Search Results (1,119)

Accurate prediction of soil organic carbon (SOC) at fine resolution is crucial for precision soil management; however, existing national products for Hungary remain too coarse for farm-scale applications. Focusing on Hungarian croplands, we developed a 30 m resolution SOC map using multi-temporal bare-soil composites, DEM derivatives, SHAP interpretability and bootstrap uncertainty. Among five evaluated algorithms, the GBDT model achieved the best performance (test R² = 0.518, RMSE = 4.498 g·kg⁻¹, MAE = 3.499 g·kg⁻¹, RPIQ = 2.229, LCCC = 0.621). SHAP analysis revealed pronounced nonlinear effects of spectral and topographic variables within this modeling framework, with spectral predictors playing a dominant role in SOC prediction. Furthermore, the bootstrap uncertainty framework yielded a Prediction Interval Coverage Probability of 94.59% at the 95% confidence level, indicating reliable interval estimation for the test set. Spatial patterns of uncertainty varied considerably, with higher values in the western hills and southern sands, and moderate levels in the northern low-mountain areas. Benchmark comparisons showed that our 30 m map captures fine-scale heterogeneity often smoothed over by coarser products, while the uncertainty layer supports risk-aware interpretation. Overall, this study provides a regionally calibrated framework for mapping in similar heterogeneous agricultural landscapes, providing practical insights for local management. Full article

Spatiotemporal differentiation and coupled driving mechanisms of urban ecological resilience in transboundary composite economic belts remain an understudied niche within human–land coupling system research. Taking 29 prefecture-level and county-level units of the Huaihe River Eco-Economic Belt from 2014 to 2023 as research samples, this study constructs an ecological resilience evaluation framework tailored to the pollution disturbance characteristics of the Huaihe River Basin under a three-dimensional theoretical framework encompassing resistance, adaptability, and recoverability. The entropy weight method is adopted to calculate comprehensive ecological resilience values, while the geographically and temporally weighted regression (GTWR) model is applied to identify spatiotemporal heterogeneous correlations among multiple influencing factors. This paper further characterizes the spatiotemporal evolutionary patterns of urban ecological resilience across the study area and unpacks the coupled associative effects of natural, economic, and social driving factors. The empirical results reveal three key findings: (1) Temporally, the overall comprehensive ecological resilience of the study region rose from 0.318 to 0.416, with a total growth rate of 30.91%. Its evolutionary trajectory follows three successive phases: rapid growth, steady improvement, and slow saturation. Adaptability, which is predominantly boosted by anthropogenic environmental governance, constitutes the primary contributor to resilience growth. The range of urban resilience values narrowed by 9.97%, indicating continuous advancement in balanced regional development. (2) Spatially, ecological resilience presents a prominent core-periphery pattern, with high-resilience zones concentrated in mountainous southwestern areas and low-resilience zones distributed across northeastern plains. All low-resilience county-level units were eliminated by 2023. (3) In terms of driving associations, topographic relief and environmental governance investment maintain persistent positive correlations with ecological resilience, while per capita GDP acts as the core economic supportive factor. The proportion of secondary industry and population density exhibit significant negative correlations with resilience. The normalized difference vegetation index (NDVI) shifts from a negative correlation to a weak positive correlation alongside progressive ecological restoration, whereas river network variables exert negligible long-term associative impacts. Collectively, the spatiotemporally heterogeneous coupling of natural endowments, industrial-economic conditions, and social governance factors shapes the evolutionary patterns of regional ecological resilience. This study fills the research gap regarding long-timescale resilience driving mechanisms for transprovincial composite river basins covering five provinces. It identifies novel human–land coupling mechanisms, including the temporal reversal of vegetation’s ecological benefits and the dual stress imposed by industrial agglomeration and dense human settlements in plain regions. The quantitative outputs of this research can provide data-based references for differentiated coordinated ecological governance across the Huaihe Ecological Economic Belt. Full article

