Search Results (1,857)

Accurate aircraft trajectory prediction is fundamental to air traffic management, operational safety, and intelligent aerospace systems. With the growing availability of flight data, deep learning has emerged as a powerful tool for modeling the spatiotemporal complexity of 4D trajectories. This paper presents a comprehensive review of deep learning-based approaches for aircraft trajectory prediction, focusing on their evolution, taxonomy, performance, and future directions. We classify existing models into five groups—RNN-based, attention-based, generative, graph-based, and hybrid and integrated models—and evaluate them using standardized metrics such as the RMSE, MAE, ADE, and FDE. Common datasets, including ADS-B and OpenSky, are summarized, along with the prevailing evaluation metrics. Beyond model comparison, we discuss real-world applications in anomaly detection, decision support, and real-time air traffic management, and highlight ongoing challenges such as data standardization, multimodal integration, uncertainty quantification, and self-supervised learning. This review provides a structured taxonomy and forward-looking perspectives, offering valuable insights for researchers and practitioners working to advance next-generation trajectory prediction technologies. Full article

Pollution and freshwater scarcity, coupled with the energy sector’s continued dependence on fossil fuels, constitute a dual challenge to sustainable development. A promising response is biosystems that jointly address wastewater treatment and the production of renewable products. This review centers on a managed consortium of aquatic macrophytes and microalgae, in which the spatial architecture of plant communities, rhizosphere processes, and the photosynthetic activity of microalgae act in concert. This configuration simultaneously expands the spectrum of removable pollutants and yields biomass suitable for biorefinery, thereby linking remediation to the production of energy carriers and bioproducts within a circular bioeconomy. The scientific novelty lies in treating the integrated platform as a coherent technological unit, and in using the biomass “metabolic passport” to align cultivation conditions with optimal valorization trajectories. The work offers a practical framework for designing and scaling such consortia that can reduce the toxicological load on aquatic ecosystems, return macronutrients to circulation, and produce low-carbon energy carriers. Full article

Cropland abandonment, a global challenge, necessitates comprehensive monitoring to achieve the zero hunger goal. Prior monitoring approaches to cropland abandonment often face constraints in resolution, time series, drivers, prediction, or a combination of these. Here, we proposed an artificial intelligence framework to comprehensively monitor cropland abandonment and tested the framework in Hengyang City, China. Specifically, we first mapped land cover at 30 m resolution from 1985 to 2023 using Landsat, stable sample points, and a machine learning model. Subsequently, we constructed the extent, time, and frequency of cropland abandonment from 1986 to 2022 by analyzing pixel-level land-use trajectories. Finally, we quantified the drivers of cropland abandonment using machine learning models and predicted the spatial distribution of cropland abandonment risk from 2032 to 2062. Our results indicated that the abandonment maps achieved overall accuracies of 0.88 and 0.78 for identifying abandonment locations and timing, respectively. From 1986 to 2022, the proportion of cropland abandonment ranged between 0.15% and 4.06%, with an annual average abandonment rate of 1.32%. Additionally, the duration of abandonment varied from 2 to 38 years, averaging approximately 14 years, indicating widespread cropland abandonment in the study area. Furthermore, 62.99% of the abandoned cropland experienced abandonment once, 27.17% experienced it twice, and only 0.23% experienced it five times or more. Over 50% of cropland abandonment remained unreclaimed or reused. During the study period, tree cover, soil pH, soil total phosphorus, potential crop yield, and the multiresolution index of valley bottom flatness emerged as the five most important environmental covariates, with relative importances of 0.087, 0.074, 0.068, 0.050, and 0.043, respectively. Temporally, cropland abandonment in 1992 was influenced by transportation inaccessibility and low agricultural productivity, soil quality degradation became an additional factor by 2010, and synergistic effects of all three drivers were observed from 2012 to 2022. Notably, most cropland had a low abandonment risk (mean: 0.36), with only 0.37% exceeding 0.7, primarily distributed in transitional zones between cropland and non-cropland. Future risk predictions suggested a gradual decline in both risk values and the spatial extent of cropland abandonment from 2032 to 2062. In summary, we developed a comprehensive framework for monitoring cropland abandonment using artificial intelligence technology, which can be used in national or regional land-use policies, warning systems, and food security planning. Full article

