Search Results (220)

Classification is a fundamental technique in data mining that predicts categorical labels by analyzing input features. However, training Artificial Neural Networks (ANNs) using traditional methods often encounters challenges, such as getting stuck in local minima and slow convergence. To address these issues, this study proposes a novel hybrid model, IPA-ANN, which integrates the Immune Plasma Algorithm (IPA) to optimize the ANN’s connection weights and biases. The IPA, inspired by the immune plasma treatment process, utilizes a unique donor-receiver mechanism to balance exploration and exploitation in the search space. The proposed model was evaluated on nine benchmark datasets from the UCI repository and compared with 18 state-of-the-art metaheuristic algorithms, including Grey Wolf Optimization (GWO), Differential Evolution (DE), and Particle Swarm Optimization (PSO). Experimental results were analyzed using accuracy, F1-score, confusion matrices, and convergence graphs. The findings indicate that IPA-ANN achieves competitive and stable classification performance across different datasets while demonstrating favorable convergence characteristics in several cases. Furthermore, the study investigates the influence of donor–receiver parameters on the optimization process, highlighting the adaptability of the proposed framework. The reliability of these findings was further examined through repeated stratified 5-fold cross-validation and paired Wilcoxon signed-rank tests with Holm–Bonferroni correction on representative datasets, confirming that a subset of the observed performance differences are statistically significant, and through a computational cost analysis showing that IPA-ANN incurs no additional overhead relative to the majority of the compared algorithms. This study contributes to the literature by presenting the first documented application of IPA in ANN training and by providing a modular infrastructure for future metaheuristic-based ANN optimization studies. Full article

Against the backdrop of global climate change, drought–flood abrupt alternation (DFAA) has become a major compound climate extreme threatening ecosystem stability and sustainable watershed management. This study investigated the spatiotemporal characteristics and ecological responses of DFAA in the Jialing River Basin, China, using meteorological and hydrological observations from 1971 to 2020. DFAA events were identified using the Standardized Weighted Average Precipitation Index (SWAP) and run theory, and their spatiotemporal heterogeneity was characterized using spatial autocorrelation analysis. The Long-duration DFAA Index (LDFAI) was derived using the WEP-L distributed hydrological model. Ecological responses during 2000–2020 were evaluated by integrating the Remote Sensing Ecological Index (RSEI), grey relational analysis, and a Copula-based conditional probability model. The results showed that drought-to-flood events exhibited stronger spatial clustering than flood-to-drought events. Ecosystem responses showed significant lag effects, averaging 6.9 months for spring–summer events and 5 months for summer–autumn events, with greater sensitivity during the summer–autumn period. Under DTF events, the probability of maintaining relatively high ecological quality was significantly higher than under FTD events, whereas FTD events were associated with a higher probability of ecological degradation. Under compound scenarios, consecutive same-type events were more conducive to ecosystem stability, while alternating sequences of different event types significantly amplified negative ecological stress and represented high-risk scenarios for ecological degradation. These findings provide scientific support for adaptive watershed management, ecological restoration, and climate change adaptation in drought–flood-prone regions. Full article

Investigating the influence level and law of various factors on the distribution of reflected overpressure resulting from explosions in vehicles carrying hazardous chemicals or explosives is of great significance for accounting for the impact of load distribution in the blast-resistant design of structures. This paper uses LS-DYNA software to simulate and investigate the effects of five factors (charge mass ($M$), charge eccentricity ($X$), the aspect ratio of cuboid charge (${\delta }_{L/H}$), charge inclination ($\theta$), and tunnel diameter ($D$)) on the distribution of reflected overpressure on the lining. The grey relational degree reveals the relative influence of each factor on the reflected overpressure parameters of the lining cross-section (RPP_CS) at the blast center. The results show that $M$, $X$, and $D$ have the greatest influence on the RPP_CS of the blast center. An independent analysis of each factor revealed that the distribution of reflected overpressure from the central charge changes from two-dimensional symmetry to one-dimensional symmetry. Non-central charge disrupts its symmetric distribution. Inclined charge results in an asymmetric distribution. The intensity and incident angle of the shock wave have a significant effect on the location of the maximum reflected overpressure on the lining cross-section (RP_CS-max) at the blast center. In the RP_CS-max at the blast center, $X$ and $\theta$ change their location. $\theta$ can alter its distribution shape. When ${\delta }_{L/H}$ is too large, increasing $M$ or ${\delta }_{L/H}$ will both reduce the reflected overpressure. The influence of various factors on RPP_CS is different. Increases in $M$ and $D$ reduce the non-uniform distribution of RP_CS, but other factors have the opposite effect. The research findings provide a basis for considering the effects of load distribution in the design of structures resistant to internal explosions. Full article