Background/Objective: Quantitative electroencephalography (qEEG) microstates, recorded under both eyes-open (EOR) and eyes-closed (ECR) resting conditions, provide a powerful neurophysiological approach for capturing the temporal dynamics of cognitive processing. Nevertheless, microstate syntax remains poorly delineated in mild cognitive impairment (MCI) and Alzheimer’s disease (AD). The present study seeks to identify potential drivers of altered microstate topography and temporal dynamics across advancing stages of cognitive decline. Methods: Resting-state EEG (rEEG) was recorded from 60 participants (40–90 years old) in each of three groups: MCI, AD, and healthy controls (HC), under both EOR and ECR conditions. After artifact rejection with EEGLAB in MATLAB R2024a, the final dataset comprised 180 clean recordings per condition (EOR and ECR) and 360 recordings in total. Microstate analysis was performed using the MICROSTATELAB toolbox. Potential group differences in microstate topography were examined with topographic analysis of variance (TANOVA). Four canonical microstates were extracted and labeled A, B, C, and E, following the well-established classification scheme. Results: Analysis of microstate topographies revealed significant group-level differences in the EOR condition for Microstate A (auditory network; p = 0.003), Microstate C (salience network; p = 0.004), and Microstate E (executive network; p = 0.036). In contrast, no significant between-group differences emerged under the ECR condition (all p > 0.05). Within-group comparisons indicated that Microstate B (visual network) was the only class to differ between the two resting conditions in healthy controls and patients with MCI. In the AD group, however, condition-related differences extended to Microstates A, C, and E, suggesting a more distributed disruption of network dynamics in advanced disease. Temporally, Microstate B coverage was the only parameter to show a significant between-group difference, being greater in MCI than in AD under the EOR condition (p = 0.031); visual trends of increasing Microstate A duration and decreasing Microstate C occurrence toward AD did not reach statistical significance. Conclusions: This study’s rEEG microstate analysis uncovered condition-dependent and disease-sensitive alterations across the HC, MCI, and AD groups. The EOR condition proved more diagnostically informative, with significant group-level topographic differences emerging for Microstates A, C, and E, whereas the ECR condition yielded no reliable between-group effects. Microstate B coverage showed the only significant temporal alteration, distinguishing MCI from AD under EOR, while Microstate A and Microstate C showed non-significant trends warranting replication in larger cohorts. Full article

The Szczecin Lagoon’s shores and its water fluctuations were analyzed. The rates of shore retreat and other threats are presented for the period 2002–2026. This work aims to present shores prone to water and ice-shove erosion and flooding. The spatial distributions of different coasts and their morphologies and geology were examined. Data were obtained through field investigations following the strongest surges, and from secondary sources, including topographic information about the coasts. The hydrometeorological conditions in which erosion is likely to occur were investigated. Events associated with the highest water levels increase in the 21st century, and examples of their impacts on the shores are given. The relationship between sea-level changes and lagoon waters during the largest storm surges in the 21st century was analyzed. During storm surges, the water level (WL) in the lagoon may be 1 m above the mean sea level (AMSL), but run-up in the lagoon may reach up to 2 m AMSL. The length of the eroded coast has increased. An increasing number of small erosive coves are cut off in reed belts and shore sediments. Their annual retreat rate is 0.1–0.2 m. Large sections of the low-lying coast up to 2 m AMSL are prone to flooding during high water levels. The rate of retreat is 0.3–0.7 m/y on most eroded coasts prone to wind and surges. Due to the observed threats, several methods of coastal protection are used. These were analyzed and are presented in spatial terms. Full article

Background: Glioblastoma (GBM) shows marked heterogeneity in overall survival (OS), yet robust radiological prognostic markers remain limited. The prognostic value of peritumoral edema and tumor location remains uncertain. Objective: To evaluate whether peritumoral edema, tumor burden, and spatial tumor distribution predict OS using automated MRI analysis and Brain-Grid-based topographical mapping. Methods: In this retrospective study, preoperative T1-contrast-enhanced and T2-FLAIR MRI sequences from 271 patients with IDH-wildtype GBM were analyzed using automated segmentation (Raidionics). Tumor and edema volumes, edema-to-tumor ratio (ETR), and voxel-wise infiltration patterns were extracted. Location was mapped using the Brain-Grid system. Survival was assessed using Kaplan–Meier and multivariable Cox regression adjusted for age and tumor volume, with correction for multiple testing. Results: In multivariable analysis, only age remained a conventional independent predictor of OS (HR 1.03, p < 0.001). Tumor volume, edema volume, and ETR were not associated with survival. In contrast, Brain-Grid analysis identified two centrally located subcortical voxel regions that remained significantly associated with shorter OS after full adjustment and multiple testing correction. Total number of infiltrated voxels showed no prognostic value. Conclusions: Spatially defined subcortical infiltration patterns, rather than global tumor or edema burden, independently stratify survival in GBM. These findings highlight the prognostic relevance of voxel-level tumor topography and support further validation of Brain-Grid-based imaging biomarkers. Full article

