Sea-level rise threatens coastal ecosystems, infrastructure, and populations worldwide. This scoping review examined methods for assessing sea-level rise impacts in the MENA region, including their strengths, limitations, geographic distribution, and research gaps. Eligible studies were English-language journal articles or conference papers published between 2010 and 2026 that empirically assessed sea-level rise impacts within the MENA region using a defined methodological approach. Scopus and the Web of Science (WoS) Core Collection were searched using terms related to sea-level rise, assessment technologies, and MENA countries. A total of 407 records were identified, with 250 remaining after duplicate removal and preliminary exclusions. Following title and abstract screening, 110 reports underwent full-text evaluation, and 87 were ultimately included. Data were charted using a structured framework and analyzed descriptively and thematically. The studies were classified into remote sensing and Geographic Information Systems (GISs), index-based assessments, numerical modelling, and artificial intelligence (AI) and data-driven methods. Remote sensing and GISs were the dominant approaches, primarily applied to inundation, shoreline change, land subsidence, and exposure mapping, with their reliability influenced by elevation accuracy and simplified treatment of flood connectivity. Index-based approaches supported vulnerability screening, though their outputs were sensitive to indicator selection, weighting, and classification thresholds. Numerical models represented coastal processes and infrastructure performance more explicitly, although sparse observations and calibration data limited their applicability. AI and data-driven methods were used for predictive analysis and dynamic exposure estimation, but their reliability depended on training-data quality, independent validation, and physically grounded interpretation. Research was mostly concentrated in Egypt and Morocco, while substantial geographic gaps persisted across several MENA coastlines. Future research should integrate validated high-resolution observations, relative sea-level change, process-based modelling, socioeconomic projections, and independently validated data-driven methods to support more reliable coastal planning and adaptation.
Accurate cycle-level battery-capacity tracking can support condition-based battery management, but it must be distinguished from state-of-health estimation and prospective long-horizon remaining-useful-life forecasting. This study formulates a bounded one-step-ahead task in which capacity at target cycle t is estimated using only health information extracted from completed cycles t−L to t−1. Four indirect features are constructed from voltage, current, and time-domain charge/discharge signals. Pearson correlation analysis across eight cells and feature-level ablation identify constant-current discharge time as the dominant capacity-related proxy under fixed-current protocols, while the remaining charging- and voltage-related features provide smaller complementary gains. An MDRSN-BiGRU-AM model is evaluated using chronological within-cell tracking, controlled M1–M4 architecture ablation, repeated seeded runs, and sensitivity analyses. The complete M4 model obtains average RMSE values of 0.0075 Ah on CALCE and 0.0116 Ah on NASA, corresponding to reductions of 17.6% and 15.9%, respectively, relative to M1 (BiGRU) within the architecture ablation. These results support bounded one-step capacity tracking under the evaluated laboratory protocols. Generalization to previously unseen cells, performance relative to fully specified conventional baselines, local capacity-increase regimes, and variable field conditions was not established and remains unresolved. EOL thresholds are used only as descriptive visual references, and no environmental or economic benefit is quantified.
There is ongoing debate about the value of infrastructure systems—energy, water, transport, waste, and communications—and how infrastructure investments should be prioritized to account for social, economic, and environmental wellbeing. The concept of an infrastructure system is inherently linked to interdependencies. Although infrastructure systems differ across countries and cities, they are all closely connected to transport, as movement involves both cost and utility. These systems ultimately exist to serve individuals, who assign value to them. To explore the full spectrum of value creation, which underpins business models, the relationship between individuals and transport infrastructure must be understood. This research tests the hypothesis that integrating economic, environmental, and social value dimensions within a unified business model provides a more comprehensive representation of infrastructure interdependencies than conventional economically focused approaches. Economic value was analyzed using principal component analysis of input–output tables, social value through structured interviews and statistical analysis, and environmental value using secondary data linked to economic demand in the infrastructure context of England, Scotland, Wales, and Northern Ireland. The proposed business model integrates social, economic, and environmental values, giving policymakers a clearer understanding of infrastructure system interactions and supporting more informed investment decisions that maximize societal value.