Incoloy 800H (Fe–Ni–Cr) is an iron-based superalloy that is difficult to machine because of its rapid work-hardening behaviour. Although Taguchi-based grey relational analysis has previously been applied to machining optimisation problems, studies employing an integrated grey-fuzzy framework for the dry turning of Incoloy 800H remain limited. Therefore, the present investigation aims to develop and validate a grey-fuzzy optimisation approach for determining the optimal dry turning parameters of Incoloy 800H by simultaneously minimising machining forces, surface roughness, and specific cutting pressure. Cutting speed (35, 45, and 55 m/min), feed rate (0.02, 0.04, and 0.06 mm/rev), and depth of cut (0.5, 0.75, and 1 mm) were selected as input factors, whereas feed force, thrust force, cutting force, surface roughness, and specific cutting pressure were considered output responses. Experiments were conducted using a Taguchi L27 orthogonal array (OA). The proposed methodology integrates grey relational analysis (GRA) with fuzzy logic (FL) to obtain a grey-fuzzy reasoning grade (GFRG) for multi-response optimisation. Analysis of variance (ANOVA) was employed to identify the most influential machining parameter. The results demonstrated that the grey-fuzzy approach provided a more discriminative optimisation index than conventional grey relational analysis by reducing uncertainty in multi-response decision-making. The confirmation experiments revealed an increase in GFRG from 0.550 to 0.900, corresponding to a relative improvement of 63.64% at the optimal parameter setting. The proposed methodology demonstrates that integrating grey relational analysis with fuzzy inference provides a reliable and statistically supported approach for multi-response optimisation of dry turning parameters for Incoloy 800H. Full article

Hydrogen-based technologies are widely considered promising pathways for decarbonizing power generation and industrial energy systems; however, their overall sustainability depends strongly on both production routes and conversion efficiencies. This study presents a comparative energy and exergy analysis of hydrogen-based decarbonization pathways under a consistent 1 MW net electrical output boundary, including natural gas combustion (S0), grey hydrogen combustion (S1), grey hydrogen fuel cell (S2), green hydrogen combustion (S3), and green hydrogen fuel cell (S4) systems. The results indicate that combustion-based pathways (S0, S1, and S3) exhibit relatively low energy efficiencies of approximately 30–40% and exergy efficiencies of 25–40%, accompanied by high exergy destruction levels generally exceeding 60%. In contrast, fuel cell-based configurations (S2 and S4) demonstrate improved conversion-stage thermodynamic performance, achieving energy efficiencies of 50–60% and exergy efficiencies of 45–65%, while reducing exergy destruction due to electrochemical conversion and lower irreversibilities. A detailed comparison shows that the natural gas reference system reaches an exergy efficiency of 33.7%, whereas the hydrogen fuel cell system achieves 46.5%, corresponding to approximately 42% lower exergy destruction and about 36% reduced fuel input. From an environmental perspective, the simplified carbon assessment indicates that natural gas combustion generates approximately 577 kg CO₂/h. Grey hydrogen pathways remain associated with substantial upstream emissions, generating approximately 857 kg CO₂/h for grey hydrogen combustion and 545 kg CO₂/h for grey hydrogen fuel cell operation under the 1 MW net electrical output basis. In contrast, green hydrogen-based pathways are assumed to have near-zero direct/upstream operational CO₂ emissions under renewable-powered production assumptions. Overall, the findings show that hydrogen use alone does not guarantee decarbonization; rather, both the hydrogen production route and the final conversion technology must be considered to achieve thermodynamically efficient and low-carbon power generation. Full article

