Search Results (11,266)

Smallholder farmers in South Africa face increasing climate variability, yet their agronomic decision-making depends on timely and reliable climate information. Although digital ICT platforms are expanding, limited evidence exists on how their effectiveness compares to human-based advisory systems. The study addresses this gap by examining the determinants of ICT-based climate information adoption using logistic regression and assessing its influence on agronomic decisions through propensity score matching (PSM). A cross-sectional survey and multistage sampling were used to collect data from 217 smallholder crop farmers in the Eastern Cape. The results indicate that 65% of farmers accessed climate information through ICT platforms, while 35% relied on human-based sources. The adoption of ICT-based information is driven by education, digital literacy, mobile network reliability, the perceived value of real-time updates, and smartphone ownership, whereas habitual dependence on traditional channels hinders digital uptake. PSM estimates show that ICT-based climate information is 10–15% less effective than human-based sources in shaping planting decisions, input use, and the timing of farm operations, likely due to digital literacy and infrastructure constraints. The study demonstrates that access to digital tools does not automatically translate into effective use and recommends a hybrid information model integrating digital platforms with trusted human intermediaries to strengthen climate resilience and agronomic decision-making. Full article

Geotechnical hazards such as landslides, subsidence, slope instability, and infrastructure deformation threaten rapidly urbanising and environmentally stressed regions worldwide, intensifying the need for scalable and intelligent monitoring systems capable of continuously observing complex Earth surface dynamics. Although multisensor remote sensing fusion has substantially expanded the observational capabilities of modern geotechnical monitoring through the integration of Synthetic Aperture Radar (SAR), optical imagery, Light Detection and Ranging (LiDAR), and environmental data, existing fusion pipelines remain subject to several well-documented constraints, including weak semantic alignment, limited temporal reasoning, and poor transferability across heterogeneous environmental conditions. This review synthesises the emerging transition from conventional sensor-centric fusion toward intelligent geospatial monitoring architectures centred on deep multimodal representation learning, transformer-based temporal reasoning, self-supervised learning, and geospatial foundation models. Particular emphasis is placed on how recent architectures are designed to better preserve coherent spatial, temporal, and contextual environmental relationships within unified latent representation spaces rather than through downstream handcrafted integration. The review further examines the growing role of multimodal transformers, masked autoencoders, contrastive learning, and large-scale geospatial foundation models in enabling scalable environmental reasoning, adaptive multimodal learning, and transferable geospatial intelligence across sensing modalities and geographic domains. Finally, remaining challenges involving uncertainty, explainability, computational scalability, and environmental generalisation are discussed alongside future research directions involving continual learning, physics-aware artificial intelligence, and autonomous geotechnical monitoring systems. Together, the reviewed literature suggests that multimodal Earth observation is evolving from passive environmental sensing toward adaptive geospatial intelligence systems capable of scalable hazard reasoning and autonomous environmental understanding. Full article

In light of the strong expansion of renewables, electrolysis may act as an alternative to conventional grid enforcement to overcome grid constraints in a timely and effective manner, as it creates additional flexible load and thus enables renewable production peaks to be absorbed. This paper examines whether hydrogen electrolysis can serve as a cost-effective alternative to conventional grid reinforcement in Austrian electricity distribution networks. It goes beyond the current state of the art by using three real-world case studies in Styria, using an integrated techno-economic framework combining distribution-grid simulations, market optimisation, PEM electrolysis modelling and cost–benefit analysis to compare the grid-supportive electrolysis against conventional grid enforcement. The results demonstrate that grid-supportive electrolysis can become competitive under suitable hydrogen market conditions. When operated in grid-supportive mode only, the capacity factor for the electrolysis lies below 5%. Economic viability emerges only when electrolysers are allowed to combine grid-supportive operation with market-driven hydrogen production. Thereby, the hydrogen price proves to be the key determinant: a hydrogen price above approximately 6 EUR/kg incentivises market-based operation and naturally resolves grid congestion without further intervention by the DSO. In some locations, smaller electrolysers (around 20–60% of the theoretically required size) deliver the best economic performance, recovering most curtailed renewable energy while limiting investment costs compared to conventional grid extension. Full article

