Search Results (873)

Multi-objective evolutionary optimization faces significant challenges due to guidance mismatch under complex Pareto-front geometries. This paper proposes a dynamic self-organizing map-assisted evolutionary algorithm (D-SOMA), a manifold-aware framework that harmonizes knowledge-informed priors with unsupervised objective-space characterization. Specifically, a knowledge-informed guided resampling strategy is formulated to bridge stochastic initialization and targeted exploitation. By distilling spatial distribution priors from the decision-variable boundaries of early-stage elite solutions, it establishes a high-quality starting population biased towards promising regions. To capture the intrinsic geometry of the evolving population, a self-organizing map (SOM)-based adaptive subregion characterization strategy leverages the topological preservation of self-organizing maps to extract latent modeling parameters. This strategy adaptively determines subregion centers and influence radii, enabling a data-driven partitioning that respects the underlying manifold structure. Furthermore, a density-driven phase-responsive scale adjustment strategy is introduced. By synthesizing spatial density feedback and temporal evolutionary trajectories, it dynamically modulates the characterization granularity K, thereby maintaining a rigorous balance between geometric modeling fidelity and computational overhead. Extensive experiments on 50 benchmark problems from the DTLZ, WFG, MaF and RWMOP suites demonstrate that D-SOMA is statistically superior to seven state-of-the-art algorithms, exhibiting robust convergence and superior diversity across diverse problem landscapes. Full article

Against the backdrop of dietary structure evolution and the “big food concept” strategy, there has been a shift from the traditional grain-centric perspective toward a diversified supply system. Taking Hubei Province—a major grain-producing region in China—as a case study, this research establishes a multi-criteria evaluation system and conducts analysis using statistical yearbooks and land survey data. By integrating natural conditions, economic benefits, and production capacity, the suitability of cultivated land for growing grain crops, cash crops, and forage crops is assessed. Concurrently, landscape pattern indices were applied to quantify the degree of farmland fragmentation. Employing a self-organizing mapping (SOM) neural network model, we synthesized suitability and fragmentation data to delineate differentiated farmland conservation zones. The results revealed significant spatial heterogeneity in crop suitability and fragmentation levels. High-suitability zones for grain crops were concentrated in the Jianghan Plain, while forage crops exhibited higher suitability in northeastern and southeastern Hubei. Farmland fragmentation showed a spatial pattern of lower levels in central Jianghan Plain, gradually increasing toward surrounding hilly and mountainous areas. SOM clustering effectively partitioned farmland into six functional zones: multifunctional agricultural zones, mixed farming zones, grain crop zones, cash crop zones, forage crop zones, and production improvement zones. This multi-source geographic and statistical data-driven zoning framework provides scientific basis for targeted policy interventions. It enables the quantitative management, quality enhancement, and spatial optimization of farmland resources, thereby operationalizing the big food concept to strengthen regional food security. Full article

This study systematically analyzes the spatio-temporal evolution, trade-offs, synergies and driving mechanisms of five ecosystem services (ESs) in Fujian Province (carbon storage, CS; habitat quality, HQ; sediment delivery ratio, SDR; water yield, WY; food provision, FP) based on multi-source data from 2003, 2013 and 2023 by adopting the InVEST model, Spearman correlation analysis, geographically weighted regression (GWR), self-organizing maps (SOM) and geographic detectors. Results show that: (1) ESs present a spatial pattern of “high in northwest and low in southeast” in Fujian; CS, HQ and FP show an overall decline, while SDR and WY increase significantly. (2) ES trade-offs and synergies have obvious scale effects and spatial heterogeneity, with stronger relationship intensity at the county level than the grid level, and FP generally shows a trade-off relationship with other services. (3) Land use is the key driving factor for CS, FP and HQ; precipitation dominates the changes in WY and SDR; and dual-factor interactions generally enhance the explanatory power of ES changes. The findings enrich the theoretical system of multi-scale ES trade-off and synergy research under rapid urbanization and provide a scientific basis for sustainable territorial spatial planning and differentiated ecological governance in Fujian. Meanwhile, the research framework can serve as a reference for ES management in other coastal mountainous regions worldwide, contributing to the realization of regional sustainable development goals (SDGs). Full article

