Search Results (490)

Traditional linear models in urban informatics struggle to capture the complex, non-linear spatial non-stationarity inherent in metropolitan housing markets. To overcome these constraints, this study introduces a data-driven computational framework integrating a Spatio-Temporal Graph Convolutional Network (STGCN) with gradient-based Explainable Artificial Intelligence (XAI) and Geographically Weighted Regression (GWR). This framework is empirically tested using 217,598 apartment transactions in Busan, the Republic of Korea, augmented with high-resolution micro-demographic grids and Digital Elevation Model (DEM) topographical data. Utilizing unsupervised K-Means clustering, the region is spatially stratified into a dense Urban Core and a dispersed Suburban Periphery. The STGCN demonstrates overwhelming predictive superiority ($R^2=0.802$) over the traditional Spatial Error Model ($R^2=0.437$). Crucially, gradient-based XAI and localized GWR coefficients successfully unspool the deep learning “black box,” visualizing hyper-localized economic realities that global linear models obscure. The analysis expose stark regional market segmentation driven by environmental topography, mathematically quantifying non-linear dynamics such as coastal high-floor premiums, severe mountainous altitude penalties, and latent urban reconstruction premiums. Ultimately, this research bridges the gap between predictive computational power and spatial economic interpretability, offering a robust informatics framework for equitable urban planning. Full article

Revealing the spatial differentiation patterns of cultivated land multifunctionality contributes to the improvement of cultivated land protection policies. This study investigated the spatiotemporal differentiation characteristics and functional zoning of cultivated land multifunctionality in Alpine Valley Area from a topographic gradient perspective. An evaluation index system for cultivated land multifunctionality in Alpine Valley Area was constructed across four dimensions: production (PF), social (SF), ecological (EF), and landscape (LF) functions. Using Yulong County, Yunnan Province, as a case study, methods including kernel density analysis, standard deviation ellipse theory, topographic gradient analysis, and hierarchical clustering were employed to quantify the horizontal and topographic gradient characteristics of the multifunctionality of cultivated land from 2010 to 2020, thereby delineating functional zones. Results indicated: (1) Cultivated land multifunctionality shows clear topographically-dependent spatial differentiation: PF concentrates in central basins and northwest specialty agricultural zones, SF overlaps with production but with more dispersed high/low values, EF follows a “high in the center, low on the lateral areas” pattern, and LF remains relatively stable; (2) Significant hierarchical differences in cultivated land functions were observed along the elevation, slope, and terrain niche index (TNI) gradients. PF, EF, and LF generally decreased with increasing elevation, slope, and TNI, whereas the dominance of SF exhibited an inverted-V-shaped distribution along the gradient. (3) The study area was divided into five zones: Flat-Basin Agritourism Zone (FAZ), River-Valley Eco-Agriculture Zone (REZ), Sub-Alpine Specialty Agricultural Production Zone (SSAPZ), Sub-Alpine Steep Slope Integrated Management Zone (SSIMZ), and Mid-Mountain Steep Slope Ecological Conservation Zone (MSECZ), with differentiated strategies proposed for each. This study innovatively integrates a topographic gradient perspective, TNI, and hierarchical clustering to systematically evaluate the cultivated land multifunctionality in Alpine Valley Area, providing a new methodological framework for similar mountainous regions. Full article