Monitoring whether metropolitan ecological spaces can sustain ecosystem functions while accommodating urbanization and economic activity is central to sustainability. Gross Ecosystem Product (GEP) accounting supports this by translating ecosystem contributions into spatially explicit indicators for assessment and territorial governance. This study developed a multi-temporal, raster-based GEP framework on a common 30 m accounting grid for the Changsha–Zhuzhou–Xiangtan Urban Agglomeration Green Heart across six observation years from 2000 to 2023. It integrated six regulating services and a tourism-related cultural contribution with Sen’s slope, a supplementary Mann–Kendall test, spatial-consistency and sensitivity analyses, and Geodetector. Total accounted GEP declined by 9.14%. Climate regulation and water conservation remained dominant, while the tourism-related cultural contribution ranked third by 2023. Farmland and forest were the principal land-cover contributors. Positive Sen’s slopes predominated spatially but were mostly weak and non-significant, despite the aggregate decline. Land-cover change and vegetation productivity showed the highest explanatory power. Spatial consistency improved at 500 m, and sensitivity to the 2023 land-cover proxy was limited. Overall, the framework provides a spatial sustainability assessment tool for identifying ecological decline and supporting cross-jurisdictional conservation, ecological compensation, and sustainable territorial governance.
Synergistic governance of pollution and carbon reduction is a critical pathway for promoting the comprehensive green transformation of economic and social development. Based on panel data from 30 Chinese provinces over the period 2006–2023, this study employs the super-efficiency SBM-DEA model to measure the synergistic efficiency of air pollution and carbon reduction (SE), and applies the Dagum Gini coefficient and spatial autocorrelation analysis to reveal its spatiotemporal differentiation characteristics. The modified gravity model and social network analysis are used to characterize the evolutionary patterns of the spatial network of synergistic efficiency of air pollution and carbon reduction (SEN). Furthermore, a two-way fixed-effects model and the Spatial Durbin Model are constructed to empirically examine the impact of new quality productivity (NQP) on SE and its spatial spillover effects. The main findings are as follows: First, SE exhibits an overall declining trend, with a clear gradient pattern of “East > West > Central > Northeast” and significant positive spatial agglomeration. Second, the linkage intensity of SEN has steadily increased, and inter-provincial synergistic connections have grown closer; however, the core–periphery structure remains stable, network density fluctuates at a persistently low level, and a multi-center balanced pattern has yet to emerge. Third, NQP significantly enhances SE, but green technological innovation exhibits a suppression effect along the transmission pathway. Fourth, the driving effect of NQP on SE demonstrates notable regional and resource-endowment heterogeneity, while also showing a significant positive spatial spillover effect. These findings offer policy implications for advancing regionally tailored synergistic governance of pollution and carbon reduction and for optimizing the structural configuration of inter-provincial synergistic networks.
The planktonic dispersal of Limnoperna fortunei larvae and the byssal attachment of juveniles and adults make this species a major invasive biofouling species in water-conveyance infrastructure, while artificial hydraulic connectivity further facilitates its spread. Dense colonization can reduce conveyance capacity, increase energy consumption, accelerate structural deterioration, and impair water quality, thereby posing multiple risks to infrastructure operation. This narrative and critical review synthesizes evidence from 110 publications retained after screening 537 records retrieved from the Web of Science Core Collection up to 30 June 2026. The review characterizes the stage-specific progression of L. fortunei biofouling from propagule input and early settlement to mature fouling and post-treatment residual risks. It compares the applicability of eDNA/qPCR assays, conventional field surveys, and remotely operated vehicle (ROV)-based image inspection, and evaluates the effectiveness and operational limitations of physical, chemical, coating-based, and biological control measures across different risk stages. Current management often targets individual stages, with limited linkage between monitoring results and subsequent intervention. Accordingly, we propose a risk-oriented decision pathway that integrates early warning, settlement confirmation, fouling-load assessment, targeted removal, and post-treatment verification while accounting for hydraulic safety, water-quality constraints, and asset accessibility. By aligning management actions with biofouling stage and asset condition, this framework provides a basis for more sustainable operation and maintenance of water-conveyance systems.