Land use change profoundly impacts the trade-offs and synergies among ecosystem services in ecologically fragile watersheds. Optimizing land use patterns based on ecological function zoning is an important approach to coordinate multiple ecosystem services and promote sustainable watershed management. This study focuses on the Wuding River Basin within the Chinese Loess Plateau, using Self-Organizing Map, multi-objective genetic algorithms, and the Future Land-Use Simulation model to explore land use optimization schemes. The results show that the windbreak and sand fixation service in the Wuding River Basin presents a spatial pattern of higher values in the northwest and lower values in the southeast, while the other six services exhibit a pattern of higher values in the east and lower values in the west. Based on the ecosystem service cluster characteristics, the basin can be divided into soil and water conservation zones, habitat conservation zones, and ecologically fragile zones. The trade-offs and synergies between ecosystem services within different zones differ significantly, with the trade-off between food supply, soil conservation, and habitat quality being particularly prominent. After optimization, the food supply and soil conservation in the soil and water conservation zones increased by an average of 0.63 × 10⁴ t and 1.94 × 10⁵ t, respectively. The food supply in the habitat conservation zones increased by 0.11 × 10⁴ t, while habitat quality remained stable. In the ecologically fragile area, water production and carbon sequestration services increased by an average of 0.26 × 10⁴ t and 0.58 × 10⁵ t, respectively. During the optimization process, the reasonable allocation of grassland and unused land played a key role in balancing service conflicts. This study provides a scientific basis for coordinating trade-offs in watershed ecosystem services and achieving land use optimization management through the framework of service clusters, functional zones, and multi-objective optimization. Full article

Strong heterogeneity and ambiguous seismic responses hinder reliable sandstone thickness prediction when using a single seismic attribute in the lower sandstone interval of the Talang Akar Formation (hereafter abbreviated as the LTAF interval) in the B gas field, South Sumatra Basin. To address this challenge, we propose a seismic attribute fusion and reservoir sweet-spot prediction framework based on a multiscale convolutional neural network (CNN) integrated with a self-attention module. Multiple seismic attribute volumes are organized as multi-channel 2D attribute slices, and parallel convolutions with kernel sizes of 3 × 3, 5 × 5, and 7 × 7 are employed to capture spatial features ranging from thin-bed boundaries and channel morphology to sand-body assemblage distribution. The self-attention module explicitly models inter-attribute dependencies and performs adaptive weighted fusion to suppress noise and emphasize informative attributes. The network adopts a dual-output design, producing (i) a sandstone thickness prediction map at the same spatial resolution as the input and (ii) attribute importance scores for quantitative attribute selection and geological interpretation. Using 3D seismic data and well-constrained thickness labels, the proposed model achieves an R² of 0.8954, outperforming linear regression (R² = 0.8281) and random forest regression (R² ≈ 0.8453). The learned importance scores indicate that amplitude-related attributes (e.g., RMS amplitude and maximum amplitude) contribute most to thickness prediction, whereas frequency- and energy-related attributes show relatively lower contributions, which is consistent with bandwidth-limited resolution effects. Overall, the proposed framework unifies attribute fusion, thickness prediction, and interpretability within a single model, providing practical support for fine reservoir characterization and development optimization in heterogeneous sandstone reservoirs. Full article

Saline irrigation water is increasingly used in arid and coastal regions, posing serious constraints to soil health and wheat yield, particularly in saline–sodic soils. A two-season field experiment was conducted to evaluate the effects of compost, biofertilizers (Azospirillum brasilense and Azotobacter chroococcum), and their combinations on soil physicochemical properties, microbial activity, wheat growth, yield, and physiological traits under two irrigation water salinity levels (3 and 6 dS m⁻¹). Two wheat varieties differing in salt tolerance (Miser 4 and Sakha 95) were tested. Salinity significantly increased soil EC and ESP and reduced plant growth, yield, and nutrient content, while integrated bio-organic treatments markedly alleviated these adverse effects. Compost combined with Azotobacter chroococcum markedly improved soil physical conditions, enhanced microbial biomass carbon, reduced sodicity indicators, and promoted wheat productivity across both seasons. Multivariate analyses including principal component analysis (PCA), redundancy analysis (RDA), and self-organizing maps (SOMs) revealed a strong positive association between yield traits, microbial activity, and soil fertility, and negative correlations with salinity stress indicators. The results demonstrate that combining compost with biofertilizers induces both immediate and residual improvements in saline–sodic soils, enhances wheat resilience to salinity stress, and offers a sustainable approach for improving cereal production under salt-affected environments. Full article