Soil organic matter (SOM) dynamics in tropical montane ecosystems remain poorly understood, particularly regarding the relative importance of particulate versus mineral-associated fractions under varying disturbance regimes. This study investigated SOM fraction distribution across the Ericaceous and Afroalpine belts of Bale Mountains National Park, Ethiopia, an Andosol-dominated landscape subject to recurrent fire. Using a stratified sampling design (n = 30 plots) across four vegetation classes (Ericaceous belt, fragmented Ericaceous belt, herbaceous and heathland, and giant Lobelia areas), three fire history categories (<10, 10–25, and >25 years since fire), and three topographic positions (northern slopes, southern slopes, and central plateau), we quantified coarse particulate organic matter (cPOM: 149–2000 μm), fine particulate organic matter (fPOM: 53–149 μm), and mineral-associated organic matter (MAOM: <53 μm). Particulate fractions dominated the SOM pool, with cPOM and fPOM together accounting for >99% of measured organic carbon. Multivariate ordination revealed a primary gradient (PC1, 61.7%) contrasting particulate-dominated soils in less disturbed areas with relatively MAOM-enriched soils in fire-impacted and fragmented zones. A global comparison reveals a profound stability gap: the Bale Mountains utilize <2% of the mineral stabilization potential of comparable Andosols, demonstrating that extreme fire frequency (<25 yr return interval) overrides even the most reactive mineralogy. We critically evaluate whether standard size-based fractionation adequately captures mineral-associated carbon in volcanic soils and discuss methodological limitations. These results provide baseline data for conservation planning in this biodiversity hotspot and underscore the need for fire management strategies that balance ecological integrity with carbon storage objectives. Full article

Soil fungal communities play a central role in nutrient cycling and ecosystem functioning in tropical montane forests, yet the relative influence of topographic heterogeneity and soil depth on their assembly remains poorly understood. This study evaluated the composition, diversity, and functional structure of soil fungal communities associated with an experimental Podocarpus oleifolius plantation in the Colombian Andes. Using ITS2 rDNA sequencing, fungal assemblages were characterized from soil samples collected around ten trees distributed along a topographic gradient. For each tree, samples were collected at two soil depths (0–10 cm and 10–20 cm), yielding a total of 17 samples after quality control. Topographic variables derived from a digital elevation model were used to evaluate their influence on community structure. A total of 1875 Operational Taxonomic Units (OTUs) were detected, dominated by Ascomycota. No significant differences in alpha or beta diversity were observed between soil depths. In contrast, slope emerged as the strongest environmental driver of community composition. A high proportion of unassigned OTUs highlighted the presence of poorly characterized fungal diversity. These findings highlight the importance of incorporating fine-scale terrain heterogeneity into restoration strategies with native species and into future studies of soil microbial dynamics in tropical montane ecosystems. Full article

Rapid urbanization and complex topography complicate Urban Heat Island (UHI) spatio-temporal dynamics. Traditional models and coarse-resolution imagery often fail to capture fine-scale, spatially non-stationary seasonal driving mechanisms. This study investigates the multi-dimensional drivers of surface thermal dynamics in Kunming, a typical low-latitude plateau city, using seasonal median LST composite (2018–2025). Integrating eXtreme Gradient Boosting (XGBoost) with eXplainable Artificial Intelligence (XAI) models decoupled the nonlinear impacts of these drivers. Results reveal a seasonal thermal dichotomy: Summer exhibits the most intense UHI effect with extreme peak temperatures, while Spring presents an anomaly where natural and vegetated Local Climate Zones (LCZs) show pronounced warming. SHapley Additive exPlanations (SHAP) analysis identified a seasonal rotation: anthropogenic and structural factors dominate Summer and Autumn warming, whereas natural and topographic regulators govern Spring and Winter. GeoShapley deconstruction demonstrated strong spatial non-stationarity. Building-density warming is amplified in poorly ventilated urban cores, and fragmented vegetation’s cooling is offset by anthropogenic heat during peak summer. This study provides new insights into the seasonal drivers of urban thermal environments in plateau cities. Full article