To address ambiguities in phase-line identification, errors in user–transformer associations, and inaccurate topology records in complex low-voltage distribution networks, this paper proposes a hierarchical topology identification method based on improved T-type grey relational analysis and Fisher optimal segmentation. In the proposed method, signed voltage increments, a resolution coefficient, and node-distance weighting are introduced to construct distance-aware relational features from user voltage sequences. Fisher optimal segmentation is subsequently applied to identify user–transformer associations, followed by a suspicious-user verification mechanism for local topology correction. Case studies using practical transformer-area data show that the proposed method provides greater discrimination among user voltage sequences than Pearson correlation analysis and conventional T-type grey relational analysis. At a random-noise level of 6%, the phase-line identification accuracy remains 83.7%, while the accuracy of user–transformer association identification reaches approximately 93% under the available field-data conditions. Comparative and robustness analyses further indicate that Fisher optimal segmentation maintains relatively stable performance under the tested missing-entry and reduced class-separation conditions. These results suggest that the proposed framework provides a feasible and interpretable approach to topology identification in complex low-voltage distribution networks. Full article

This study proposes a sequential Hybrid GP-ANN architecture based on the concept of autonomous feature engineering for multi-output performance prediction of single-phase induction motors, serving as a high-fidelity surrogate model ready for digital twin integration. The required high-resolution motor dataset (88,375 samples) was generated using a parametric sweep approach with Ansys RMxprt. In the proposed architecture, Genetic Programming (GP) is not positioned as a final predictor but as an analytical filter that discovers hidden physical relationships in raw input data and converts them into super features, thereby structurally eliminating the polynomial explosion risk and scale sensitivity that arise when raw data are modelled directly. The nonlinear physical relationships discovered autonomously by GP are added to the network input matrix as mathematical vectors, breaking the black-box structure of standard artificial neural networks and transforming it into a physics-inspired grey-box model. The nonlinear terms discovered by GP are fed into the network after independent Z-score normalisation to preserve gradient stability. To comprehensively evaluate this framework, its predictive performance is benchmarked against industry-standard machine learning algorithms, including Random Forest (RF), Support Vector Regression (SVR), and Extreme Gradient Boosting (XGBoost). Results on variation-based unseen test data show that the hybrid model achieves competitive prediction accuracy relative to XGBoost—matching or exceeding it for Output Torque and Input Current, and remaining broadly comparable for Output Power, though XGBoost achieves substantially lower RMSE for Efficiency and Power Factor—while additionally offering transparent mathematical traceability, reducing error rates (RMSE) by 42.1% to 66.1% per parameter compared to the standard ANN. The model achieves an $R^2$ score of 0.9879 for the power factor parameter, where conventional approaches struggle. To rigorously validate the interpretability of this grey-box architecture, a global Permutation Feature Importance (PFI) analysis was conducted, showing that the GP-derived super features collectively account for 61.46% of the decision logic, outweighing the combined contribution of the raw inputs (38.54%). Furthermore, the autonomous feature engineering layer is found to reduce the learning burden on the ANN, allowing it to converge to a substantially lower error floor within the same fixed epoch budget. With an online inference time below 0.02 ms, the proposed architecture offers a robust methodological infrastructure for sustainable motor digital twins through a balanced trade-off between prediction accuracy and computational efficiency. Full article

With the continuous digital transformation of the construction industry, differences in the depth and effectiveness of BIM application during the construction phase of building projects have become increasingly evident. To systematically evaluate BIM application maturity during this stage, this study develops a construction phase-specific maturity assessment framework. First, based on the characteristics of BIM application during the construction phase and the logic of maturity assessment, the concept of BIM application maturity is defined. An evaluation indicator system is then constructed using the Balanced Scorecard as an organising framework, covering four dimensions: financial and cost-effectiveness, customer and delivery value, internal processes and efficiency, and learning and innovation capability. Second, grey relational analysis is used to screen and optimise the initial indicators, while the AHP-CRITIC combined weighting method is adopted to integrate subjective expert judgement and objective data characteristics. On this basis, a cloud model-based evaluation method is introduced to transform qualitative maturity assessment into quantitative evaluation while considering fuzziness and randomness. Finally, the proposed framework is applied to Project C as an empirical case application. The results show that the overall BIM application maturity of Project C during the construction phase is classified as the Integration Level. Among the four first-level dimensions, the customer and delivery value dimension performs relatively strongly, while the learning and innovation capability dimension shows the lowest expectation value. The proposed framework can help identify the maturity level and relative weaknesses of BIM applications during the construction phase, and can provide a reference for targeted BIM improvement and construction management decision-making. Full article