The recent growth of generative artificial intelligence (AI) has brought new possibilities and revolutionary applications in many fields. It has also, however, created important ethical and security issues, especially with the abusive use of deepfakes, which are artificial media that can propagate very realistic but false information. This paper provides an extensive bibliometric, statistical, and trend analysis of deepfake research in the age of generative AI. Utilizing the Web of Science (WoS) database for the years 2014–2024, the research identifies key authors, influential publications, collaboration networks, and leading institutions. Biblioshiny (Bibliometrix R package, University of Naples Federico II, Naples, Italy) and VOSviewer (version 1.6.20, Centre for Science and Technology Studies, Leiden University, Leiden, The Netherlands) are utilized in the research for mapping the science production, theme development, and geographical distribution. The cutoff point of ten keyword frequencies by occurrence was applied to the data for relevance. This study aims to provide a comprehensive snapshot of the research status, identify gaps in the knowledge, and direct upcoming studies in the creation, detection, and mitigation of deepfakes. The study is intended to help researchers, developers, and policymakers understand the trajectory and impact of deepfake technology, supporting innovation and governance strategies. The findings highlight a strong average annual growth rate of 61.94% in publications between 2014 and 2024, with China, the United States, and India as leading contributors, IEEE Access among the most influential sources, and three dominant clusters emerging around disinformation, generative models, and detection methods. Full article

The European Union (EU) has positioned itself as a global leader in digital regulation, with landmark frameworks such as the Digital Services Act (DSA), the Digital Markets Act (DMA), and relevant AI Act. These initiatives reflect the EU’s ambition to balance technological innovation with consumer protection, market fairness, and digital sovereignty. Yet, a growing body of research suggests that the EU may be lagging its global competitors—namely the United States and China—when it comes to scaling high-growth digital enterprises and attracting investment in frontier technologies. This study investigates the paradox of regulation versus innovation in the EU by comparing key performance indicators such as R&D investment, venture capital availability, and digital innovation output with those of the U.S. and China. Drawing on datasets from WIPO, the OECD, IMF, and the World Bank, the paper incorporates both cross-sectional and longitudinal analysis to assess the EU’s digital trajectory. Findings suggest that while the EU excels in institutional frameworks and research output, structural barriers—such as regulatory fragmentation and underdeveloped capital markets—limit its global competitiveness. The article concludes by discussing policy implications and the need for adaptive governance to maintain Europe’s digital leadership. Full article

This study focuses on the design and implementation of an Adaptive High-Order sliding mode control for by-wire ground vehicle systems. The controller integrates advanced technologies such as Active Front Steering (AFS) and Rear Torque Vectoring (RTV), aimed at enhancing vehicle dynamics. However, lateral velocity remains one of the most challenging variables to measure, even in modern vehicles. To address this limitation, a High-Order Sliding Mode (HOSM)-based observer with adaptive gains is proposed. The HOSM observer provides critical information for the operation of the dynamic controller, ensuring the tracking of desired references. Compared with traditional observers, the proposed adaptive HOSM observer achieves finite-time convergence of state estimation errors and exhibits enhanced robustness against external disturbances, as confirmed through simulation results. The adaptive gains dynamically adjust the system parameters, enhancing its precision and flexibility under changing environmental conditions. This dynamic approach ensures efficient and reliable performance, enabling the system to respond effectively to complex scenarios. The stability of the dynamic HOSM controller with adaptive gain is analyzed through a Lyapunov-based approach, providing solid theoretical guarantees. Its performance is evaluated using detailed simulations conducted in CarSim 2017 software. The simulation results demonstrate that the proposed controller is highly effective in ensuring accurate trajectory tracking. Full article