To investigate the influence of complex terrain on precipitation characteristics in the Jinsha River Basin (JRB), this study analyzes the spatiotemporal distribution of precipitation amount, frequency, and intensity under different topographic factors in the middle and lower reaches of the JRB (MLJRB), based on hourly precipitation observations from 1745 ground stations deployed by the China Meteorological Administration. The results indicate the following: (1) Precipitation amount increases gradually from low altitudes, peaks at sub-high altitudes, and then decreases. The highest precipitation frequency occurs at high altitudes, while the greatest precipitation intensity is observed at mid altitudes. (2) Spatially, a high-precipitation center with high frequency and intensity is formed in the lower reaches of the JRB, whereas the northern part of the study area exhibits a low center for both frequency and intensity. (3) Pronounced diurnal and monthly variations are observed at all altitudes. Precipitation amount and intensity peak during nighttime hours. On a monthly scale, both precipitation amount and intensity increase from May to July or August and then decrease, while the trend for precipitation frequency is not entirely consistent. (4) Precipitation amount shows little change with increasing slope gradient. Precipitation frequency increases with slope gradient, whereas precipitation intensity exhibits a clear decreasing trend. Eastern slopes receive higher precipitation amount and frequency compared to other aspects, followed by southern slopes, with western slopes receiving the lowest; however, differences in precipitation intensity among different slope aspects are minimal. In conclusion, the MLJRB exhibits strong spatiotemporal variability, distinct vertical differentiation, and pronounced periodic variation in precipitation. Precipitation frequency and intensity in this region are also associated with micro-topography. Full article

Fragmented farmland and persistent cloud–snow interference in the high-altitude cold regions of the Qinghai–Tibet Plateau, coupled with unstable crop phenology, pose significant challenges for accurate cereal and oil crop identification using single-date imagery or low-dimensional features. This study focused on the agricultural areas of the Shigatse River Valley in the Qinghai–Tibet Plateau. Leveraging the Google Earth Engine (GEE) cloud computing platform, we integrated Sentinel-2 remote sensing data with field survey sampling data to extract the planting structures, distribution patterns, and cultivated areas of cereal and oil crops. Three machine-learning classifiers—Random Forest (RF), Support Vector Machine (SVM), and Gradient Boosted Trees (GBT)—were evaluated to investigate the influence of different feature sets and classifier combinations on mapping accuracy. The results indicated that when all feature bands were utilized, the RF classifier achieved the highest performance, with an overall accuracy of 84.77% and a kappa coefficient of 0.64, outperforming both the SVM and GBT models. The incorporation of phenological and topographic features further enhanced classification accuracy, providing a robust framework for identifying cereal and oil crops in high-altitude environments. Based on the optimal model estimation, the cultivated areas in 2021 were 581.52 km² for highland barley, 295.39 km² for wheat, and 386.81 km² for rapeseed. Their spatial patterns closely aligned with the valley-terrace topography and local irrigation conditions. These findings offer novel insights and a reliable methodology for the rapid extraction of crop spatial information in regions with complex planting structures. Full article

Rural settlements are significant carriers of rural production, living, and land use activities and are also significant subjects for researching regional socio-economic development and spatial structural changes. With regard to the unique topographical environment and transportation situation in the Qiongbei volcanic lava area, a settlement form with prominent topographical constraints and transportation orientation is created. This paper utilizes land use/land cover data from different periods, along with rural settlement expansion patch data, to quantitatively analyze the spatial patterns and expansion characteristics of rural settlements, as well as their influencing factors, from 1990 to 2025 using GIS spatial analysis, buffer gradient analysis (BGA), and multi-order adjacency index (MAI). The research results indicate the following: (1) The spatial pattern of rural settlement distribution in the study area is “peripheral agglomeration and core sparsity,” and the general expansion trend is “rapid in the early period and stable in the late period.” The settlement area expands from 37.21 km² in 1990 to 80.87 km² in 2025. (2) The evolutionary pattern of rural settlements in the study area changes from “core–peripheral extension” in the early period to a mixed “core stabilization and peripheral leapfrogging development” model in the later period. The new patches formed in the peripheral areas have obvious discrete features, such as varying land use patterns and differing population densities compared to the core areas. (3) The spatial correlation factors for rural settlement expansion in the study area exhibit stage differences and distinct spatial non-stationary characteristics. During the early period (1990–2008), with strict limitations imposed by the natural material environment, sunlight (interpretability of 0.367) and water systems (0.286) show significant spatial coherence, indicating the great adaptability of rural settlements to the material conditions of the landforms; during the later period (2008–2025), after the implementation of the rural revitalization strategy, the population density (0.135) and transport-related factors become the main spatial correlation factors. The GWR model also shows the percentage of positive and negative influences by influencing factors at each stage and their significant differences in space, proving that human activities break through in the limitations of natural topology in a discontinuous way. According to this research, “inefficient land use” should be understood in a dialectical manner in volcanic geomorphological areas, and spatial optimization should be achieved on the premise of respecting the physicality of volcanic landscapes and rural identity. The research conclusions have important guiding significance for the spatial resilience planning in tropical volcanic areas and traditional settlement culture preservation. Full article