In response to ecological degradation caused by uncontrolled dust emissions from open-pit mines, this study selected the Hequ open-pit coal mine as the study area and established a monitoring system to collect data on TSP, PM10, PM2.5, and environmental indicators across three zones: the mining pit, the main haul road, and the coal yard. The necessity of zoning was validated using the least significant difference (LSD) method. Pollutant correlations were examined using the individual air quality index (IAQI), Pearson correlation matrix analysis, and grey relational analysis. Univariate models, multiple linear regression (MLR), and principal component analysis–multiple linear regression (PCA–MLR) were applied to quantitatively analyze dust evolution patterns and the influence of environmental factors, with model accuracy verified by the mean relative error (MRE) method. The results showed significant differences in dust concentrations among the three zones. Dust concentrations of all particle sizes in the mining pit and coal yard exceeded the secondary standard limit, whereas those on the haul road only exceeded the primary limit, with pollution intensity ranked as mining pit > coal yard > haul road and PM2.5 identified as the core pollutant in all zones. Linear relationships were significant in univariate models, and multivariate fitting outperformed univariate fitting, with MLR prediction accuracy ranked as coal yard (3.02%) > haul road (9.46%) > mining pit (10.75%). In the mining pit, TSP and PM10 exhibited a strong positive correlation with atmospheric pressure, while PM2.5 showed a strong negative correlation with relative humidity. On the haul road, all particle size fractions displayed strong negative correlations with temperature and wind speed. In the coal yard, only a strong negative correlation with temperature was observed. The PCA–MLR model improved prediction accuracy by 56.63% and 13.41% compared to the direct MLR model. Comprehensive analysis indicates that the atmospheric environment of the Hequ open-pit mine urgently requires proactive restoration measures to optimize the sustainability of the ecological environment. Full article

Regulated deficit irrigation (RDI) is an important water-saving strategy in arid regions. To quantify the effects of RDI on foxtail millet yield and water use efficiency and determine an optimal RDI strategy, a three-year field trial was carried out over dry, normal, and wet rainfall years in the Loess Plateau. Full irrigation throughout the whole growth period served as the control, whereas mild, moderate, and severe deficit irrigation treatments were conducted at the jointing–booting stage, heading–flowering stage, and across the whole growing period, respectively. The results indicate that the effects of RDI on foxtail millet yield varied with crop growth stage and deficit severity. During the heading–flowering stage, mild RDI showed statistically similar grain yield and WUE relative to those under full irrigation. In normal and wet years, moderate and severe RDI had no statistically significant effects on grain yield and WUE. Additionally, moderate and severe RDI significantly improved irrigation water use efficiency by 19.94–28.50% and 34.35–47.72%, respectively. The primary reason is that RDI at this stage maintained root development and led to only limited suppression of plant growth. In contrast, moderate and severe RDI at the jointing–booting stage or throughout the whole growth period significantly inhibited root establishment and plant development, reduced dry matter accumulation, and consequently led to substantial yield losses. The inhibitory effect became more pronounced with increasing deficit severity. Specifically, severe RDI at the jointing–booting stage and throughout the entire growth period significantly reduced yield by 19.35–54.98% and 31.47–100%, respectively. Furthermore, to identify the optimal RDI regime adaptable to variable rainfall years, a multi-model comprehensive evaluation system based on yield and WUE was established by integrating three individual evaluation models, including the membership function method, TOPSIS, and grey relational analysis, with the Fuzzy–Borda combined evaluation model. The result showed that the heading–flowering stage is the critical period for implementing RDI in foxtail millet in the Loess Plateau. Mild RDI during this stage is preferred because it maintains stable yield and WUE while substantially reducing irrigation amount over various rainfall years. Additionally, moderate and severe RDI can also maintain stable yield while significantly improving irrigation water use efficiency in normal and wet years. Full article

The traditional urbanization path based on scale expansion is unsustainable in karst mountainous regions due to fragmented topography and ecological fragility. Taking Guiyang City as a case study, this paper constructs two evaluation indicator systems for urban–rural development and environmental support. Employing the entropy method, coupled coordination degree model, Grey relational analysis, Geodetector, and multi-source spatial analysis methods to examine the evolutionary trajectory, driving mechanisms, and spatial responses of the human–land system from 2000 to 2024. The results show three main findings. First, the comprehensive score of Guiyang’s urban–rural human–land system increased from 0.054 to 0.826, and the coupling coordination degree rose from 0.223 (relative imbalance) in 2000 to 0.903 (high-quality coordination) in 2024, while the environmental support system deviated from the classic environmental Kuznets curve. Second, the driving force has shifted from economic scale to green well-being. The interaction analysis using Geodetector shows that all interaction types fall under the category of two-factor enhancement, among which the interaction coefficient between the number of broadband internet subscribers and other driving factors has the highest explanatory power, with a q-value of 0.949. Third, spatially, the light center distribution stabilized after 2015, and the land use ecological transition index dropped from 0.162 to 0.050 while the D-value continued rising, showing a significant negative correlation (r = −0.89, p < 0.05). Construction land was concentrated in low-slope (0–6°) and mid-elevation (1000–1400 m) basin areas, overlapping with high-quality farmland, and the synchronization rate between economically active areas and construction expansion was 50%. These findings reveal a digital–ecological co-evolution path in karst regions and provide an empirical basis for urban–rural integration governance. Full article