To address the challenges of strong tectonic stress anisotropy, multi-scale pore networks, and complex seepage pathways in the tight sandstone reservoirs of the Shaximiao Formation, southern Sichuan Basin, this study integrates petrophysical analysis with machine learning techniques to develop an intelligent flow unit identification methodology applicable to complex structural settings. Based on core petrophysical properties, mercury injection capillary pressure (MICP) data, and production dynamics, the reservoirs were classified into a fracture-type plus four conventional-type (I–IV) flow unit system. Quantitative identification of flow units was achieved using conventional well-logging curves (Gamma Ray, Spontaneous Potential, Caliper, etc.—eight curves total) using the Gradient Boosting Decision Tree (GBDT), Backpropagation Neural Network (BPANN), and Supervised Self-Organizing Map (SSOM) algorithms. Key findings include the following: The SSOM algorithm delivered optimal performance, achieving a 90.1% average accuracy on the test set, significantly outperforming GBDT (87.8%) and BPANN (85.5%), particularly in capturing nonlinear responses of fracture-type reservoirs and class-overlapping samples. Flow unit spatial distribution exhibits dual sedimentary-structural control: High-quality units (Types I/II) are enriched at the base of distributary channels in deltaic plain facies (J₂S1²), while fracture-type units cluster near fault peripheries. Strong planar heterogeneity is observed in the J₂S1³ sub-member: Near-source areas (south/southwest) develop banded Type I/II units, whereas distal regions are dominated by Type IV units. This methodology provides a theoretical foundation and intelligent technological pathway for the efficient development of highly heterogeneous tight sandstone reservoirs. Full article

Thermal comfort and adequate sunlight exposure are essential for maintaining the health of older adults. Although multi-objective optimization (MOO) has been increasingly applied to improve environmental performance in spatial design, most existing studies still rely on computationally expensive physical simulations, and their optimization results often lack interpretability and operability in early design decision-making. To address these issues, this study proposes a collaborative optimization framework that integrates machine learning surrogate models with neural visualization tools to support performance-driven design of age-friendly outdoor spaces at the early stage. Based on survey data from 46 typical Beijing communities, we constructed a parametric model with three objectives: minimizing summer UTCI, maximizing winter UTCI, and maximizing sunlight duration. An XGBoost model is adopted as a surrogate to accelerate performance prediction, while a self-organizing map (SOM) was applied to cluster and visualize Pareto-optimal solutions. The results indicate that the surrogate model achieves high predictive accuracy and reduces overall computational time by approximately 45% compared with conventional physical simulations. Moreover, the SOM-based visual decision process compresses the high-dimensional solution space and reduces candidate schemes by more than 90%, enabling rapid identification of design solutions that balance environmental performance and spatial morphology. The proposed framework improves both computational efficiency and decision support capacity for performance-oriented spatial design and provides a novel methodological reference for the environmental renewal of age-friendly outdoor spaces. Full article

As one of the most important transportation corridors in China, the long-term operation of the Beijing–Shanghai High-Speed Railway may lead to the fragmentation and fragility of the ecological pattern and an imbalance between the supply and demand of ecosystem services in the provinces along the line, thereby affecting ecological security. How to construct and optimize the ecological security pattern to address these issues is a challenging problem in the territorial spatial planning of the provinces along the Beijing–Shanghai High-Speed Railway. Complex networks serve as the primary approach for constructing ecological security frameworks, and the SOM model can objectively extract ecological source areas from the perspective of ecosystem service functional dimension. Therefore, this study combines the SOM model with complex network analysis methods to construct and optimize the ecological security pattern across seven provinces along the Beijing–Shanghai High-Speed Railway. The results show that, except for carbon sequestration, the other five types of ecosystem services (habitat quality, soil conservation, water purification, water production, and NPP) in the study area exhibit significant spatial heterogeneity. The ecological network constructed in this study identified 335 source areas and extracted 334 ecological corridors. A comparative study of three edge addition schemes shows that the edge addition strategy based on betweenness centrality has the best optimization effect, adding 93 new corridors to the original ecological network. The ecological security pattern constructed in this study provides an important reference for territorial spatial planning and for constructing forestry and grassland ecological restoration projects in the seven provinces along the Beijing–Shanghai High-Speed Railway, thereby contributing to the region’s ecological sustainable development. Full article

The geochemical characteristics of major elements in lake sediments provide insights into aquatic environmental variations, the regional geological background, and the intensity of weathering processes. This study investigates Dongping Lake (DL) using 20 surface sediment samples, analyzing nine major elements. Spatial interpolation was used to characterize their distribution patterns, while principal component analysis, self-organizing maps, and absolute factor analysis–multiple linear regression methods were applied to identify element sources and interpret their geological significance using weathering indicators. Results show that surface sediments are dominated by SiO₂ (46.49%), Al₂O₃ (13.10%), and CaO (11.25%). Controlled by hydrodynamic conditions, major elements are mainly concentrated in the southern part of the lake near the inflows of the Dawen and Liuchang Rivers, with concentrations decreasing from south to north. Riverine transport is the primary source of major elements, with the Dawen River contributing the most followed by the Liuchang and Yellow rivers. Weathering indicators suggest that source rocks have experienced moderate chemical weathering, reflecting initial sedimentation in a tectonically active setting under warm and humid conditions and relatively short transport distances. These findings provide a geochemical basis for understanding sedimentary processes and environmental evolution in the Dongping Lake basin and offer valuable support for regional water resource management, ecological restoration, and sustainable watershed governance. Full article