This study aimed to enhance the accuracy and interpretability of erosion gully classification within black soil regions by focusing on Changxing Township, Xinxing District, Qitaihe City, Heilongjiang Province as the research site. Utilizing RTK (Real-Time Kinematic) surveying technology, three-dimensional topographic data were collected for 139 actively developing erosion gullies. Key morphological parameters—including gully length, depth, gradient, average top width, average bottom width, and slope gradients on both sides—were extracted to construct interactive features. The variable set was refined through correlation analysis and variance inflation factor (VIF) diagnostics to mitigate multicollinearity. A random forest model was employed as the primary classification approach and benchmarked against logistic regression, support vector machines (SVM), decision trees, and backpropagation neural networks. To address class imbalance, a combination of class weighting, Synthetic Minority Over-sampling Technique (SMOTE), and undersampling methods was implemented. Model tuning and interpretability assessments were performed using cross-validation, grid search optimization, and SHapley Additive exPlanations (SHAP) analysis. The findings demonstrate that the random forest model achieved superior overall performance, with test set accuracy, macro-averaged F1 score, and balanced accuracy values of 0.9143, 0.8087, and 0.8427, respectively. Among imbalance handling techniques, class weighting yielded better results compared to oversampling and undersampling. Feature importance and SHAP analyses identified gully length, average crest width, and their interaction with gully depth as the principal determinants influencing gully grade classification. These results elucidate the synergistic developmental dynamics of gully longitudinal extension, vertical deepening, and lateral widening. The proposed methodology offers valuable technical support for the rapid surveying, classification, and management decision-making processes related to black soil erosion gullies. Full article

Groundwater drainage-induced karst collapse is a major geohazard in coal-mining regions of central Hunan, threatening residential safety and infrastructure. This study focuses on the Tuoshan minefield in the Jinzhushan mining area by integrating multi-source field data, including surveys of 170 collapse points, long-term groundwater monitoring at six boreholes, and high-density electrical geophysics. A topographically corrected MODFLOW seepage-field model is developed and calibrated for 2014 (RMSE = 0.32 m; NSE = 0.85) and validated for 2015–2016 (RMSE = 0.41 m; NSE = 0.81). To address the large groundwater-level simulation errors commonly encountered in subtropical hilly karst mining settings, the model incorporates a topographic correction, improving simulation accuracy by 12% relative to an uncorrected model. The simulations capture rapid “steep rise–slow fall” groundwater dynamics: Heavy rainfall (>100 mm/day) raises groundwater levels by 2.8–3.1 m within 2–3 days, whereas pumping (200 m³/h) causes a 1.9–2.2 m decline within one week. A 1.2 km drawdown funnel forms and overlaps with 89% of collapse points, indicating that seepage-field evolution and groundwater-level decline control collapse clustering, with soil suffusion and soil–water–rock interaction acting as key amplifying processes. Based on Terzaghi’s effective stress principle and the Theis solution, a collapse prediction formula is derived and validated using measured events (accuracy = 87.5%), and a region-specific critical hydraulic gradient (i_n = 0.85) is determined, lower than values reported for North China. The proposed workflow provides quantitative thresholds and model-based guidance for karst collapse prevention in subtropical mining areas. Full article