Deep learning has been widely deployed in critical scenarios such as the Internet of Things (IoT), industrial sensing, network intrusion detection, and cyber-physical system monitoring, where model inference directly affects system security, operational reliability, and service continuity. However, existing adversarial example detection studies remain insufficient for practical IoT deployment, as their validation often overlooks endpoint resource constraints, heterogeneous data modalities, physical environmental interference, communication protocol specifications, adaptive attacks, and adversary capability models. Moreover, detection outcomes are rarely connected with deployment locations, computational overhead, formal security assurance, and subsequent response strategies, which limits their engineering applicability. To address these limitations, this review systematically synthesizes recent representative studies in adversarial example detection and constructs a unified analytical framework integrating detection evidence, IoT deployment feasibility, and adaptive-attack evaluation. Based on the source of detection evidence, existing methods are categorized into input-consistency-based, feature-statistics-based, predictive-uncertainty-based, model-reconstruction-based, runtime-context-aware, and multi-strategy fusion detection, while formal certification is discussed as an independent security-assurance dimension. The review further analyzes the principles, applicable conditions, limitations, compatibility conflicts with IoT deployment constraints, and typical failure modes of these methods. The analysis identifies four key challenges: the lack of IoT-native adaptive evaluation, limited anomaly-boundary identification and cross-modal generalization, insufficient deployment-time security assurance, and weak coordination between detection decisions and security responses. Future research should therefore emphasize feasible attack paradigms, hierarchical lightweight detection, reliable multimodal fusion, certifiable operational boundaries, and auditable end-to-end response mechanisms, thereby supporting the evaluation and deployment of adversarial example detection in IoT scenarios. Full article

This study develops and applies a GIS-based 3D visualization model for observed flooding and subsidence conditions to support preliminary spatial screening for sustainable urban land fund development in the rapidly urbanizing Binh Chanh area, Ho Chi Minh City, during the period of 2020–2024. Field-survey records, official flood records, topographic maps, InSAR-based subsidence information, rainfall and tidal records, cadastral data, urban land-use expansion data, and planning information were integrated in a GIS environment. A DEM was generated using IDW interpolation and used as the terrain base for overlaying observed flood-prone locations with elevation, subsidence, road networks, cadastral parcels, urban land-use expansion, and planned urban land fund development areas. The overlaid datasets were then visualized in ArcScene, and an integrated map of observed flooding, subsidence, and urban land-use planning to 2030 was created to support preliminary spatial screening for sustainable urban land fund development. The observed inventory shows an increase in recorded flood-prone locations from 12 in 2020 to 34 in 2024, with maximum recorded flood depth reaching approximately 1.0 m and the largest recorded inundated area approaching 56,000 m². Areas below 1.2 m elevation account for 80.30% of the study area, while the high and moderately high subsidence classes occupy 57.19%. The proposed approach provides a practical, parcel-linked 3D GIS visualization tool for organizing observed flood information, communicating spatial constraints, and supporting preliminary screening in data-limited urbanizing areas. Full article

In automated dry bulk terminal operations, accurate perception of the spatial pose of portal crane wire ropes is important for grab positioning and can provide geometric information for subsequent anti-sway control research. Vision-based measurements may be affected by metallic reflections, illumination variation, and dust occlusion, whereas inertial or mechanically coupled measurements may be affected by vibration and dynamic coupling. This study proposes a LiDAR-based method for wire rope point cloud segmentation and pose estimation using an improved PointNet++. Dual-LiDAR point clouds are aligned and filtered using a kinematic constraint-based Region of Interest (ROI) to reduce background redundancy. A Spatial Self-Attention (SSA) module is introduced to combine long-range semantic dependencies with local spatial weighting, improving the representation of sparse and fragmented wire rope points. The segmented wire rope points are separated by t–k-means clustering and fitted with spatial lines for pose estimation. The complete acquisition comprises 11,348 annotated frames: a 9458-frame model development dataset from 1000 complete operating cycles, and a separately retained 1890-frame independent engineering test set from 200 condition-specific operating sequences. The development dataset was divided into mutually exclusive training and validation partitions at the level of complete operating cycles, and checkpoint selection was performed only on the validation set. Three independent training runs with fixed random seeds were conducted. On the independent test set, PointNet++ achieved an F1-score of 87.5 ± 0.2% and an mIoU of 79.0 ± 0.2%, whereas the complete proposed method achieved an F1-score of 92.8 ± 0.2% and an mIoU of 86.6 ± 0.2%. These results characterize performance on independent operating sequences collected from the crane and sensor configurations represented in the dataset. The standalone segmentation stage achieved 111.9 FPS, whereas the complete processing pipeline required slightly more than 2 s per frame because of frame-by-frame KD-ICP fine registration. Full article

