Search Results (415)

Reference evapotranspiration (ET₀) represents the atmospheric demand for water from a well-watered vegetated surface and is a key component of the hydrological cycle and agricultural water management. This study evaluated the performance of seven machine learning (ML) models: linear regression (LR), Random Forest (RF), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), Extreme Gradient Boosting (XGBoost), Decision Trees (DT), and Cubist, for predicting monthly FAO-56 Penman–Monteith ET₀ in Benin. The target variable was calculated from data collected at six synoptic stations over the 2017–2021 period. Ten remote-sensing and topographic predictors were used: MODIS Land Surface Temperature (LST), six Sentinel-2 optical vegetation indices (NDVI, EVI, NDMI, NDWI, MSI, NDRE), elevation, and cyclic month encoding. Models were trained on the 2017–2019 period and evaluated on an independent temporal test set (2020–2021). All models showed positive predictive performance, with the BMA ensemble achieving the highest accuracy (RMSE = 7.0% of mean ET₀, R² = 0.802), followed by Cubist (RMSE = 7.3%, R² = 0.787) and DT (RMSE = 7.5%, R² = 0.776). The seven models were combined via Bayesian Model Averaging (BMA) with posterior weights estimated by the EM algorithm to produce 1 km monthly ET₀ maps for Benin for 2025. BMA-derived inter-model standard deviation provided spatially explicit uncertainty estimates, revealing that prediction uncertainty is greatest in the northern Sudanian zone during the dry season. The ET₀ target variable was constructed as a hybrid product combining station temperature observations with solar radiation, wind speed, and vapor pressure deficit extracted from the TerraClimate gridded reanalysis dataset; this methodological choice is discussed as a study limitation. Full article

This study develops a cooperative multi-agent deep reinforcement learning (MARL) framework for simulation-based cost-overrun mitigation in smart grid construction projects under dynamic engineering uncertainty. Modern smart grid construction involves digital substations, renewable-energy-connected facilities, flexible transmission assets, intelligent monitoring systems, and geographically distributed contractors; therefore, cost escalation is driven by sequential interactions among procurement, schedule execution, equipment deployment, supervision, weather, logistics, and price volatility. The proposed framework models procurement management, construction scheduling, equipment allocation, and supervision-control units as decentralized agents embedded in a calibrated construction simulation environment. The environment is parameterized from 42 smart grid construction projects in Henan Province, China and generates disturbance scenarios involving weather efficiency loss, transportation delay, market-price volatility, labor shortage, and supply-chain interruption. A hybrid DQN–PPO mechanism represents mixed decision structures: value-based DQN modules handle discrete managerial choices such as task acceleration, supplier switching, and procurement timing, whereas PPO modules adjust continuous resource-allocation and recovery-intensity decisions. A hierarchical reward function combines local departmental objectives with project-level penalties for cost overrun, schedule delay, idle resources, recovery expenditure, safety risk, and environmental impact. The experimental protocol uses 30 paired random seeds, nonparametric bootstrap confidence intervals, Holm-adjusted Wilcoxon signed-rank tests, and comparison with deterministic optimization, rolling-horizon MPC, stochastic/robust optimization, single-agent DRL, MAPPO, MADDPG/MATD3, QMIX, and HAPPO baselines. The proposed framework achieves a mean cost-overrun rate of 6.83% and a mean schedule deviation of 16.82 days, reducing cost overrun by 18.7% and schedule deviation by 21.4% relative to rule-based construction management under the reported disturbance settings. The calibrated simulation evidence establishes a statistically evaluated decision-support framework for coordinated construction cost control and provides an artifact-level reproducibility pathway through configuration files, random-seed lists, anonymized synthetic benchmarks, and aggregated logs. Full article