China’s vast rural landscape exhibits pronounced regional disparities in both foundational resources and development potential. In the context of nationwide rural revitalization efforts, the emergent divergence in village development pathways underscores a pressing need for context-specific, classified interventions. To furnish a scientifically grounded typology of villages and inform differentiated development planning, this investigation focuses on Hubei Province as an illustrative case. Synthesizing survey data from 32,457 villages, we developed a multidimensional evaluation framework encompassing four pivotal domains: economic vitality, social service provision, ecological integrity, and cultural value. Leveraging the Self-Organizing Feature Map (SOFM) neural network—an unsupervised machine learning algorithm—we performed a cluster analysis on multi-source, heterogeneous datasets. This technique enabled the objective delineation of spatial typological patterns among Hubei’s villages, elucidated their underlying classification architecture shaped by multifaceted drivers, and demonstrated the methodological robustness and applicability of this approach for large-scale village categorization. Grounded in the derived typologies and informed by strategic directives from higher-tier planning instruments, we conducted a nuanced examination of the distinctive attributes characterizing each village type. The findings provide scientific evidence and decision-making support for village classification and rural revitalization planning in Hubei Province, with valuable implications for other regions with similar development foundations in China. Full article

Linear integrators are traditionally used in motion control systems to compensate for static effects and suppress low-frequency disturbances. However, their use is inevitably accompanied by phase delays that limit the performance and robustness of control systems, especially in conditions of parametric uncertainty. In this regard, nonlinear integrators have been considered for several decades as a promising alternative that can weaken phase constraints and improve the quality of transients. In this paper, the concept of nonlinear integrators is reinterpreted in the context of self-organizing motion control of precision stages. In contrast to traditional approaches focused primarily on frequency analysis and the method of describing the function, a method is proposed for the synthesis of a self-organizing control system for nonlinear SISO objects based on catastrophe theory, namely in the class of elliptical dynamics with the property of structural stability. The control action is formed in such a way that transitions between stable modes occur due to bifurcation-conditioned self-organization, without using external switching logic. To ensure strict analytical guarantees of stability, the Lyapunov gradient-velocity vector function method is used, which guarantees aperiodic robust stability, suppression of oscillatory and chaotic modes, as well as monotonic convergence of trajectories under conditions of parameter uncertainty. The parameters of the nonlinear integrator are adapted using Self-Organizing Maps (SOM), while any parameter changes are allowed only within the regions that meet the conditions of Lyapunov stability. This approach ensures the alignment of analytical and data-oriented methods without violating the structural stability of the system. The results of numerical experiments demonstrate the superiority of the proposed method in comparison with classical linear and adaptive regulators in problems of controlling the movement of stages, especially near bifurcation boundaries and with significant parametric uncertainty. The results obtained confirm that the integration of nonlinear integrators with catastrophe theory and self-organization mechanisms forms a promising basis for the creation of robust and high-precision motion control systems of a new generation. Full article

Invasive freshwater fishes often display high trophic plasticity, facilitating their establishment and persistence in novel environments. This study examined the feeding ecology, growth patterns, and trophic role of the invasive black bullhead Ameiurus melas in the eutrophic Gruža Reservoir (Central Serbia), with emphasis on ontogenetic dietary shifts and potential ecological impact. Diet composition was analyzed in 103 individuals representing three age classes using traditional diet indices, Costello graphical analysis, self-organizing maps (SOMs), and the Indicator Value (IndVal). Chironomidae, Protozoa, and fish eggs were the dominant dietary components across age classes, although their relative importance varied ontogenetically. Younger individuals exhibited a more generalized feeding strategy, whereas older fish showed increased specialization on benthic prey. SOM-IndVal analyses revealed prey taxa associated with specific feeding patterns at the individual level, identifying Diptera as an indicator prey not detected by population-level indices. Length–weight relationships indicated negative allometric growth (b < 3) across all age classes, consistent with a diet dominated by low-energy prey. These feeding patterns may contribute to altered benthic processes, reduced native fish recruitment, and reinforcement of eutrophic conditions. Overall, the results highlight the pronounced trophic flexibility and ecological plasticity of A. melas, supporting its invasive success in degraded freshwater ecosystems. Full article