Soil organic carbon (SOC) is a key indicator of soil quality, farmland productivity, and the terrestrial carbon cycle. Visible and near-infrared (Vis-NIR) spectroscopy offers a rapid approach for SOC estimation, but wavelength point selection may disrupt continuous spectral structures, whereas conventional wavelength interval selection may fail to fully exploit complementary information across spectral regions. In this study, a synergistic interval-constrained Ridge regression framework, termed sicRidge, was developed for SOC prediction. Continuous candidate intervals were generated using a sliding-window strategy, and a dual-interval synergistic search with an overlap constraint was applied to identify complementary and low-redundancy interval combinations. The selected intervals were then used to construct Ridge regression models. Using Vis-NIR spectra from 168 soil samples, sicRidge was compared with full-spectrum Ridge regression, five wavelength point selection-based Ridge models, and several wavelength interval selection-related benchmark models. sicRidge achieved the best prediction performance using 140 selected bands, with an R²_P of 0.834, RMSE_P of 2.010 g kg⁻¹, RPD of 2.483, and RPIQ of 3.777. The optimal intervals were 570~649 nm and 1880~1939 nm. These results indicate that sicRidge can improve SOC prediction by preserving continuous spectral structures while exploiting complementary cross-region information. Full article

Sand Cat Swarm Optimization (SCSO) is a swarm intelligence algorithm characterized by a simple structure and a small number of control parameters. However, when solving complex optimization problems, SCSO suffers from several limitations, including an uneven initial population distribution, excessive dependence on the current best individual during the search process, insufficient local exploitation accuracy, and susceptibility to local optima. To address these limitations, a Collaborative Multi-Strategy Sand Cat Swarm Optimization algorithm (CMSCSO) is proposed. The good point set method is adopted to generate a uniformly distributed initial population. An adaptive random reuse strategy is designed to selectively inherit dimensional information from the best individual according to differences in individual fitness. A prey impatience coefficient is introduced to dynamically adjust the local search intensity according to the distance between the population and the current best solution. In addition, a refractive-mechanism-based opposition-based learning strategy for the worst individuals is incorporated to update low-quality individuals and improve the ability of the algorithm to escape from local optima. CMSCSO was evaluated using the 30-dimensional CEC2017 and 10-dimensional CEC2022 benchmark suites. Its performance was compared with that of SCSO and several recently developed metaheuristic algorithms. The experimental results show that CMSCSO achieved the best mean values on 24 of the 29 CEC2017 benchmark functions and on 10 of the 12 CEC2022 benchmark functions. In the Wilcoxon tests conducted on CEC2017 and CEC2022, CMSCSO achieved 220 and 90 statistically significant wins, respectively. It also ranked first in the Friedman tests for both benchmark suites. For engineering optimization problems, the results obtained from six types of engineering design problems demonstrate that CMSCSO can consistently obtain high-quality feasible solutions that satisfy the specified constraints. In two-dimensional and three-dimensional wireless sensor network coverage optimization problems, coverage rates of 96.30% and 89.54% were achieved. For photovoltaic model parameter identification, CMSCSO achieved the highest identification accuracy. The numerical and engineering test results demonstrate that CMSCSO provides high optimization accuracy, strong stability, and good adaptability to complex engineering problems. It can therefore serve as an effective solution method for optimization tasks in structural design, mechanical engineering, and other related fields. Full article

Industrial digital twins integrate physical objects, dynamic models, control systems, data analysis tools, 2D and 3D visualization, and existing software systems. Much research has focused on the functional composition of the digital twin, modeling, and application scenarios, while the organization of the digital twin as an evolving software system composed of technologically heterogeneous and autonomous subsystems remains insufficiently formalized. The goal of this study is to develop a conceptual composite architecture for an industrial digital twin, in which complex subsystems are viewed as highly interconnected and loosely coupled service components of a higher-order system. The research method is based on analogy, transfer, and adaptation of proven principles of distributed and microservice systems to the constraints of industrial digital twins. An architectural model is proposed that includes a physical object, a process model, SCADA subsystems, a unified data exchange subsystem, 2D and 3D representations, VR/AR components, and automated model building modules. The practical feasibility of the approach is demonstrated using a proof-of-concept digital twin of a methanol–ammonia co-production plant, integrating Honeywell UniSim Design R460.1, web-based SCADA, Unity, and specialized 2D and 3D representation generation modules. This demonstration confirms the feasibility of integrating independently developed subsystems and the technological heterogeneity of the solution, but does not constitute a production test of performance, scalability, or cost effectiveness. Requirements for contract stability, a consistent interaction environment, assigned data responsibility, version compatibility, and complete documentation are defined. Research limitations and areas for subsequent quantitative architecture validation are identified. Full article