Tourism firms frequently invoke heritage, tradition, and place identity, yet cultural visibility does not show whether corporate narratives connect culture to organisational action, stewardship, or community value. This study develops and independently validates a relational measure of annual report cultural sustainability disclosure using 85 reports from 17 Chinese A-share tourism firms during 2021–2025. A frozen rule-based classifier was evaluated on 400 previously unseen narrative units coded independently by two authors. Intercoder kappa ranged from 0.810 to 1.000 across eight dimensions. In the 200-unit probability sample, confirmatory F1 was 0.982 for cultural symbols, 1.000 for organisational capability and consumption scenarios, and 0.977 for participation/benefit; naturally rare dimensions are reported descriptively. Applied to 26,131 punctuation-based narrative units, the classifier identified 3828 cultural symbol units, of which 2167 had a strict semantic link to capability, scenario, or partner content. The pooled isolation share was 43.4% (firm-cluster bootstrap 95% CI: 34.7–50.4%). Stewardship appeared in 220 units across 40 firm-years. Eleven strict same-unit community participation/benefit links were observed across 10 firm-years, increasing to 47 windows under an adjacent-unit sensitivity definition. Firm-level trajectories were heterogeneous: all Holm-adjusted sign test p-values were at least 0.717. Category-pair coverage was only weakly related to report length and remained highly correlated with equal-unit rarefaction. The study contributes a reproducible measurement architecture that separates cultural visibility, relational operationalisation, and documentary accountability. It does not verify implementation, consent, benefit distribution, or sustainability performance.
Soil contamination represents a pervasive and multifaceted threat to environmental integrity, public health, and sustainable land use. In response to this challenge, this systematic review synthesizes recent advancements in sustainable soil remediation techniques, with an emphasis on bioremediation, nature-based solutions (NBSs), innovative physicochemical methods, and multidimensional assessment frameworks. Utilizing the adapted PRISMA methodology, 3222 peer-reviewed articles published between 2015 and 2025 were initially identified, with 53 studies selected for in-depth evaluation based on methodological rigor, innovation, and relevance to sustainability. The findings reveal a pronounced research trajectory toward biologically mediated remediation strategies, including microbial bioremediation, phytoremediation, and vermiremediation, as well as hybrid systems that incorporate biochar and nano-enabled materials to enhance efficacy. Concurrently, emerging physicochemical techniques, such as stepped steam heating and composite stabilization using fly ash demonstrate potential for high-efficiency contaminant immobilization with reduced environmental trade-offs. The integration of computational tools, particularly machine learning for remediation optimization, and the application of life cycle assessment (LCA) and Multi-Criteria Decision Analysis (MCDA), are redefining how sustainability is quantified and operationalized. In addition to technical innovation, the review underscores critical policy and socio-economic dimensions, including regulatory fragmentation, funding asymmetries, and stakeholder engagement. Comparative analyses of EU and US regulatory frameworks highlight the impact of governance structures on implementation scalability and public acceptance. The review concludes by advocating for a paradigm shift toward holistic, transdisciplinary remediation approaches that are ecologically resilient, economically viable, and socially just aligned with the Sustainable Development Goals (SDG 15.3) and the Paris Agreement. This review provides a comprehensive and integrative perspective on the current state and future directions of sustainable soil remediation, offering a strategic foundation for researchers, policymakers, and practitioners engaged in the restoration of contaminated lands.