Deep learning surrogate models trained with mean-squared-error loss produce statistically accurate but physically unconstrained flood predictions: water may flow uphill, appear spontaneously, or smooth over street-level corridors. In this work, a physics-informed training framework is developed for CNN-LSTM models that predict urban flood depths at 15 min intervals over a $128\times 128$ spatial grid. Three differentiable penalty terms are embedded directly into the loss function: (i) a gravity loss that penalizes depth increases against the water-surface-elevation gradient, (ii) a continuity loss enforcing local mass conservation with rainfall-adaptive thresholds, and (iii) a topography-aware false-alarm penalty modulated by the topographic wetness index (TWI). The framework is evaluated on the Norfolk, Virginia, flood dataset spanning two major storm events (August 2017 and September 2022) comprising 300 samples, with all variants trained on identical splits and robustness assessed over repeated random splits and leave-one-storm-out tests. A road-proximal evaluation restricted to a TWI-derived street mask quantifies street-level skill. The physics-constrained model achieves near-zero gravity violations (∼10⁻⁶) and the highest street-channel recall (0.77 ± 0.09 versus 0.44 ± 0.10 for the unconstrained baseline), the capability most relevant to downstream traffic routing, and its recall advantage more than doubles on a held-out storm, while a uniform false-alarm variant attains 16% lower mean absolute error but suppresses street recall to 0.25. The proposed TWI-modulated penalty reconciles this trade-off: it improves upon the uniform variant on every metric measured, recovering 60% higher street recall at the lowest MAE among all constrained variants and the best street-level F1 score. These results expose a fundamental tension between aggregate pixel-level error metrics and application-specific physical plausibility, and demonstrate that terrain-aware loss modulation offers a principled resolution. Full article

The Dongping Lake Basin (DLB) serves as a critical water regulation and supply zone for the South-to-North Water Diversion Project in China. Understanding the coupling effects and influence mechanisms between ecosystem services is essential for regional ecological restoration and sustainable development. This study employed the Coupling Coordination Degree (CCD) model, Random Forest, and Geodetector. We analyzed the spatiotemporal characteristics and driving factors of the relationship between carbon storage and water yield in the DLB from 1990 to 2020. The results showed that: (1) Carbon storage and water yield exhibited a pronounced spatial mismatch. This was generally characterized by a pattern of high in the eastern/northeastern regions and low in the west/southwest. (2) The overall coordination between carbon storage and water yield remained at a medium-to-low level. Temporally, the CCD followed a trajectory of initial stability, abrupt decline post-2000, and subsequent low-level stagnation. Spatially, the CCD presented an agglomeration gradient of “high in the northeast and low in the southwest”. It also exhibited a significant positive correlation with rising elevation, peaking in mid-to-high altitude zones. Furthermore, the overall coupling relationship showed a continuous degradation trend, heavily concentrated in the southwestern region. (3) Land use type and topographic slope were the primary driving factors shaping the CCD pattern. However, the synergistic interaction between precipitation and soil sand content demonstrated the strongest spatial explanatory power. This underscores the necessity of adapting localized management to specific environmental conditions. This study provides scientific support for carbon sink enhancement and water resource management in lake basins, thereby mitigating potential negative impacts on human well-being. Full article

Evaluating the lateral bearing behavior of rectangular piles in sloping ground is computationally demanding due to the complex three-dimensional spatial pile-soil interaction. To circumvent the inefficiency of full-scale numerical modeling and the limitations of conventional p-y methods, this study proposes a simplified analytical framework for rapid preliminary design. By systematically isolating the topographical slope effect and the cross-sectional shape effect, a series of mathematical modification factors, namely the ultimate lateral capacity factor K_H, the maximum bending moment factor K_M, and the maximum reverse shear force factor K_Q, were established utilizing a standard level-ground square pile as the computational baseline. The results indicate that increasing the slope angle from 0° to 30° reduces the lateral capacity by approximately 14–20%, whereas increasing the aspect ratio from 1 to 4 effectively compensates for this reduction, improving the capacity by approximately 75%. However, the correspondingly enhanced flexural stiffness simultaneously triggers a substantial non-linear amplification in both the maximum bending moment and the deep reverse shear force. Benchmark comparisons show a maximum deviation of 4.58% for lateral capacity, while the maximum deviations in bending moment and reverse shear force are 10.43% and 9.78%, respectively. By integrating these modification factors with conventional equivalent calculation methods, this study provides an efficient analytical tool for rectangular pile foundation design in sloping ground. Full article

