybrid A* algorithm is presented. First, the cohesion cost is reformulated in a vector-space representation. Distance and heading-consistency terms are evaluated using dot products, which eliminates trigonometric operations and reduces the overhead of node evaluation. Second, an RS (Reeds–Shepp) cost template is constructed on a sparse grid of key nodes. Neighborhood costs are approximated with Euclidean-distance correction. In addition, a geometry reachability-based trigger is designed for analytic RS connections to avoid redundant analytic linking and unnecessary RS curve computations. Third, a KD-tree spatial index is introduced to accelerate nearest-neighbor queries in the Voronoi potential field, and vehicle corner coordinates are updated in a vectorized manner to improve the efficiency of potential-field evaluation. Simulation results in parallel and perpendicular parking show that, compared with the baseline bidirectional Hybrid A* algorithm, RS computations are reduced by 98.7% and 97.8%, respectively, while total planning time is shortened by 63.2% and 57.5%, with stable path quality. These results indicate that the proposed method effectively mitigates the dominant computational costs of bidirectional Hybrid A* in complex parking tasks and improves the efficiency and real-time performance of automatic parking path planning. Full article

Utilizing video surveillance in mines to identify unsafe behaviors of miners is an important technical means for preventing coal mine accidents and achieving safety control. However, the complex underground environment (such as chaotic backgrounds, personnel occlusion, etc.) severely affects the estimation of human postures and feature extraction, resulting in low accuracy of unsafe behavior identification. To address this issue, this paper proposes a miner unsafe behavior recognition algorithm based on improved AlphaPose (RS-AlphaPose). Firstly, the improved real-time detection Transformer (RTDETR) is adopted to replace the original target detection network. Through the deformable attention mechanism and the addition of small target detection layers, the target detection ability in complex scenes is enhanced. Secondly, the sliding window attention and channel attention mechanisms are integrated in the posture estimation network to strengthen multi-scale semantics and global context correlation, thereby improving the accuracy of skeleton extraction in the presence of occlusion. Finally, the spatio-temporal graph convolution network is introduced to construct the spatio-temporal dependency of the skeleton sequence, capturing the temporal features of dynamic behaviors. On the COCO2017 posture dataset, the average accuracy of posture estimation of this algorithm reaches 72.5%, which is 2.2% higher than the basic AlphaPose model. On the self-built miner dynamic behavior dataset, the average recognition accuracy for typical unsafe behaviors such as climbing and crossing reaches 94.5%, which is 4.5% higher than the basic model. The experiments show that the proposed algorithm can effectively solve the interference problems in complex underground environments, significantly improve the accuracy of dynamic unsafe behavior recognition of miners, and provide a reliable technical solution for coal mine safety production. Full article

Accurate medium-term evapotranspiration (ET) forecasting is critical for irrigation scheduling and hydrological assessments. To address biases in numerical weather prediction (NWP) systems, we developed a hybrid GWO_XGB model integrating Extreme Gradient Boosting (XGBoost) with Gray Wolf Optimizer (GWO) for bias correction. Using the corrected data, we evaluate four hybrid models—Support Vector Machine (SVM) and XGBoost, each optimized with either GWO or Grasshopper Optimization Algorithm (GOA)—for 1- to 10-day ET forecasts across 11 farmland stations in Europe and North America (2003–2014). The results showed that the GWO_XGB model demonstrated the best comprehensive performance (average RMSE = 0.476 mm d⁻¹, R² = 0.829), while the GWO_SVM model performed the weakest (average RMSE = 0.572 mm d⁻¹, R² = 0.761). Forecast accuracy of Rs and VPD declined with lead time, with the 1-day forecasts being most accurate (RMSE range: 2.005–3.061 MJ mm d⁻¹). Using calibrated NWP data, the highest 1-day forecast accuracy was achieved (average RMSE = 0.715 mm d⁻¹), with GWO_XGB remaining the best (1–3 days average RMSE = 0.667 mm d⁻¹; 10-day cumulative forecast RMSE = 0.698 mm d⁻¹). Overall, the GWO_XGB model combined with NWP calibration provides reliable short- to medium-term ET forecasts for agricultural water management. Full article

Background: Age-related macular degeneration (AMD) is a major cause of vision loss, yet publicly available Optical Coherence Tomography (OCT) datasets lack demographic diversity, particularly from South Asian populations. Existing datasets largely represent Western cohorts, limiting AI generalizability. Moreover, raw OCT volumes contain redundant spatial information and speckle noise, hindering efficient analysis. Methods: We introduce BanglaOCT2025, a retrospective dataset collected from the National Institute of Ophthalmology and Hospital (NIOH), Bangladesh, using Nidek RS-330 Duo 2 and RS-3000 Advance systems. We propose a novel preprocessing pipeline comprising two stages: (1) A constraint-based centroid minimization algorithm automatically localizes the foveal center and extracts a fixed 33-slice macular sub-volume, robust to retinal tilt and acquisition variability; and (2) A self-supervised volumetric denoising module based on a Flip-Flop Swin Transformer (FFSwin) backbone suppresses speckle noise without requiring paired clean reference data. Results: The dataset comprises 1585 OCT volumes (202,880 B-scans), including 857 expert-annotated cases (54 DryAMD, 61 WetAMD, and 742 NonAMD). Denoising quality was evaluated using reference-free volumetric metrics, paired statistical analysis, and blinded clinical review by a retinal specialist, confirming preservation of pathological biomarkers and absence of hallucination. Under a controlled paired evaluation using the same classifier with frozen weights, downstream AMD classification accuracy improved from 69.08% to 99.88%, interpreted as an upper-bound estimate of diagnostic signal recoverability rather than independent generalization. Conclusions: BanglaOCT2025 is the first clinically validated OCT dataset representing the Bengali population and establishes a reproducible fovea-centric volumetric preprocessing and restoration framework for AMD analysis, with future validation across independent and multi-centre test cohorts. Full article

In this study, the non-destructive determination of pH, total soluble solids (TSS), total acidity (TA), reducing sugars (RS), seed total phenolic content (TPCD), and skin total phenolic content (TPCN) in Ugni Blanc grapes was performed using visible/near-infrared (Vis/NIR) spectroscopy coupled with chemometric quantitative analysis. Diffuse reflectance spectra in the 400–1507 nm range were measured using a handheld Vis–NIR spectrometer, after which the dataset was partitioned using the SPXY algorithm, accounting for joint X-Y distances. Six spectral preprocessing methods and three modeling algorithms, Partial Least Squares (PLS), Support Vector Machine Regression (SVR), and Convolutional Neural Network (CNN), were used to construct quantitative models based on full-wavelength and feature-wavelength data. Feature-based models outperformed full-spectrum models for TA, RS, and TPCN, whereas full-spectrum models performed better for pH, TSS, and TPCD. The optimal models achieved ${\mathit{R}}_{\mathit{p}}^{\mathit{2}}$ values of 0.940, 0.957, 0.913, 0.889, 0.917, and 0.871 and RPD values of 4.074, 4.798, 3.397, 2.998, 2.904, and 2.786, correspondingly. The findings highlight the applicability of Vis/NIR spectroscopy for the accurate and non-destructive prediction of key physicochemical indicators in Ugni Blanc grapes. Full article