The rapid transition toward electric vehicles (EVs) in Saudi Arabia requires reliable and sustainable charging infrastructure capable of supporting long-distance highway transportation. However, the deployment of emergency charging systems is challenged by sparse charging infrastructure, stochastic emergency charging demand, battery degradation under harsh climatic conditions, and the need for cost-effective integration of renewable energy resources. This study presents a three-stage unified techno-economic planning framework for renewable-assisted emergency EV charging networks that integrates strategically located charging hubs with a coordinated fleet of solar-assisted Mobile Emergency Charging Vehicles (MECVs). The proposed framework jointly optimizes charging hub locations, photovoltaic (PV) generation capacity, battery energy storage system (BESS) sizing, and MECV allocation while explicitly accounting for stochastic emergency charging demand, renewable-energy utilization, and temperature-dependent battery degradation. Emergency charging demand is modeled using Monte Carlo simulation based on EV penetration scenarios, and battery aging is incorporated into the optimization through a temperature-dependent degradation model. The planning problem is formulated as a Mixed Integer Nonlinear Programming (MINLP) model and comparatively solved using three independent metaheuristic algorithms, namely the Musical Chairs Algorithm (MCA), Particle Swarm Optimization (PSO), and Grey Wolf Optimization (GWO). The proposed framework is evaluated using two representative highway corridors in Saudi Arabia. The results indicate that renewable-assisted charging can reduce annual grid-related CO2 emissions by approximately 25,360 and 57,641 t CO2/year for the Riyadh–Dammam and Riyadh–Makkah corridors, respectively. Battery degradation contributes approximately 12.7–14.2% of the total annualized system cost, highlighting the importance of incorporating lifecycle degradation into infrastructure planning. Temperature sensitivity analysis further indicates the significant influence of harsh climatic conditions on battery lifetime, renewable-energy utilization, and overall system economics. The proposed framework provides a practical planning methodology for developing reliable, sustainable, and economically viable emergency EV charging infrastructure in regions with similar geographical and climatic characteristics.
Biocomposites reinforced with natural fibres are receiving increased attention due to growing concern over the environmental impacts of their synthetic counterparts. Grass mowed from roadside verges has the potential to serve as an alternative to commonly used natural fibres and as a renewable feedstock for the biocomposite industry. However, it is generally treated as waste due to its high volume, seasonal availability, contamination (e.g., with metals and plastic bottles), and legal status. In this study, a techno-economic assessment was performed for different roadside grass valorisation scenarios covering the entire value chain from mowing and pre-treatment to fibre and biocomposite granule production. In addition, a screening greenhouse gas emissions assessment based on the main energy and material inputs was performed for fibre production. This screening assessment provides an initial indication of the operational environmental performance and is not intended to represent a complete life cycle or integrated sustainability assessment. One scenario investigated a value chain with flail mowing and grass fibres as the final product. Grass fibres can be produced at €528/t when mowing costs are included and as low as €295/t when mowing costs are excluded under the processor/incremental-cost perspective. A reduction of 6.4% in fibre price was estimated for the rotary-mowing scenario when mowing costs were excluded. In comparison, the market price of commonly available natural fibres ranges from €300 to €4000/t, although the price is strongly dependent on fibre quality, which was not considered in this assessment. Another scenario considered biocomposite granules consisting of 25% fibres, 60% polylactic acid, and 15% filler as the final product. The biocomposite granules can be produced at €1073/t and €1013/t with and without mowing costs, respectively. The production cost of the granules is largely influenced by the price of the polymer matrix and the compound composition, while the average market price is approximately €2000/t. Overall, the results indicate that roadside grass fibres may be cost-competitive under the evaluated assumptions. The screening assessment resulted in 364.20–701.32 kg CO2-eq/t fibre for the flail system and 275.96–327.96 kg CO2-eq/t fibre for the rotary system, depending on whether mowing was excluded or included. Drying energy and diesel consumption associated with mowing and collection were identified as the main operational emission sources.