Regenerating fragile historical contexts requires choices of repurposing that combine heritage protection, continuity of use and managerial feasibility, in the presence of multiple objectives and stakeholders with different preferences. This study develops and tests an MCDA-based decision-support framework for the ex-ante selection of adaptive reuse scenario applied to Craco (Italy) and Palazzo Carbone-Rigirone. Craco and Palazzo Carbone-Rigirone were selected as a critical case because they combine heritage abandonment, geomorphological fragility, cultural visibility, weak local services and the need for a feasible management model. The methodology involves: (i) defining four adaptive reuse scenarios; (ii) constructing nine criteria that integrate socio-economic impacts, safety/security, cultural attractiveness, compatibility with the property and economic–financial feasibility; (iii) elicitation of weights using a hybrid approach, combining the decision-maker’s macro priorities and the social quota derived from questionnaires using normalised indicators of satisfaction/dissatisfaction and priorities for improvement; (iv) classification using the Weighted Sum Model and TOPSIS under two normalizations (distributive and ideal) and two variants (relative and absolute). The results show convergence between methods and stability of the ranking, with a preference for the multifunctional scenario oriented towards cultural services and socialising. In the case of Craco, adaptive reuse offers advantages compared with purely conservative, passive musealization or tourism-only strategies. The study concludes that MCDA is useful as a transparent pre-selection tool and supports the alignment of local needs and institutional priorities; its robustness can be strengthened with sensitivity analyses and policy scenarios. Full article

Early diagnosis of Diabetic Retinopathy (DR) is critical for preventing irreversible vision loss, but precise lesion annotation by ophthalmologists is the dominant cost in building any clinical-grade DR detection model. The structural problem in real hospital settings is not labeling cost per se, but expert availability: ophthalmologists’ time is bounded by clinical duties, so the active-learning (AL) cycle can iterate only a handful of times in practice. We frame this constraint explicitly and ask which AL designs work best under a tight expert budget. We propose Virtuous Cycle, a Human-in-the-Loop (HITL) pipeline that integrates (i) a YOLOv8x-based object detector for microaneurysms, hemorrhages, and exudates, (ii) four AL sampling strategies (Average Confidence, Random, Hybrid-Diversity, Monte Carlo Dropout), and (iii) an in-hospital annotation platform (Diavision Studio) in which clinicians refine AI pre-labels rather than draw from scratch. We evaluate Virtuous Cycle on a real-world fundus dataset from the National Medical Center (NMC) across eight AL rounds, expanding the labeled pool from 81 images (R0) to 481 images (R8) within the actual expert-time budget of two ophthalmologists. Across three independent random seeds, random sampling dominates at cold start (mean mAP@50 $0.14\to 0.25$ over R0–R1), whereas Hybrid-Diversity converges to the highest mAP@50, Precision, and Recall by R7 (431 images; mAP@50 $0.40$, Precision $0.55$, Recall $0.41$), with MC Dropout close behind; by R8, the labeled pool is exhausted and all strategies converge to the same final model. A clinician crossover analysis of 36 paired clinical images, controlling for per-clinician speed bias and per-image difficulty bias, shows no statistically significant difference in overall per-image labeling time between AI-assisted and manual annotation ($p=0.52$), but a statistically significant increase in confirmed lesion detections under AI assistance ($p=0.0058$), driven predominantly (84–$100\%$ of the net increase) by microaneurysms, the lesion type most prone to being missed unaided. The results indicate that, under expert-budget constraints, AL strategy choice should be staged: random sampling for cold start, uncertainty-and-diversity sampling once the model has matured, and that AI assistance trades a modest, lesion-burden-dependent time cost for a measurable gain in the sensitivity of microaneurysm detection. Full article