Accurate traffic flow prediction is a core task in intelligent transportation systems because urban traffic observations are spatially distributed, temporally dynamic, and commonly held by different regional management entities. Existing centralized and local models remain limited when traffic data are non-independent and identically distributed across regions, and when raw data cannot be directly exchanged because of privacy, ownership, and communication constraints. To address these challenges, this study proposes a personalized similarity-aware federated spatiotemporal learning framework for multi-regional traffic flow prediction. The framework integrates three mechanisms: client-specific adaptation for regional distributional heterogeneity, adaptive delayed graph learning for dynamic congestion propagation, and similarity-aware federated aggregation for information-quality-based cross-client collaboration. Spatial dependency, temporal evolution, traffic-flow-theory-informed variables, road attributes, and temporal contextual features are jointly modeled without sharing raw client data. Experiments on controlled synthetic data and the Q-Traffic real-world dataset demonstrate that the proposed method consistently outperforms independent training, FedAvg, FedProx, FedSTN-inspired, and FedAGCN-inspired baselines. On the Q-Traffic grid-level setting, the proposed adaptive graph version reduces MSE by 35.3% compared with FedAvg, while the CNN version reduces MSE by 27.5%. Under the cluster-level setting, the adaptive graph version reduces MSE by 26.3% compared with FedAvg. Ablation, sensitivity, communication-cost, differential-privacy, and client-dropout analyses further show that the proposed framework improves predictive accuracy, cross-client stability, and robustness under heterogeneous federated traffic scenarios. Full article

Precise estimation of lithium-ion battery State of Health (SOH) is highly demanded for reliable battery management systems, lifetime prediction, and safety assurance in electric vehicle and energy storage applications. Traditional data-driven approaches such as multilayer perceptron (MLP) often suffer from poor generalization and may produce non-physical degradation trends due to the absence of domain knowledge constraints. To address these limitations, this work proposes a monotonic Physics-Informed Residual MLP neural network framework for SOH estimation using the NASA battery dataset (B0005, B0006, B0007, and B0018). The proposed model incorporates a physics-based monotonic degradation constraint by penalizing positive gradients of SOH with respect to cycle index, thereby enforcing physically consistent capacity fade behavior. A loss function is employed to improve robustness and enhance late-cycle learning. Experimental results demonstrate that the proposed approach achieves an RMSE of 0.0287, MAE of 0.0181, and MAPE of 2.69%, indicating accurate and stable SOH prediction across multiple degradation patterns. The use of physics-informed constraints markedly enhances deterioration consistency and diminishes overfitting relative to solely data-driven models. The proposed structure offers a faithful solution for State of Health estimation in practical battery management systems. Full article

Designing time-optimal trajectories for solar sail spacecraft is highly difficult due to the strong nonlinearity of the solar radiation pressure model, the attitude–orbit coupling, and the prevalence of local minima, which often lead to the failure of gradient-based solvers lacking adequate initial guesses. To address this issue, the present study proposes a two-stage hybrid optimization framework: a coarse-search stage uses B-spline-parameterized metaheuristics to identify a dynamically feasible trajectory, which then serves as a physics-informed warm start for direct-collocation-based gradient refinement, strictly satisfying the full nonlinear dynamics and terminal constraints. The methodology is validated through three increasingly difficult space missions: a rendezvous between Earth and Mars (Case A), a near-Earth asteroid rendezvous considering non-ideal optical reflection (Case B), and a Solar Polar Orbiter mission necessitating an $82.75$ inclination adjustment with a thermal safety constraint (Case C). Statistical evaluations reveal that no single metaheuristic dominates universally; each algorithm’s suitability is contingent on the problem’s constraint structure. The hybrid framework further shows a consistent advantage over stand-alone direct collocation: by redirecting the gradient solver toward favorable convergence basins, it locates transfer solutions that remain inaccessible from a cold start. Full article