This paper addresses the geomorphic response of an engineered Chicago beach to a >1.5 m rise in Lake Michigan’s base water level, from 2013 to 2020. Topographic monitoring data acquired since 2012 and subsurface geophysical data collected in 2022 are integrated to explore the roles of lakefront infrastructure and beach topographic development on sedimentary dynamics, beach morphologic development, and stratigraphic architecture. While conceptual models of coastal geomorphology infer upward and landward beach-profile translation with lake-level rise, a high degree of along-shore variance occurs within pocket beaches. This stems from infrastructure-related modifications of storm hydrodynamics and scour patterns, close to shore, and backshore terrain physiography. The studied beach evolved contrary to how regional littoral drift patterns would have suggested, with erosion most severe along the embayment’s downdrift end, a product of infrastructure-induced scour and the reduced capacity for sediment retention through overwash accretion. Documented geomorphic patterns with lake-level rise are manifested in subsurface imaging data from the lake-level highstand, accordingly, providing a guide to more regional paleo-reconstruction. Great Lakes urban pocket beaches buffer shoreline infrastructure, offer recreational terrains, and support dune ecosystems of value to migrating shorebirds. Understanding their geomorphology benefits coastal managers looking to mitigate impacts of future climate and lake-level change. Full article

Vegetation restoration is widely used to combat soil erosion on the Chinese Loess Plateau, where intense rainfall and steep slopes make this region one of the most eroded areas in the world. However, the effectiveness of strip grass cover (Vc) in reducing erosion under varying rainfall and topographic conditions remains insufficiently quantified. In this research, based on indoor simulated rainfall experiments in a soil tank, we investigated the erosion characteristics of slopes under six Vc levels (0%, 20%, 30%, 40%, 50%, and 60%), three rainfall intensities (RI) (1.33, 1.67, and 2.0 mm·min⁻¹), and four slope gradients (SG) (10°, 15°, 20°, and 25°), and quantified the effects of Vc on slope erosion processes. Runoff and sediment reduction effects by Vc ranged from 3.5% to 62.6% and from 15.2% to 99.1%, respectively. An exponential decay in erosion rate was observed with increasing Vc, whereas runoff velocity initially decreased and then increased as the Vc increased. By integrating RI, SG, and Vc, the average runoff rate and erosion rate models accurately simulate erosion processes on Vc slopes. These findings provide laboratory-based evidence that Vc substantially reduces slope erosion, and support the development of empirical models for predicting runoff and erosion under the tested conditions. Full article

Improving water use efficiency (WUE) is a crucial approach to addressing agricultural water scarcity and promoting the sustainability of agricultural ecosystems. Although extensive research has been conducted on the factors associated with cropland WUE, the relationship between cropland fragmentation and WUE remains poorly understood. This study focused on northern China and employed an integrated “size–shape–configuration” framework to measure cropland fragmentation from 2005 to 2020. A geographically weighted regression (GWR) model was then applied to analyze the spatially varying relationships between cropland fragmentation and WUE. The results showed that over half of northern China experienced intensified cropland fragmentation. Noticeable spatial heterogeneity was observed, with relatively low fragmentation in the North China Plain and the Northeast China Plain and higher levels in the topographically complex northwestern region. Throughout the study period, the size-based fragmentation index (FI_size) consistently exhibited higher mean values than the shape-based (FI_shape) and configuration-based (FI_config) indices. The mean cropland WUE across the 1027 analysis units increased from 0.962 to 1.071, although 220 units—mainly distributed in the three northeastern provinces—experienced a decline. Among the analysis units with statistically significant local coefficients, FI_config was predominantly negatively associated with WUE, whereas FI_size and FI_shape were predominantly positively associated with WUE, with the positive associations mainly concentrated in the North China Plain. Moreover, FI_config exhibited larger absolute local coefficient magnitudes and greater spatial variability than the other two fragmentation dimensions. Environmental factors also showed distinct spatial associations with WUE, with annual precipitation and NDVI being predominantly positively associated with WUE, whereas soil erodibility and slope were mainly negatively associated. These findings highlight the need for region-specific management of cropland landscape patterns. This study provides preliminary quantitative evidence of the relationships between cropland fragmentation and WUE, offering valuable insights for improving WUE and promoting sustainable agricultural management. Full article