The North China Plain is one of the largest plains in China, where domestic water supply, agricultural irrigation, and industrial production rely on groundwater resources. Groundwater quality is increasingly affected by the combined effects of intense human activity and geological conditions. To ensure sustainable groundwater utilization, it is crucial to investigate the hydrogeochemical processes linked to hydrogeological conditions. In this study, 85 samples were collected from cold wells and 56 samples from geothermal wells in North China. By integrating self-organizing mapping (SOM), hydrochemical and isotopic analysis, nitrate distribution, water quality index (WQI), and human health risk assessment (HHRA) methodologies, we systematically evaluated the spatial variability of groundwater quality and the associated health risks in the region. Hydrochemical analysis indicates that groundwater recharge is primarily driven by atmospheric precipitation. Shallow cold groundwater in Cluster 1 exhibited a mixed phase, whereas geothermal water in Clusters 2 and 3 and cold groundwater in Cluster 4 predominantly displayed a Na-Cl type. Cation exchange processes are the primary factors controlling ion composition. Water quality assessment studies indicate that 75.15% of the groundwater is suitable for drinking. The average water quality index of the geothermal water was higher than that of the cold water. Shallow groundwater in plains is significantly affected by agricultural activities, typically manifested as elevated NO₃⁻ concentrations. Arsenic and boron are the primary non-carcinogenic risk pollutants in geothermal water, and children are more vulnerable than adults. The non-carcinogenic risk zones for cold wells were primarily distributed in Shijiazhuang, Baoding, and the coastal areas downstream of the Yellow River. Tianjin has high-risk geothermal water. Therefore, effective strategies must be implemented to protect this valuable water resource and achieve sustainable development in the region. Full article

Land use transformation directly affects the stability and sustainability of regional ecosystems. Clarification of the trade-off/synergy dynamics among ecosystem services (ESs) provides a theoretical foundation to understand the transition of ES interactions from trade-offs to synergies, thereby facilitating the achievement in ecological sustainability in the ecoregion. This study, taking Jiangxi Province, China, as an example, utilized the InVEST model, Theil–Sen estimator, Mann–Kendall test, bivariate spatial autocorrelation, ecosystem service bundles (ESBs), and Random Forest (RF) models to conduct such an ecosystem-focused integrated analysis. According to land use changes from 1980 to 2020, the time-series spatiotemporal patterns of water yield (WY), soil conservation (SC), habitat quality (HQ), and carbon storage (CS) were analyzed. Differences in ES trade-off/synergy relationships and their underlying motivating factors were examined using a 3 km spatial grid framework. Compared with previous studies that mainly focused on typical subregions and of which driver analyses often remained at the individual ES level, this study introduced an explainable RF-SHAP framework based on the cooperative game theory at the grid scale, to quantitatively characterize the relative contributions of every motivating factor to ES trade-off/synergy relationships. The results indicate that from 1980 to 2020, forests and croplands constituted the predominant land use types, taking up 88% of the studied area. Throughout this period, forests, croplands, and grasslands decreased markedly, while built-up areas expanded notably, with a rise of 2876.65 km². Over the same time span, WY increased on average by 0.50% whereas SC, HQ, and CS declined by 0.50%, 0.98%, and 1.30%, respectively. Overall, these ESs demonstrated a geographical distribution characterized by low levels in SC, HQ and CS in the central area and high levels towards the provincial boundary. At the grid scale, the four ESs demonstrated predominantly a synergistic relationship while WY&HQ and WY&SC pairs were characterized by trade-offs. The constraint effect analysis revealed U-shaped relationships for SC&HQ, WY&HQ, and WY&SC, and inverted U-shaped relationships for SC&CS and HQ&CS, with clear threshold effects among these ES pairs. Based on self-organizing maps, the study area is partitioned into six ESBs, and the trade-off/synergy linkages of ESs are affected by the interplay of natural and societal forces. Elevation, slope, and rainfall emerge as the primary driving variables accompanied by population density and proximity to urban centers. These results are anticipated to offer reference to governments for their sustainable management in environmental resources to achieve United Nations Sustainable Development Goal (SDG) 15 (Life on Land: Protect, restore and promote sustainable use of terrestrial ecosystems). The methods used in this paper provide a replicable framework for exploring ES interactions and driving mechanisms in other ecologically sensitive regions in the world. Full article