Reliable Predictive Maintenance (PdM) in Industrial Internet of Things (IIoT) environments is challenged by severe class imbalance, heterogeneous sensor variables, inconsistent experimental protocols, and deployment constraints. This study proposes a Physics-Informed Benchmarking Framework that integrates engineering-guided feature construction, Mutual Information (MI)-based feature relevance analysis, standardized model development, and deployment-oriented evaluation within a unified and reproducible workflow. Using the AI4I 2020 Predictive Maintenance Dataset, Logistic Regression, Isolation Forest, Random Forest, and Extreme Gradient Boosting (XGBoost) were evaluated using identical feature representations, train–test partitions, preprocessing procedures, and imbalance-handling strategies. The engineered feature space incorporates thermal, mechanical, interaction, and degradation-related information derived from the original sensor measurements. The results show that tree-based ensembles provide the strongest overall performance under severe class imbalance. Random Forest achieved an accuracy of 0.986, an F1-score of 0.722, and a ROC-AUC of 0.983, providing the best balance between failure detection and false-alarm control. XGBoost achieved an accuracy of 0.978, a recall of 0.853, and the lowest inference latency of 0.35 ms, indicating its suitability for latency-sensitive IIoT deployment. These findings demonstrate that combining engineering-guided feature representation with a standardized evaluation protocol enables fair comparison of representative learning paradigms while preserving engineering interpretability and deployment relevance. Full article

Rockets were launched from a freely ascending balloon, and the attitude dynamics of the rockoon system were investigated. Compared with ground-based or aircraft-based launches, rockoons offer reduced aerodynamic drag and pressure losses, leading to higher maximum altitudes of sub-orbital trajectory and improved launch capacity to earth orbits. To ensure trajectory accuracy and flight safety, an azimuth control system based on a control moment gyroscope (CMG) was implemented. The launcher, suspended beneath a helium balloon, was equipped with a CMG device for active azimuth control. Three model rocket launches were conducted, and attitude data were obtained using multiple accelerometers installed on the rocket and launcher. The results confirmed that azimuth control remained effective during free ascent, with the azimuth error at ignition within 7° of the target in all three launches. Oscillatory motion was observed in roll and yaw angles. It was identified as rotation about the launcher’s principal inertia axis, indicating no significant impact on the rocket’s flight trajectory. Additionally, pitch-up behavior during launch due to rail friction was observed, consistent with previous studies. Frequency analysis showed that a double-pendulum model reproduced the measured first-mode frequency within approximately 2%, while the measured second-mode frequencies were higher than the predictions, indicating an increase in the effective pendulum length due to the relaxed constraint of the balloon suspension. Under free-flight conditions, the first mode was no longer observed within the measurable frequency band, consistent with the removal of the ground constraint. These findings provide an experimental characterization of the attitude dynamics of rockoon launches with active azimuth control. Full article

Effective sustainable environmental governance requires feedback between institutional risk management and lived public experience. We propose a hierarchical Topic–Aspect–Frame framework to compare pollution discourse across news and social media. Using 30,635 chunk-level Taiwanese Chinese texts collected from OpView Product Insight in May 2026, treated as an early summer one-month validation window, we analyze topic selection, aspect foregrounding, and frame-based risk construction. Category-balanced audits yielded conditional label precision among analyzable chunks of 91.3% for topics, 85.8% for aspects, and 90.1% for frames. Among 30,304 frame-eligible chunks, Governance/Regulation was more prevalent in news (gap = +4.47 pp; 95% CI = [+3.11, +5.88]), whereas Health and Lived Risk was more prevalent in social media (gap = −9.84 pp; 95% CI = [−10.68, −9.02]). Under the aspect-conditioned prototype design, sequential decomposition attributed the latter gap mainly to topic selection (−5.40 pp) and aspect foregrounding (−4.14 pp), with a smaller within-aspect component (−0.30 pp). Both core directions persisted across four fixed windows and 100 same-fraction subsamples. The framework offers a preliminary, auditable approach for identifying cross-media governance-experience mismatches, subject to seasonal, platform, denominator, and model-support constraints. Full article