Extensive small-ruminant grazing sustains food production on the Mediterranean land with few alternative uses, yet supervision is intermittent and welfare oversight weak. Digital monitoring is expected to close that gap, but detection alone does not produce intervention. In remote rangelands the link is unreliable, so an inference may reach the farmer late, degraded or not at all, and an alert arriving after the animal has moved is not a weaker alert but a different decision. This study develops a human-in-the-loop decision framework in which the delivery state of the link becomes a decision variable rather than a transport detail, coupling technology, farmer behaviour and governance. Constructed through design science research and structured analysis of an EU-funded project’s specifications and evaluation plans, it comprises a seven-layer architecture, a decision-episode schema, a connectivity-aware alert lifecycle, a decision-provenance matrix, and an evidence-maturity classification constraining what may be claimed. Five decision classes from a Cretan sheep and goat pilot instantiate it. After applying it, specification inconsistencies invisible to component-level review surfaced, among which is an alert payload lacking the coordinates, confidence and severity that its own indicators require. The framework is an instantiated specification, not a validated intervention: no detection, delivery, acknowledgement, usability or sustainability outcome is measured.
Northeast Thailand’s Chi-Mun River Basin is among Southeast Asia’s most flood-prone regions, experiencing annual monsoon inundation and extreme flood events that threaten community sustainability. Despite substantial investment in flood management infrastructure, community responses to flood hazards vary considerably, with some areas demonstrating adaptive capacity while others exhibit maladaptive development patterns that increase vulnerability. This study assesses community resilience to flood hazards by integrating flood exposure, environmental conditions (Sentinel-2 spectral indices), and population dynamics across 1157 locations in the Upper Chi River Basin, Maha Sarakham Province. A two-stage analytical framework combining K-means clustering and Random Forest classification identified five resilience classes: Slow Recovery (36.3%), Vulnerable Decline (25.8%), Unknown (17.7%), High Resilience (14.2%), and Maladaptive Growth (6.1%). Results reveal that Maladaptive Growth and High Resilience were clearly distinguished by population volatility (254.3 vs. 65.4), population change (+585.8% vs. −18.7%), and elevation (152.7 m vs. 168.1 m). Population trend emerged as the strongest predictor (importance = 0.135), followed by MNDWI (0.114) and elevation (0.113), indicating that demographic dynamics and topographic characteristics are more influential than flood frequency alone in determining resilience class membership. The findings reveal that Maladaptive Growth areas exhibit extreme population growth with high volatility in lower-elevation areas, whereas High Resilience communities maintain environmental quality and demographic stability despite population decline. These findings inform targeted interventions for sustainable flood risk management and contribute to understanding maladaptation in flood-prone regions, supporting the achievement of Sustainable Development Goals 11, 13, and 15.
Mobility-as-a-Service (MaaS) has emerged as a promising approach to urban transportation by integrating multiple mobility services into a single digital platform for trip planning, booking, and payment. More recently, Artificial Intelligence (AI) has expanded the capabilities of MaaS, enabling more efficient data processing, predictive analytics, personalized services, and intelligent decision support. This narrative review examines the current state of research on AI-enabled MaaS from both technological and socioeconomic perspectives. The analysis covers five major research areas: data integration and interoperability, predictive systems and demand forecasting, AI-enabled decision support for policy and planning, fairness and ethical AI, and cybersecurity and privacy protection. The findings show that successful implementation depends not only on advances in AI algorithms but also on high-quality interoperable data, effective governance, regulatory support, public trust, and collaboration among stakeholders. The review concludes that the main challenges facing AI-enabled MaaS are no longer primarily technical but organizational, institutional, and social. Future research should focus on trustworthy and explainable AI, privacy-preserving learning, standardized evaluation methods, fairness-aware optimization, resilient cybersecurity, and long-term assessments of MaaS impacts on sustainable urban mobility.