Background: Breast cancer remains a leading cause of cancer-related mortality, and reliable computational decision support is increasingly viewed as a complement to expert pathological assessment rather than a replacement for it. Variational quantum classifiers (VQCs) and Quantum Support Vector Machines (QSVMs) have recently been promoted as candidate models for medical classification, yet most published comparisons rely on internal hold-out validation alone and report only a single point estimate of discrimination, omitting calibration, decision-analytic value, and explainability—three ingredients that any clinically credible model must furnish. Methods: We assembled a complete quantum–classical machine learning pipeline and evaluated it under a deliberately stringent protocol designed to expose, rather than conceal, the limitations of current Noisy Intermediate-Scale Quantum (NISQ)-era models. The analytical hypothesis was conservative and stated in advance; in light of saturated classical baselines on this benchmark, we did not anticipate a quantum advantage in raw discrimination, and we framed the study as a methodological probe rather than as a competition. Using the Wisconsin Diagnostic Breast Cancer (WDBC) dataset (n = 569) for development and an independent Wisconsin Original (WBC) cohort (n = 683) for external validation, we benchmarked five classical learners (XGBoost, LightGBM, CatBoost, RandomForest, RBF-SVM), two quantum models (an eight-qubit VQC implemented in PennyLane and a ZZ-feature-map QSVM implemented in Qiskit), and a stacked hybrid ensemble. The evaluation framework combined Optuna-driven hyperparameter optimisation, internal–external cross-validation, and external validation on the independent WBC cohort. Robustness and interpretability were then probed through circuit depth and embedding rotation ablation, depolarising noise stress tests, learning curve and feature stability analysis, decision curve analysis, and dual SHAP-based explanations covering both a direct tree-based explanation and a quantum surrogate. Reporting followed the TRIPOD + AI guideline. Results: On the internal test partition, RBF-SVM achieved the highest discrimination (AUC = 0.998), with XGBoost, LightGBM, CatBoost, the hybrid ensemble, and the VQC clustering between 0.992 and 0.996; the QSVM with a ZZ-fidelity kernel underperformed substantially (AUC = 0.727). Pairwise tests for correlated ROC curves indicated that most differences among top models were not statistically significant. On the external WBC cohort, model rankings reorganised, as RBF-SVM (AUC = 0.986, 95% CI 0.946–0.997), RandomForest (0.985, 95% CI 0.945–0.996), VQC (0.983, 95% CI 0.942–0.995), and the hybrid ensemble (0.982, 95% CI 0.941–0.995) all retained near-ceiling discrimination with extensively overlapping confidence intervals. Ablation analysis demonstrated that the choice of embedding rotation is decisive—Z-rotation embeddings collapsed VQC performance to chance levels (AUC ≈ 0.50), whereas X- and Y-rotations preserved it. Depolarising noise up to p = 0.10 had a negligible effect on the VQC, and SHAP analyses converged on worst concave points, mean concave points, and worst area as the dominant predictors across both classical and quantum models. Decision curve analysis showed positive net benefit for both classical and hybrid models across the clinically meaningful threshold range, exceeding both the treat-all and treat-none reference strategies throughout. Conclusions: In the present regime, the principal contribution of QML is not raw discrimination—modern classical learners are already at the data ceiling—but the construction of a rigorous, reproducible, externally validated, and interpretable benchmarking framework in which quantum models can be fairly compared with their classical counterparts. Because evaluation was confined to curated benchmark datasets rather than real-world clinical populations, the interpretability and net benefit findings reported here should be read as benchmark-level evidence and not as a demonstration of readiness for clinical deployment. Full article

Graphite nozzles remain the dominant choice for small hybrid and solid rocket motors operating on laboratory and university budgets, owing to their low cost, ease of machining, and rapid turnaround during iterative design campaigns. These same programs, however, must contend with the fact that graphite erodes through coupled thermochemical and mechanical mechanisms when exposed to the oxidizing species generated by high-energy propellant combustion, and the resulting throat-area growth fundamentally alters the time histories of chamber pressure, thrust, and delivered specific impulse. This paper presents a nozzle-erosion reconstruction model that extracts the time-resolved throat area from coupled thrust and chamber-pressure measurements using the thrust coefficient relationship, scales the reconstructed area history against pre- and post-test throat measurements, identifies the onset and rate of erosion, and accounts for variable sensor lag between the thrust-stand and pressure-transducer signal chains. The model is exercised on two complementary sets of laboratory-scale GOX/ABS hybrid hot-fire data that together span roughly two orders of magnitude in total throat-area change and peak chamber pressures from 0.5 to 3.4 MPa: a controlled three-operating-point campaign conducted in support of the NASA Plume-Surface Interaction (PSI) program, and a set of higher-pressure firings from the laboratory development series in which the technique was matured. Reconstructed erosion-onset times, erosion rates, and total throat-diameter change are reported for each firing, the reconstruction accuracy is characterized as a function of erosion magnitude. A correlation of graphite erosion with chamber pressure is examined across the combined envelope. The results demonstrate the robustness of the reconstruction technique and provide a reusable framework for post-test reconstruction of transient nozzle geometry in rocket-engine ground testing. Full article