The neotropical genus Inga (Fabaceae) is a fast-growing tree component of tropical forests which plays crucial ecological and functional roles. However, its diversity patterns and the specific environmental drivers that structure its distribution in Andean landscapes remain insufficiently documented. This study aimed to quantify the diversity and distribution of Inga species in the province of Imbabura (4785 km²), northern Ecuador, while evaluating the influence of key environmental determinants. By integrating 52 field records along 321 km of exploration and 22 herbarium records (QCNE, MO, AAU, F, HUTN), the study analyzes the role of topographic variables (12.5 m resolution) and climate data (1 km² resolution). Seventeen species were recorded, almost tripling previous regional findings. The results demonstrate that species richness and occurrence are strongly structured by altitude, temperature, and soil properties as primary environmental drivers. Ten species showed narrow altitudinal ranges and limited thermal tolerance (<2 °C), indicating high habitat specialization, while I. densiflora and I. insignis exhibited broader niches. Edaphically, most species were associated with sandy loam soils, particularly Mollisols and Inceptisols developed from volcanic material. These findings indicate that climatic gradients and edaphic conditions act as the main environmental filters shaping Inga assemblages in heterogeneous montane landscapes. The observed high level of specialization suggests significant vulnerability to land-use change and highlights the need for habitat-specific conservation strategies in Andean forests. Full article

Cultivated land fragmentation has become a critical constraint on regional agricultural sustainable development. Revealing its spatial patterns and driving mechanisms is of great significance for optimizing the utilization and management of cultivated land resources and enhancing regional agricultural productivity. This study focuses on the main grain-producing areas in the middle and lower reaches of the Yangtze River Basin. It constructs a Cultivated Land Fragmentation Index (CLFI) using an integrated method that combines landscape index analysis with an entropy-weighted approach, based on 2023 land-use data. The optimal analytical grain size and extent were determined before employing geographic detectors to identify dominant factors influencing cultivated land fragmentation. The key findings include the following: (1) The appropriate spatial resolution for fragmentation analysis was identified as 330 m, with an optimal analysis extent of 8910 m. (2) CLFI values ranged from 0.001 to 0.973, exhibiting significant spatial heterogeneity. The central plains and northeastern regions demonstrated low fragmentation levels and better contiguous cultivated land distribution, while the western and peripheral areas showed higher fragmentation. A provincial-scale comparison revealed that Jiangxi Province had the highest fragmentation level (0.255), whereas Jiangsu Province had the lowest (0.146). The topographic gradient analysis indicated a decreasing trend from the Guizhou Plateau (0.503) to the North China Plain (0.125), with plateaus and basins showing significantly higher fragmentation than hilly and plain regions. (3) Dominant controlling factors varied among provinces: In provinces with greater topographic relief (Anhui, Hubei, Hunan, Jiangxi), natural factors like elevation, slope gradient, and NDVI primarily controlled fragmentation patterns; in contrast, socioeconomic factors such as nighttime light intensity dominated in Jiangsu Province, characterized by flat terrain and high urbanization. Multi-factor interactions generally enhanced explanatory power regarding spatial patterns, confirming that cultivated land fragmentation is a result of comprehensive multi-factor interactions. This study reveals the spatial distribution characteristics of cultivated land fragmentation at the pixel scale in the study region, providing theoretical foundations and decision-making references for the efficient utilization of cultivated land resources and rural land system reforms. Full article