Smart tourism destinations, shaped by the integration of tourism and information technology, have become a central theme in international academic research. This study employs bibliometric methods using CiteSpace to conduct co-authorship, co-citation, keyword co-occurrence, and burst analyses, with the aim of mapping the knowledge structure and research evolution of the field. Drawing on 232 articles from the Web of Science Core Collection (2013–2025), the results reveal a shift from technology-centered approaches toward themes of visitor experience, collaborative governance, and sustainable development. The Universitat d’Alacant (Spain) and The Hong Kong Polytechnic University (China) have emerged as leading research hubs, with Ivars-Baidal and colleagues as major contributors. Foundational studies by Buhalis and Gretzel continue to shape the domain. Keyword trends highlight increasing attention to technological efficiency and sustainable ethics. Overall, the study traces the developmental trajectory of smart tourism destinations, proposes a systematic knowledge framework, and identifies future directions for theoretical integration and methodological innovation. The findings provide both conceptual insights for academic research and strategic guidance for destination governance and policy. Full article

The continuous growth in global demand for mineral resources and the increasing difficulty of mineral exploration have created bottlenecks for traditional mineral prediction methods in handling complex geological information and large amounts of data. This review aims to explore the latest research progress in machine learning technology in the field of large-scale mineral prediction from 2016 to 2025. By systematically searching the Web of Science core database, we have screened and analyzed 255 high-quality scientific studies. These studies cover key areas such as mineral information extraction, target area selection, mineral regularity modeling, and resource potential evaluation. The applied machine learning technologies include Random Forests, Support Vector Machines, Convolutional Neural Networks, Recurrent Neural Networks, etc., and have been widely used in the exploration and prediction of various mineral deposits such as porphyry copper, sandstone uranium, and tin. The findings indicate a substantial shift within the discipline towards the utilization of deep learning methodologies and the integration of multi-source geological data. There is a notable rise in the deployment of cutting-edge techniques, including automatic feature extraction, transfer learning, and few-shot learning. This review endeavors to synthesize the prevailing state and prospective developmental trajectory of machine learning within the domain of large-scale mineral prediction. It seeks to delineate the field’s progression, spotlight pivotal research dilemmas, and pinpoint innovative breakthroughs. Full article

Product development in academia and its technology transfer are crucial activities for the sustainable development of society. Nevertheless, transferring academic research is a complex process that requires mature research results aligned with market needs. Existing approaches frequently focus on process management and the relationships between system participants, disregarding the importance of maturity assessment in the product development cycle. This paper proposes an approach, comprising a Framework and a Method, to guide the progressive maturation of ICT products from universities and to facilitate their transfer to productive and social sectors. The Framework maps the innovation trajectory from research to commercialization by phases, tasks, activities, and stakeholders. The Method articulates agile cycles inspired by Scrum, with a continuous TRL-based maturity assessment and sustained market engagement to align academic product development with market demands. Innovation experts evaluated the approach using content validity indices and qualitative content analysis. The results showed a high level of agreement on the relevance and usefulness of the Framework and the Method, and qualitative feedback informed improvements in presentation and clarity. In summary, the proposed approach provides a practical roadmap for aligning university research with market needs and enhancing the conversion of prototypes into transferable and marketable solutions. Full article

Bamboo (subfamily Bambusoideae, Poaceae) ranks among the fastest-growing plants on Earth, achieving up to 1 m day⁻¹, significantly faster than other fast growing woody plant such as Eucalyptus (up to 0.6 m day⁻¹) and Populus (up to 0.5 m day⁻¹). Native to Asia, South America and Africa, and cultivated on approximately 37 million ha worldwide, bamboo delivers multifaceted environmental, social, and economic benefits. Historically central to construction, handicrafts, paper and cuisine, bamboo has evolved into a high-value cash crop and green innovation platform. Its rapid renewability allows multiple harvests of young shoots in fast-growing species such as Phyllostachys edulis and Dendrocalamus asper. Its high tensile strength, flexibility, and ecological adaptability make it suitable for applications in bioenergy (bioethanol, biogas, biochar), advanced materials (engineered composites, textiles, activated carbon), and biotechnology (fermentable sugars, prebiotics, biochemicals). Bamboo shoots and leaves provide essential nutrients, antioxidants and bioactive compounds with documented health and pharmaceutical potential. With a global market value exceeding USD 41 billion, bamboo demand continues to grow in response to the call for sustainable materials. Ecologically, bamboo sequesters up to 259 t C ha⁻¹, stabilizes soil, enhances agroforestry systems and enables phytoremediation of degraded lands. Nonetheless, challenges persist, including species- and age-dependent mechanical variability; vulnerability to decay and pests; flammability; lack of standardized harvesting and engineering codes; and environmental impacts of certain processing methods. This review traces bamboo’s trajectory from a traditional resource to a strategic bioresource aligned with Industry 5.0, underscores its role in low-emission, circular bioeconomies and identifies pathways for optimized cultivation, green processing technologies and integration into carbon-credit frameworks. By addressing these challenges through innovation and policy support, bamboo can underpin resilient, human-centric economies and drive sustainable development. Full article