Optimal sizing of hybrid renewable energy systems for desert camps is a multi-objective problem that must account for cost, reliability, component degradation, and uncertainty. This paper introduces an improved multi-objective neural architecture search (IMONAS) framework for hybrid nanogrid sizing in the desert environment of Hafr Al-Batin, Saudi Arabia. The framework combines neural optimization, stochastic uncertainty modeling, and explicit battery degradation modeling, a combination not addressed in the reviewed studies for this application. Six test cases are examined by varying uncertainty assumptions, battery degradation, and the annual duration of uncertain operation. For each case, IMONAS provides Pareto-front solutions that specify the photovoltaic, diesel generator, battery autonomy, and inverter choices while minimizing the cost of energy (COE) and the loss of power supply probability (LPSP). IMONAS is compared with the original MONAS and five other multi-objective optimization methods. In addition to visual Pareto-front comparisons, the assessment uses Pareto-dominance indicators, namely the C-metric and an aggregated score derived from pairwise C-metric comparisons across the algorithms and cases. The results provide a validated sizing framework for remote arid-region nanogrids under uncertainty and battery degradation. Full article

Precision agriculture increasingly relies on machine learning applied to high-resolution data acquired by unmanned aerial vehicles (UAVs) to support crop monitoring, stress detection, and yield forecasting. This survey presents a structured review of machine learning methods for UAV-enabled precision agriculture and organizes over 100 peer-reviewed studies within a unified four-dimensional taxonomy defined by sensing modality, data type, model family, and analytical task. The taxonomy enables systematic comparison across RGB, multispectral, hyperspectral, LiDAR, and IoT data sources and across classical machine learning, deep learning, hybrid sequential models, and emerging transformer-based architectures. We analyze how modeling choices interact with data characteristics to influence robustness, cross-environment generalization, computational efficiency, and deployment feasibility on UAV and edge platforms. Recurring challenges include limited labeled data, domain shift across seasons and fields, multimodal heterogeneity, occlusion, and real-time processing constraints. We identify emerging research directions, including data-efficient learning, representation-level multimodal fusion, domain adaptation, lightweight architectures for embedded deployment, and uncertainty aware decision support. By formalizing the landscape through a unified taxonomy, this survey provides a foundation for designing scalable, robust, and deployable machine learning systems for next-generation precision agriculture. Full article

Accurate forecasting of groundwater level (GWL) fluctuations in drought-prone and data-limited regions remains a major challenge for sustainable groundwater management. The complexity of nonlinear and dynamic groundwater systems, influenced by spatiotemporal variability and limited observational data, further complicates the development of reliable predictive models. Groundwater is a critical resource for irrigation and domestic use in drought-prone northwestern Bangladesh, requiring accurate forecasting of GWL dynamics for sustainable management. To address this challenge, the present study evaluates seven deep learning (DL) approaches: GRU, LSTM, hybrid LSTM–GRU, and their Genetic Algorithm (GA)- and Particle Swarm Optimization (PSO)-variants, using time-series data from nine observation wells. The developed models were benchmarked against the widely used univariate time-series forecasting model, ARIMA. Model performance varied spatially. The GA-LSTM model performed best at Bagha–Arani (R = 0.879, IOA = 0.906, NRMSE = 0.149), while the standalone LSTM achieved superior results at Bagmara–Auchpara (R = 0.940, IOA = 0.958, NRMSE = 0.155). All DL models outperformed the benchmark ARIMA model across all locations. Overall, the best models achieved R = 0.724–0.940, IOA = 0.707–0.958, NRMSE = 0.149–0.285, and MAD = 0.369–1.369 m, indicating strong predictive skill. Optimization (GA, PSO) improved accuracy, particularly for GRU-based models, though LSTM remained competitive in several sites. Hybrid and optimized models required higher computational cost due to iterative tuning but often yielded improved accuracy. A CRITIC–EDAS multi-criteria decision-making framework, based on six statistical metrics, identified no universally superior model; instead, optimal choices varied by location. Selected models successfully forecasted future GWL trends, capturing temporal variability. The integrated modelling–ranking framework provides a robust, scalable approach for groundwater management in data-limited, drought-affected regions. Full article