Cloud and quality screening removes approximately 65% of daily TROPOMI tropospheric NO₂ pixels, creating structured data gaps that coincide with meteorological conditions driving pollution extremes. Standard gap-filling methods—kriging, Random Forests and other machine learning methods—act as statistical smoothers that systematically suppress extreme concentrations and ignore the Missing Not At Random (MNAR) character of cloud-induced missingness. Here we present a physically informed framework that treats urban NO₂ as a forced nonlinear dynamical system and reconstructs missing satellite observations through geometric navigation on a shadow manifold rather than statistical interpolation. The framework integrates five components: (i) Multivariate State-Space Reconstruction (MSSR) using multiview embeddings of continuous ground-based NO₂, O₃, and ERA5 meteorology, grounded in Stark’s forced-system embedding theorem; (ii) Short-Time Regime-Conditioned Convergent Cross Mapping (ST-RC-CCM) with a spatial-mismatch negative control for falsifiable causal validation; (iii) Inverse Probability Weighting (IPW) to correct the clear-sky sampling bias; (iv) trajectory-matrix denoising via Singular Spectrum Analysis (SSA) and Robust PCA; (v) topology-inspired fidelity metrics—Manifold Overlap Ratio (MOR) and Dynamic Trend Capture (DTC)—that penalize smoothing artefacts. The physical basis for this coupling is the shared dynamical history of surface and column NO₂: tropospheric NO₂ has a photochemical lifetime of 1–4 h near urban emission sources, comparable to the boundary layer mixing timescale, ensuring that surface and column concentrations are jointly governed by the same emission–photolysis–transport attractor. The planetary boundary layer height (PBLH), solar zenith angle (SZA), and surface O₃—all included as MSSR coordinates—are the dominant physical drivers of the instantaneous surface-to-column scaling, and their joint trajectory in state space constitutes the physically grounded basis for analogue selection. The framework is validated on a synthetic forced Lorenz-96 system, then applied to five European primary cities spanning contrasting regimes (Sofia, Milano, Stuttgart, Kraków, Hamburg) plus five N1 spatial-mismatch control stations (Plovdiv, Genova, Frankfurt, Warszawa, Berlin)—ten urban-background stations across four countries—with structured ablations (A0-A4V-A4K). Across >3600 evaluations, MOR_ext distributions for EDM and non-EDM methods are non-overlapping by a factor exceeding 5× (EDM minimum 0.59 vs. non-EDM maximum 0.10; median non-EDM MOR_ext ≤ 0.05 at every city × mask combination), while EDM achieves MOR_ext up to 0.915 (Milano Po Valley). Under a fair-comparison benchmark that withholds ground-level NO₂ from Random Forest, EDM’s RMSE advantage remains robust at a median of 3.9× (RF_FULL) and increases to 4.2× (RF_METEO), confirming that the performance gap is physical rather than an information artefact. A three-level temporal validation—within-window pseudo-cloud masking, cross-year transfer (full 2022 holdout and DJF 2023/24), and a COVID-19 out-of-distribution test—demonstrates robustness beyond standard train/test splits, with CCM library-length convergence confirmed for 60/60 ablations (p < 0.001) across all ten stations. Spatial-mismatch tests confirm local dynamical specificity at all five primary–control pairs (Δρ = 0.090–0.210), with seasonal modulation driven by orographic and synoptic mechanisms. These results establish manifold-based gap filling as a dynamically informative complement to statistical approaches, particularly in topographically confined, stagnation-prone basins where preserving extreme-event geometry is essential for exposure assessment. Full article

Clarifying how ecosystem services (ESs) change over time and space, and how their trade-offs and synergies evolve, is essential for regional ecological protection and high-quality development. Using Shandong Province as a case study, this research quantified carbon storage (CS), water yield (WY), soil conservation (SC), and habitat quality (HQ) with the InVEST model. GeoDetector, geographically weighted regression (GWR), XGBoost-SHAP, Spearman’s rank correlation, bivariate spatial autocorrelation, and spatial overlay analysis were then combined to examine ES patterns, driving mechanisms, and interaction relationships. The main findings are as follows. (1) During 2000–2020, the most evident land-use changes occurred in cropland, grassland, built-up land, and water bodies. (2) The dominant drivers varied markedly among services: CS and HQ were mainly shaped by land-use type and human activity, WY was chiefly controlled by precipitation, and SC was most sensitive to topographic conditions. Factor interactions were generally stronger than single-factor effects, with two-factor enhancement being the prevailing interaction type. (3) ES trade-off/synergy relationships were relatively stable through time. A strong synergy persisted between CS and HQ, whereas CS and SC exhibited a moderate synergistic relationship. By contrast, WY showed evident trade-offs with both HQ and CS, with the WY–HQ trade-off being particularly pronounced. (4) Spatial overlay results showed that the overall ES synergy level remained low. Low-synergy areas accounted for 69.23–70.94% of the study area across the study period. Although strong-trade-off areas expanded overall, high-synergy areas remained limited, indicating considerable room to improve the coordinated provision of ESs in Shandong Province. Full article