Objective: This study aims to explore the differences in chemical composition among Tibetan medicinal Rhododendron species and their potential correlation with anti-complement activity, with the goal of identifying promising medicinal resources. In Tibetan medicinal practice, the two groups of large-leaved Rhododendron (Tibetan: Dama) and small-leaved Rhododendron (Tibetan: Tali) are often used interchangeably despite unclear chemical and taxonomic bases. By comparing chemical profiles and evaluating anti-complement effects, this investigation seeks to provide preliminary scientific evidence for clarifying medicinal origins and facilitating the targeted development of high-quality resources. Methods: Ultra-performance liquid chromatography coupled with quadrupole time-of-flight mass spectrometry (UPLC-Q-TOF-MS) was employed to analyze seven Rhododendron samples. Separation was achieved on a Waters CORTECS UPLC C18 column (2.1 × 100 mm, 1.6 μm) using a gradient mobile phase system consisting of acetonitrile and 0.1% formic acid in water, at a flow rate of 0.3 mL/min and a column temperature of 30 °C. Data were acquired in both positive and negative electrospray ionization (ESI) modes. Compound identification was performed using Peakview 1.2 software by comparison with databases and literature. Grey relational analysis and partial least squares (PLS) regression, combined with 5000 bootstrap resampling iterations, were applied to establish spectrum–effect relationships and to screen for characteristic peaks potentially associated with anti-complement activity. Results: A total of 52 compounds were tentatively identified, including flavonoids (e.g., hyperin, isoquercitrin, taxifolin-3-O-arabinoside), terpenoids (e.g., grayanotoxin I/III), and chromanes (e.g., anthopogochromane series). The CH₅₀ values of the ethanol extracts ranged from 179.29 to 579.47 μg/mL, with Rhododendron principis showing the strongest activity (179.29 ± 11.86 μg/mL), followed by Rhododendron vellereum (198.61 ± 7.93 μg/mL). Spectrum–effect analysis revealed that four unidentified peaks (F5315, F5822, F5368, F5991) exhibited negative regression coefficients and VIP means close to or above 0.8, suggesting a possible positive correlation with anti-complement activity. Among these, F5315 (VIP = 0.909), F5822 (VIP = 0.877), and F5368 (VIP = 0.834) showed relatively higher values and were considered preliminary candidate peaks warranting further investigation. Conclusions: This study tentatively identifies 52 compounds from the ethanol extracts of seven Tibetan medicinal Rhododendron species and reports their anti-complement activities. The findings reveal chemical distinctions between the large-leaved (Dama) and small-leaved (Tali) groups, offering a potential chemical basis for species differentiation and quality evaluation. Furthermore, four unknown peaks were preliminarily screened through spectrum–effect analysis as potential anti-complement candidates, which may serve as a foundation for future activity-guided isolation and quality marker studies. Full article