Deep learning has significantly advanced image super-resolution (SR), yet many state-of-the-art models remain too computationally expensive for resource-constrained devices. This paper demonstrates that a highly parameter-efficient design can achieve comparable performance to the very deep super-resolution network (VDSR) with a tiny fraction of parameters. Starting from the classic VDSR architecture (2016), we systematically evaluate three design choices: depthwise separable convolution (DSConv), Hybrid Attention Transformer (HAT), and a local residual connection (LR). HAT provides no performance gain—an honest negative result supported by controlled experiments (increased training, different reduction ratios, and standard convolution baseline). In contrast, LR alone yields a 0.20 dB improvement without introducing any extra parameters. Consequently, we discard HAT and propose DSConv+LR. Our model contains only 49,217 parameters—about 7.4% of VDSR—yet attains a peak signal-to-noise ratio (PSNR) of 35.21 dB on Set5 (×2), which is 99.7% of VDSR’s performance (35.33 dB). On additional benchmarks (Set14, BSD100, and Urban100), DSConv+LR maintains similar relative performance (within 0.12 dB of VDSR). Perceptual loss (AlexNet features, lower better) is 0.2556, slightly better than VDSR (0.2717). We acknowledge that modern lightweight networks such as cascaded residual attention network (CARN) and information multi-distillation network (IMDN) achieve 2–3 dB higher PSNR at the cost of 9–14× more parameters. This work advocates a minimalist approach while honestly reporting both its strengths and limitations. Full article

The Leaf Area Index (LAI) serves as a vital biophysical parameter for quantifying vegetation dynamics and ecosystem functioning. While traditional LAI retrieval methods face challenges in handling nonlinear spectral-vegetation relationships, machine learning (ML) approaches offer promising alternatives through their data-driven adaptability. This study presents a comprehensive cross-site assessment of 13 ML algorithms for LAI estimation, leveraging ground observations from 98 sites worldwide. Our systematic assessment reveals three key findings: First, ensemble methods consistently outperformed other approaches, with Gradient Boosted Tree Regression (GBTR) achieving superior accuracy (R² = 0.647, RMSE = 0.899) and robustness (ΔR² < 0.05 beyond n = 69 training samples). Second, Gaussian Process Regression (GPR) illustrated exceptional stability across varying training sizes (R² = 0.607 ± 0.012), highlighting its reliability for data-limited scenarios. Third, all tested ML models substantially outperformed operational LAI products, with the GBTR model demonstrating superior explanatory power (external validation R² = 0.647) compared to MODIS; its R² value had increased by 0.489. This optimal balance of accuracy, computational efficiency, and resistance to overfitting positions GBTR as a reasonable choice for large-scale LAI mapping. These findings underscore ML’s promising potential in vegetation monitoring while highlighting the need for hybrid approaches that combine physical principles with data-driven learning to address current limitations in extreme-value estimation and ecological generalizability. Full article

Airport systems rely on tightly connected digital and physical components, so cyber disruptions can affect both service performance and passenger movement. Existing airport simulation studies often focus on either queue-based passenger processing or pedestrian movement but rarely combine both in a framework suited for cyber-resilience analysis. This paper presents a hybrid simulation framework that integrates discrete-event simulation (DES), JuPedSim-based microscopic pedestrian modeling, and structured large language model (LLM) decision support to examine how cyber disruptions propagate through passenger-facing airport operations. The DES layer models service processes such as check-in, information desks, and security screening, while the pedestrian layer models movement, congestion, route choice, and spatial occupancy. Under degraded display or guidance conditions, the LLM generates structured passenger-level post-security decisions, such as going directly to the gate, checking a display, asking staff, waiting, visiting optional activity areas, or first moving to a wrong intermediate area. The framework is evaluated through a 500-passenger terminal case study with one baseline case and four disruption cases. Results show that check-in and security degradation produce the largest throughput loss, queue growth, and completion-time increase, while guidance degradation mainly affects post-security behavior. Spatial heatmaps further show where bottlenecks emerge and how congestion shifts across the terminal. Additional Rotterdam checkpoint validation, Palma benchmark analysis, and LLM ablation results support the framework’s ability to reproduce plausible queue, timing, throughput, and behavior-sensitive disruption patterns. The study provides a practical methodology for exploratory airport cyber-resilience assessment under coupled service, movement, and degraded-guidance conditions. Full article