Forest fire susceptibility mapping is an important component of disaster risk reduction, particularly in transitional climatic zones such as Anhui Province, China. Traditional approaches often rely on expert weighting (AHP) or linear assumptions, which may be insufficient for capturing the complex, non-linear interactions of fire drivers. This study develops a data-driven framework integrating 816 field-surveyed fuel plots with MODIS active fire data (2000–2025). We applied a systematic preprocessing pipeline, including 1–99% Winsorization to reduce the influence of sensor outliers, Non-Linear Gamma Curvature Normalization to represent asymmetrical risk responses, and a spatial buffer-based pseudo-absence protocol combined with semantic land-cover masking to reduce label ambiguity and macro-environmental bias. Benchmarking against seven machine learning algorithms on a naturally balanced dataset showed that the Random Forest (RF) model achieved the highest test-set performance among the evaluated models (Test AUC = 0.831). Youden’s J statistic was used to define a data-driven risk threshold. The results suggest that topographic configuration and forest stand density act as important baseline constraints and interact with physiological moisture stress indicators to influence fire susceptibility. The species-level risk analysis was broadly consistent with ecological expectations: coniferous forests showed the highest predicted high-risk proportion (79.10%), whereas soft broadleaves showed a substantially lower predicted high-risk proportion (4.29%). Spatial mapping indicated a “South-High, North-Low” pattern associated with topographic forcing and fuel continuity, which may provide useful information for regional fire management and the planning of green firebreaks. Full article

ICESat-2/ATLAS photon-counting LiDAR faces several challenges in regional-scale forest aboveground biomass (AGB) estimation. These challenges include sparse sampling, signal saturation, terrain effects, and limited model generalization. To solve these challenges, this study proposes a new synergistic multi-source remote sensing framework for regional-scale AGB estimation by integrating terrain-corrected ICESat-2 canopy height and forest-type heterogeneity. The framework combines structural, spectral, textural, topographic, and climatic information derived from multiple remote sensing datasets to improve biomass estimation accuracy and model robustness across different forest types. In this paper, multi-source datasets were integrated, including Sentinel-1, Sentinel-2, the Shuttle Radar Topography Mission (SRTM), WorldClim, and a terrain-corrected canopy height model (CHM). Subsequently, candidate features were derived such as spectral, textural, topographic, and climatic variables. In terms of the terrain-corrected CHM, canopy structural parameters were extracted from the Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2) ATL08 data after terrain correction based on a high-resolution DEM. Footprint-level AGB samples were first generated using ICESat-2-derived canopy structural parameters through four regression approaches, including Multiple linear regression, Stepwise multiple regression, Ridge regression, and Lasso regression. These generated AGB samples were then used as response variables for subsequent regional-scale modeling. To build accurate AGB estimation model, key features were first identified using correlation analysis. To account for forest structural heterogeneity, three models including random forest (RF), extreme gradient boosting (XGBoost), and support vector machine (SVM) were developed for regional AGB mapping. To evaluate the performance of the proposed AGB estimation model by integrating terrain-corrected canopy height and forest-type heterogeneity, this study conducted AGB estimation at the Harvard Forest (HARV) site in the United States. The experimental results show that forest-type-specific modeling improves model adaptability and robustness. Among the models (RF, XGBoost and SVM), RF achieved the best performance, with an average coefficient of determination of 0.694. The optimized model was applied to produce a 30 m resolution AGB map. The validation was conducted using airborne LiDAR-derived AGB referenced results. The validation shows that an overall coefficient of determination (R²) of 0.606 and a root mean square error (RMSE) of 16.53 Mg ha⁻¹. These results demonstrate that the proposed new synergistic AGB estimation framework, which integrates terrain-corrected ICESat-2 canopy height with forest-type-specific modeling, provides an accurate and reliable solution for regional-scale forest biomass mapping and carbon stock assessment. Full article