Oases in arid regions are crucial for sustaining agricultural production and ecological stability, yet few studies have simultaneously examined the coupled dynamics of land use/cover change (LUCC), carbon emissions, and ecosystem service value (ESV) at the oasis–agricultural scale. This gap limits our understanding of how different land use trajectories shape trade-offs between carbon processes and ecosystem services in fragile arid ecosystems. This study examines the spatiotemporal interactions between land use carbon emissions and ESV from 1990 to 2020 in the Wensu Oasis, Northwest China, and predicts their future trajectories under four development scenarios. Multi-period remote sensing data, combined with the carbon emission coefficient method, modified equivalent factor method, spatial autocorrelation analysis, the coupling coordination degree model, and the PLUS model, were employed to quantify LUCC patterns, carbon emission intensity, ESV, and its coupling relationships. The results indicated that (1) cultivated land, construction land, and unused land expanded continuously (by 974.56, 66.77, and 1899.36 km²), while grassland, forests, and water bodies declined (by 1363.93, 77.92, and 1498.83 km²), with the most pronounced changes occurring between 2000 and 2010; (2) carbon emission intensity increased steadily—from 23.90 × 10⁴ t in 1990 to 169.17 × 10⁴ t in 2020—primarily driven by construction land expansion—whereas total ESV declined by 46.37%, with water and grassland losses contributing substantially; (3) carbon emission intensity and ESV exhibited a significant negative spatial correlation, and the coupling coordination degree remained low, following a “high in the north, low in the south” distribution; and (4) scenario simulations for 2030–2050 suggested that this negative correlation and low coordination will persist, with only the ecological protection scenario (EPS) showing potential to enhance both carbon sequestration and ESV. Based on spatial clustering patterns and scenario outcomes, we recommend spatially differentiated land use regulation and prioritizing EPS measures, including glacier and wetland conservation, adoption of water-saving irrigation technologies, development of agroforestry systems, and renewable energy utilization on unused land. By explicitly linking LUCC-driven carbon–ESV interactions with scenario-based prediction and evaluation, this study provides new insights into oasis sustainability, offers a scientific basis for balancing agricultural production with ecological protection in the oasis of the arid region, and informs China’s dual-carbon strategy, as well as the Sustainable Development Goals. Full article

Absolute linear encoders have emerged as a core technical enabler in the fields of high-end manufacturing and precision displacement measurement, owing to their inherent advantages such as the elimination of the need for homing operations and the retention of position data even upon power failure. However, there remains a notable scarcity of comprehensive review materials that can provide systematic guidance for practitioners engaged in the field of absolute linear encoder measurement technology. The present study aims to address this gap by offering a practical reference to professionals in this domain. In this research, we first systematically delineate the three fundamental categories of measurement principles underlying absolute linear encoders. Subsequently, we analyze the evolutionary trajectory of coding technologies, encompassing the design logics and application characteristics of quasi-absolute coding (including non-embedded and embedded variants) as well as absolute coding (covering multi-track and single-track configurations). Furthermore, we summarize the primary error sources that influence measurement accuracy and explore the operational mechanisms of various types of errors. This study clarifies the key technical pathways and existing challenges associated with absolute linear encoders, thereby providing practitioners in relevant fields with a decision-making guide for technology selection and insights into future development directions. Moving forward, efforts should focus on achieving breakthroughs in critical technologies such as high fault-tolerant coding design, integrated manufacturing, and error compensation, so as to advance the development of absolute linear encoders toward higher precision, miniaturization, cost reduction, and enhanced reliability. Full article