The transition to a hydrogen-based energy economy emphasizes the potential of hydrogen as a fuel for plug-in hybrid electric vehicles (PHEVs). The performance of a hydrogen engine within a PHEV depends on the choice of its operating modes, which influence both efficiency and emissions. This study proposes a method for developing engine operating lines (EOLs) on engine maps based on minimizing nitrogen oxide (NOx) emissions while considering constraints on maximum engine power. A total of 15 EOLs are proposed for configurations with both constant and variable maximum engine power. Using mathematical modeling of PHEV operation under the Worldwide Harmonized Light Vehicles Test Cycle (WLTC), the impact of EOL selection on engine characteristics, as well as on battery and generator parameters, is analyzed. For a comprehensive evaluation of EOL effectiveness, five criteria are introduced, considering fuel energy consumption, NOx emissions, wear, mechanical fatigue, and noise, vibration, and harshness (NVH). The Analytic Hierarchy Process (AHP) and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) are applied to determine the weighting factors of the criteria and to rank the proposed EOLs, thereby identifying the most efficient configurations. The results show that, for the base hydrogen engine configuration, selecting appropriate operating modes alone enables NOx emissions to be reduced significantly below Euro 6 limits, without any hardware modifications or exhaust aftertreatment. Full article

This article examines remittances not only as financial transfers but also as datafied political objects shaped by measurement, modelling and presentation infrastructures. Using the UK–Romania corridor, we compare observed personal remittance receipts published by the National Bank of Romania (NBR) with model-based bilateral estimates associated with World Bank/KNOMAD data. The article develops an analytical framework that links quantification, metric power, algorithmic governmentality, hybrid media circulation and emerging bottom-up social policies. It then shows how nominal values, real values at constant 2021 prices, year-by-year changes, moving-average smoothing, employment-scaled scenarios and transfer-balance indicators generate different representations of diaspora contribution, welfare substitution and national economic performance. Rather than assigning final authority to one dataset, the article demonstrates how calculation and presentation choices become communicative interventions. The conclusion emphasises methodological transparency and the need to connect remittance statistics to both political communication and community-level welfare practices. Full article

Phishing and malicious websites are a serious threat on the internet. Attackers use fake links to trick users and steal their private information. Detecting these links is difficult because attackers change their tricks often. Many old methods cannot detect new or hidden threats. Some recent models use deep learning (DL), but they are large, slow, and hard to use in real-time systems. In this paper, we present a lightweight and accurate model called MiniLM-CNNLSTM. It combines a small transformer model (MiniLM) with a hybrid DL network using Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) layers. The transformer learns the meaning of URLs. The CNN finds important patterns. The LSTM captures the order of characters. We also add handcrafted features that help the model detect tricky URLs. We test our method on two public datasets: the Phishing Site URLs dataset and the Malicious URLs dataset from Kaggle. We use 3-fold cross-validation and early stopping to ensure fair and stable results. The MiniLM-CNN-LSTM model outperformed previous benchmarks by achieving an average three-fold cross-validation accuracy of 98.98%, a precision of 98.63%, a recall of 98.29%, an F1-score of 98.46%, and a false positive rate of 0.68%. The proposed model has a higher accuracy, precision, recall, F1-score and a lower false positive rate, which enhances the accuracy by 1.88, precision by 3.77, recall by 4.17 and decreases the false positive rate by 61.58% compared with the strongest baseline (Distil BERT + CNN-LSTM), showing significant practical improvements. The results show that our approach is fast, small, and highly effective. It can detect phishing and malicious links with high accuracy. This makes it a good choice for real-time security systems like browsers, email filters, or firewalls. Full article