Indian metropolitan cities such as Mumbai grapple with rapid urbanisation, extreme urban density, high built-up areas, loss of green cover, and shrinking open spaces, resulting in increased impermeable surfaces, urban heat island effects, and frequent flooding occurrences. Modern stormwater management has increasingly been characterised by integrated grey-green approaches; however, cities in the Global North benefit from established policies, technical expertise, and financial resources that enable the systematic and large-scale integration of Blue-Green Infrastructure (BGI) through district-wide geospatial assessment frameworks, unlike many cities in the Global South. Despite growing interest in nature-based stormwater solutions, there remains a dearth of geospatial empirical research from India examining the placement, distribution, performance, and functionality of BGI integrated with existing stormwater management systems in cities such as Mumbai. Furthermore, hydrological modelling using tools such as the Storm Water Management Model (SWMM) for the design, planning, and implementation of BGI in Indian cities remains largely unexplored. This study explores the role of BGI strategies in improving urban stormwater management within high-density Indian cities under a 25-year return period extreme rainfall scenario. Using an integrated approach that combines QGIS-based spatial analysis with EPA-SWMM hydrologic-hydraulic modelling, the research examines runoff behaviour, identifies flooding hotspots, and evaluates the effectiveness of Low Impact Development (LID)-based BGI measures such as permeable pavements, infiltration trenches, and green roofs applied at the ward level in Mumbai’s F/North and G/North Wards. Detailed land use classification, spatial mapping, and rainfall simulation corresponding specifically to a 25-year return period rainfall event was used to assess pre- and post-intervention conditions. The findings indicate that the applied BGI measures led to a 12.6% reduction in peak runoff (137.6 m³/s to 120.2 m³/s) and a 5.5% decrease in total runoff volume (783,510 m³ to 740,410 m³). More importantly, the peak flooding flow rate decreased by 45% (94.1 m³/s to 51.7 m³/s), demonstrating that BGI measures can efficiently reduce peak flooding flows by extending runoff hydrographs during extreme rainfall events. These findings are specifically applicable to the simulated 25-year return period extreme rainfall scenario and may vary under different rainfall intensities or return periods. Less extreme events could potentially experience even greater relative reductions or prevent flooding altogether, while also easing downstream hydraulic loads. Overall, strategically placed BGI interventions can significantly reduce surface runoff and peak flow, thereby enhancing stormwater resilience within spatially constrained urban environments. This study provides a replicable, data-driven framework for catchment-scale stormwater planning in dense Indian cities under extreme rainfall conditions, offering practical insights into methods, local contextual considerations, and spatial planning strategies for policymakers and urban planners seeking to retrofit and adapt existing infrastructure under increasing hydrologic stress and climate variability. Full article

Rapid urbanization reshapes urban land systems and intensifies surface thermal heterogeneity, yet nonlinear day–night land surface temperature (LST) responses to grey–green spatial organization and building morphology remain insufficiently understood, particularly in thermally stressed areas across the urban–rural gradient. Using Xi’an, China, as a case study, this study develops a priority-area-based land–climate interaction framework. Priority areas were defined as grid cells where elevated LST coincided with relatively strong local explanatory relationships between LST and land-cover or morphological variables. Multiscale geographically weighted regression (MGWR), gradient boosting decision trees (GBDTs), SHAP-based interpretation, and threshold sensitivity analysis were combined to identify dominant drivers, nonlinear response patterns, and interaction structures of daytime and nighttime LST. The results show pronounced day–night differentiation: daytime hotspots were concentrated in the built-up core, whereas nighttime hotspots extended toward the urban–rural fringe. Daytime LST was mainly associated with building coverage and grey-space organization, while nighttime LST was more strongly related to mean building height and the cooling contribution of green-space coverage. The analysis further identified localized empirical response ranges for built-up intensity, grey-space connectivity, building height, and green-space coverage within the priority areas. These findings clarify how land-cover configuration and building morphology jointly shape day–night surface thermal responses and provide context-specific evidence for land-use planning and targeted urban heat mitigation. Full article

Exposure to urban green spaces has been associated with mental wellbeing, but the neural responses to specific visual properties of urban green spaces remain unclear. This study investigated regional electroencephalogram (EEG) responses to latent visual dimensions of virtual urban green space exposures. This study used a quantitative scene-based approach that extracted 41 visual metrics to capture the heterogeneous structural properties of 24 panoramic urban green images. EEG recordings were analyzed from 150 participants, each of whom viewed eight randomly selected images repeated three times. Dimension-wise factor analysis with varimax rotation was used to derive latent factor scores for four conceptual dimensions: naturalness, complexity, coherence, and visual scale. These factors were then used as predictors in crossed mixed-effects models of regional EEG relative power changes. The hypothesis-driven primary analysis showed a significant and positive association between parietal alpha–theta activity and a naturalness factor reflecting green–grey scene compositions. Exploratory frontal associations with a terrain-related visual scale factor reached nominal significance but did not survive false discovery rate correction. Overall, the findings support a quantitative, feature-based approach for linking urban green space structure with regional neurophysiological responses. This study provides a methodological step toward more evidence-informed assessment of smart and sustainable urban environments. Full article