Mediterranean seagrass meadows, particularly Posidonia oceanica and Cymodocea nodosa, provide important ecosystem services including blue carbon storage, biodiversity support, sediment stabilization, and coastal protection, yet they continue to decline under multiple anthropogenic pressures. This article presents a SEEA EA-aligned natural capital accounting framework for seagrass restoration, developed within the INTERREG EuroMed ARTEMIS project and applied to four pilot sites in Crete, Menorca, Sardinia, and Monfalcone. The sites were selected to represent heterogeneous Mediterranean restoration contexts, including different seagrass species, degradation histories, pressure regimes, and restoration strategies. The methodology applies a seven-step marine natural capital accounting cycle combining ecosystem extent and condition accounts, physical blue carbon accounts, monetary ecosystem service accounts, impact statement accounts, and natural capital balance sheets. Two ecosystem service components are valued: global climate regulation, through blue carbon sequestration and storage, and biodiversity preservation, through a defensive cost approach. Results show strong site-specific variation. Biodiversity preservation dominates total asset values across all sites, while blue carbon is particularly relevant in Sardinia because of its high accumulation rate and carbon stock. A passive restoration scenario for Sardinia shows that pressure reduction and eco-mooring infrastructure can generate substantially larger aggregate values than small-scale active transplantation, mainly because of the larger area addressed. Compared with previous service-specific or broad-scale seagrass valuation studies, this article contributes by linking site-specific ecological monitoring, SEEA EA-compatible accounting outputs, and natural capital balance sheet values within a single framework relevant to marine restoration finance and future nature credit design.
Exposure to nitrogen oxide (NOx) in underground mining workings poses a significant threat to the health and safety of workers, while NOx emissions also represent an important environmental challenge associated with the operation of diesel-powered mining equipment. This article provides an overview of primary and secondary methods for limiting emissions and reducing exposure to NOx under underground mining conditions. The primary methods include intensified ventilation, extended ventilation time after blasting, the use of low-emission fuels, and modifications to combustion engines, including exhaust gas recirculation (EGR). The secondary methods include the use of exhaust gas purification technologies such as photocatalysis, oxidation catalysts (DOCs), selective catalytic reduction (SCR), and nitrogen oxide traps (LNTs). The presented solutions were compared in terms of NOx reduction efficiency, implementation costs, technical requirements, and practical applicability in underground workings. The most effective strategies in the short and long term were identified, taking into account the growing role of machine park electrification as a potentially sustainable solution to reducing emissions at their sources. Additionally, an SWOT analysis of NOx emission reduction methods designed for deep underground ore mines was conducted, enabling assessment of their strengths and weaknesses as well as opportunities and threats related to their implementation. The results can support the selection of NOx emission reduction methods that take into account environmental protection, worker safety, technical possibilities, and implementation costs and thus contribute to more sustainable underground mining.
Regional tourism sustainability depends on systemic resilience and synergy effects. This study constructs a tourism flow network covering the three northeastern provinces using ice–snow tourism travelogue data, and identifies sustainability bottlenecks along four dimensions: hierarchy, assortativity, transmissibility, and clustering. The results show that: ① the tourism flow exhibits a “southeastern agglomeration and central–southern polarization” pattern, with Jilin Province exhibiting the highest structural embeddedness, while Heilongjiang’s monocentric concentration implies higher systemic vulnerability; ② assortativity varies significantly across provinces—Heilongjiang demonstrates homogeneous agglomeration, which tends to amplify disturbance propagation, whereas Jilin and Liaoning exhibit cross-level linkages; ③ although intra-provincial transmission efficiency remains relatively high, the overall clustering coefficient is weak, with widespread isolated nodes and substantial cross-provincial mobility friction. Based on these diagnostics, this paper proposes tiered and spatially differentiated governance strategies: capacity–buffering measures for overloaded hub nodes, service upgrades along specific tourism corridors, and selective cooperation with culturally endowed but structurally peripheral nodes. These provide a new analytical tool and practical pathway for alleviating the spatial mismatch between tourist flows and carrying capacities, enhancing the adaptability of regional tourism systems to external shocks, and promoting the sustainable development of seasonal tourism destinations.