Driven by the growing demand for sustainable resource utilization, the recovery of valuable constituents from spent lithium-ion batteries (LIBs) has attracted considerable attention, whereas conventional recycling processes remain energy-intensive, inefficient, and environmentally detrimental. Herein, an efficient and environmentally benign separation strategy integrating dielectrophoresis (DEP) and magnetophoresis (MAP) is proposed for isolating the primary components of “black mass” from spent LIBs, i.e., lithium iron phosphate (LFP) and graphite microparticles. A coupled electric–magnetic–fluid dynamic model is established to predict particle motion behavior, and a custom-designed microparticle separator is developed for continuous LFP–graphite separation. Numerical simulations are performed to analyze microparticle trajectories under mutual effects of DEP and MAP and to evaluate the feasibility of binary separation. Structural optimization revealed that the optimal separator configuration comprised an electrode spacing of 2 mm and a ferromagnetic body length of 5 mm with 3 mm spacing. Additionally, a numerical study also found that an auxiliary flow velocity ratio of 3 resulted in the best particle focusing effect. Furthermore, the effects of key operational parameters, including electric and magnetic field strengths and flow velocity, on particle migration were systematically investigated. The findings revealed that these factors significantly enhanced the lateral migration disparity between LFP and graphite within the separation channel, thereby enabling complete separation of LFP particles with high purity and recovery under optimized conditions. Overall, this study provides a theoretical foundation for the development of high-performance and environmentally sustainable LIBs recovery technologies. Full article

To address the challenge of asymmetric deformation and failure in the surrounding rock of main roadways within extra-thick coal seams caused by level differences under intense mining disturbance, this study systematically analyzed the evolution laws of principal stress fields, deviatoric stress fields, and their impact on surrounding rock stability in upper-, middle-, and lower-level roadways within a 20 m extra-thick coal seam during mining retreat. The analysis employed numerical simulation, similarity simulation, and field monitoring. Key findings include the following: ① As the working face advances, the principal stress vector lines deflect following a bias-unloading pattern, while the peak value of the deviatoric stress field (PVDSF) exhibits asymmetric bias-loading characteristics. The lower-layer roadway emerges as the primary load-bearing layer controlling surrounding rock stability. ② The evolution trend of the maximum principal stress vector orientation is consistent across different layers. The deflection trajectory manifests as “the deflection of the goaf side → the near layer orientation → the deflection of the solid coal side”. ③ The deviatoric stress peak zones (DSPZs) at all layers exhibit a characteristic “three-stage” evolution. The deviatoric loading pattern for the lower-layer roadway surrounding rock is the following: initial state double peak region crescent-shaped non-layer distribution type → the range of the bimodal region and the extreme value increased simultaneously, distributed in a non-layer manner → the asymmetrical distribution type of steep drop in the peak area of non-mining deviator stress. ④ The junctions between the mining-side rib and floor and the non-mining-side rib and roof were identified as critical control zones. An innovative zonal asymmetric directional anchoring control technology, “anchor cable foundation support + concrete floor + asymmetric reinforcing anchor cable support”, along with a “One Directional Penetration and Three Synergies” control methodology, was proposed. Field monitoring confirmed the significant effectiveness of the optimized support system. Full article

This article addresses the multifaceted challenges inherent in the development of the novel REEFS (Renewable Electric Energy From Sea) wave energy converter (WEC). Building on the submerged pressure differential principle, it frames similar WECs before focusing on REEFS that combines renewable energy generation with coastal protection, functioning as an artificial reef. The review follows chronological criteria, encompassing experimental proof-of-concept, small-scale laboratory modeling, simplified and advanced computational fluid dynamics (CFD) simulations, and the design of a forthcoming real-sea model deployment. Key milestones include the validation of a passive variable porosity system, demonstration of wave-to-wire energy conversion, and quantification of wave attenuation for coastal defense. Additionally, the study introduces a second patent-protected REEFS configuration, isolating internal components from seawater via an elastic enveloping membrane. Challenges related to scaling, numerical modeling, and funding are thoroughly examined. The results highlight the importance of the proof-of-concept as the keystone of the development process, underscore the relevance of mixed laboratory-computational approaches and emphasize the need for a balanced equilibrium between intellectual property safeguard and scientific publishing. The REEFS development trajectory offers interesting insights for researchers and developers navigating the complex innovation seas of emerging wave energy technologies. Full article