Digital elevation models (DEMs) are foundational for critical tasks such as flood inundation simulation, disaster risk assessment, and ecosystem monitoring in coastal zones, yet their vertical accuracy is significantly compromised by complex terrain and surface characteristics. This study quantitatively decomposes the vertical errors of three 30 m global DEMs (COP30, NASADEM, and AW3D30) across the subtropical coastal region of Southeast China using ICESat-2 ATL08 data as a reference. By integrating an eXtreme Gradient Boosting (XGBoost) model with SHapley Additive exPlanations (SHAP), we successfully decoupled systematic biases from random noise. The results show that NASADEM achieved the lowest RMSE (7.775 m), followed by COP30 and AW3D30. While the Terrain Ruggedness Index (TRI) and categorically encoded Land Cover were identified as the universally dominant error drivers across all datasets, explainable analysis revealed distinct secondary mechanisms: X-band COP30 is notably susceptible to canopy height, exhibiting significant positive bias in forests exceeding 15 m; C-band NASADEM shows a systematic bias related to topographic position, typically overestimating ridges and underestimating valleys; and optical AW3D30 is significantly affected by stereo-matching errors. Furthermore, the analysis quantified a systematic error component of ~40%. These findings provide a data-driven basis for DEM selection and highlight that accuracy improvements should prioritize vegetation removal for radar DEMs and enhanced stereo-matching for optical models. Full article

Water planning in semi-arid regions depends on climate information that resolves both seasonal timing and topographic gradients. This study evaluated 15 CMIP6 models over Zacatecas, Mexico, and produced a 1 km historical dataset for 1985–2014 by statistically refining bias-corrected daily fields from NEX-GDDP-CMIP6. Downscaling was referenced to the CHELSA climatology: temperature was refined using an elevation-informed hybrid spline approach, whereas rainfall was downscaled with geographically weighted regression (GWR) to represent orographic gradients. The resulting fields were assessed against two independent observational baselines: an automated INIFAP network (2004–2014) and a conventional CONAGUA network (1985–2014). For temperature, BCC-CSM2-MR showed the highest performance, with a Pearson correlation of R = 0.94 for both T_max and T_min. A consistent network-dependent bias pattern was identified: the downscaled models overestimated the diurnal temperature range relative to INIFAP but underestimated it relative to CONAGUA, highlighting the influence of instrumentation and observational protocols on model evaluation. For rainfall, ACCESS-ESM1-5 reproduced the seasonal cycle and dominant orographic patterns, with a correlation of R = 0.611 despite the intrinsic stochasticity of semi-arid rainfall. The resulting 1 km fields provide a spatially consistent baseline for regional applications, including stochastic weather generation and impact models in complex semi-arid regions. Full article

Leaf Area Index (LAI) is a fundamental parameter for characterizing the growth of tea (Camellia sinensis L.). However, in rugged mountainous regions, the combined effects of topographic relief and canopy structural heterogeneity severely constrain the accuracy of UAV-based multispectral LAI retrieval. This study develops an integrated framework combining topographic correction with interpretable machine learning to improve LAI estimation. We utilized a UAV multispectral dataset collected during the peak growing season from a typical tea-growing region in Fujian Province, China (altitude range: 58–186 m), comprising a total of 90 samples. Three topographic correction methods, including Sun–Canopy–Sensor (SCS), SCS with C correction (SCS+C), and Minnaert+SCS, were evaluated in combination with Linear Regression (LR), Decision Tree (DT), Random Forest (RF), and Extreme Gradient Boosting (XGBoost) models. Results indicated that the SCS+C algorithm outperformed other methods by effectively accounting for direct and diffuse radiation components, thereby reducing topographic dependence while maintaining radiometric consistency across heterogeneous surfaces. The XGBoost model combined with SCS+C correction achieved the highest performance (R² = 0.8930, RMSE = 0.6676, nRMSE = 7.93%, MAE = 0.4936, Bias = −0.0836). SHapley Additive exPlanations (SHAP) analysis revealed a structure-dominated retrieval mechanism, in which red-band textural features (Correlation_R) exhibited higher importance than conventional vegetation indices. Compared with previous studies that primarily focus on either topographic correction or model development, this study provides quantitative insights into the underlying retrieval mechanisms. This framework improves the precision of tea LAI retrieval in complex terrains and provides a robust methodological basis for digital management in mountainous agriculture. Full article