Sustainable Responsible Investment (SRI) emphasizes the integration of Environmental, Social, and Governance (ESG) factors into investment decisions. This study examines the relationship between ESG disclosures and individual investors’ trading behaviors, with corporate reputation as a mediating construct within the framework of signaling theory. Extending signaling theory, the study incorporates both cognitive and affective dimensions of corporate reputation to explain how ESG signals are interpreted by investors in emerging markets. Primary data were collected in 2025 from 390 individual investors in the Pakistan Stock Exchange (PSX), and Structural Equation Modeling (SEM) was used for analysis. The findings reveal that environmental and governance disclosures have a significant positive impact on investors’ behaviors, while social disclosures show a limited direct effect on both cognitive and affective corporate reputation dimensions. The results further indicate that corporate reputation significantly mediates the relationship between environmental and governance disclosures and investors’ behaviors. However, no mediation effect is observed for social disclosures. The study demonstrates that both cognitive (rational evaluation) and affective (emotional trust) dimensions of corporate reputation enhance the credibility of ESG signals and strengthen their influence on investment decisions. Overall, the study contributes to the ESG and signaling theory literature by highlighting how dual-dimensional corporate reputation shapes investors’ responses to ESG disclosures in emerging markets such as Pakistan.
Accurate ultra-short-term wind power forecasting at the turbine level is important for grid stability and dispatching. To address the time-varying spatial and temporal correlations among multiple turbines in a single wind farm, we build dynamic spatio-temporal graphs to model dynamic spatial dependencies, propose a parallel multi-scale temporal convolutional encoder to combine short-term and long-term dependencies, and propose a graph fusion layer to achieve weight fusion of different graph sources. Experiments demonstrate that GraphFusionGRU achieves lower overall error in short-term forecasting and achieves competitive average performance relative to other baseline models on longer horizons. The results confirm that the model’s robustness and interpretability are enhanced in complex wind-farm environments.
Sustainable road safety continues to be a major concern worldwide, with failure to wear seatbelts representing a significant risk, particularly in developing countries. In this study, we propose a deep learning-based framework for the automatic detection of seatbelt violations, leveraging a custom dataset collected on Moroccan roads that captures different vehicle types, driver clothing color variations, and environmental conditions. We explore the YOLO family of object detection models, from YOLOv8 to YOLOv26, evaluating 23 variants ranging from nano to large architectures. Each model was trained to classify drivers as Person–Seatbelt or Person–No-Seatbelt. Experimental results on this diverse dataset demonstrate that the proposed approach achieves a validation mAP@0.5:0.95 of 63.5% and a test mAP@0.5:0.95 of 56.1% on three entirely unseen vehicles, highlighting its robustness across previously unseen driver and vehicle conditions. To assess real-world deployment, the best-performing models are further benchmarked on the NVIDIA Jetson Orin Nano embedded platform using PyTorch and TensorRT FP16 formats in MAXN mode, with the most efficient configuration sustaining 94.4 FPS inference at 6.40 W. This work contributes to sustainable road safety by developing traffic violation detection systems and provides a foundation for future automated monitoring of driver behavior in real-world conditions.
This narrative literature review examines African American family fishing as a historically grounded practice of food provision, cultural continuity, place-based learning, and environmental stewardship, and considers its conceptual relationship to the United Nations Sustainable Development Goals (SDGs). The review synthesizes an analytical corpus of 41 works spanning history, fishing participation, food insecurity, food sovereignty, foodways, place attachment, environmental education, and social-ecological systems. The literature indicates that Black fishing cannot be understood as recreation alone; historically and contemporarily, it has connected food acquisition, family interaction, livelihood, cultural memory, and community identity. These functions are conceptually aligned with SDGs 2, 3, and 10 through plausible pathways involving culturally meaningful food access, family-centered outdoor activity, and attention to racial disparities in food security, environmental access, and institutional representation. Family fishing may also provide a place-based learning context relevant to SDG 4, while responsible harvesting, reduced waste, and ecological literacy may contribute to SDG 12. Repeated engagement with local waters may cultivate belonging and stewardship; freshwater relationships are most directly relevant to SDG 6, whereas coastal, estuarine, and marine contexts may contribute to SDG 14. These are interpretive alignments, not measured SDG outcomes. The review concludes that family-centered pilot initiatives may productively integrate cultural history, ecological education, food skills, mentorship, and community leadership, subject to feasibility testing and empirical evaluation. Contemporary family-level research is needed to examine harvest, food sharing, learning, health, access, and stewardship across generations.
