The Yellow River Delta is one of China’s most ecologically fragile regions, experiencing prolonged pressures from rapid urbanization and ecological degradation. Existing research, however, has predominantly focused on constructing ecological security patterns under single scenarios, with limited systematic multi-scenario comparisons and insufficient statistical support. To address this gap, this study proposes an integrated framework of “land use simulation—multi-scenario ecological security pattern construction—statistical comparative analysis.” Using the PLUS model, three scenarios were constructed—Business-as-Usual (BAU), Priority Urban Development (PUD), and Priority Ecological Protection (PEP)—to simulate land use changes by 2040. Habitat quality assessment, Multi-Scale Pattern Analysis (MSPA), landscape connectivity, and circuit theory were integrated to identify ecological source areas, corridors, and nodes, incorporating a novel hexagonal grid partitioning method. Statistical significance was evaluated using parametric tests (ANOVA, t-test) and non-parametric tests (permutation test, PERMANOVA). Analysis indicated significant differences in ecological security patterns across scenarios. Under the PEP scenario, ecological source areas reached 3580.42 km² (12.39% of the total Yellow River Delta), corresponding to a 14.85% increase relative to the BAU scenario and a 32.79% increase relative to the PUD scenario. These gains are primarily attributable to stringent wetland and forestland protection policies, which successfully limited the encroachment of construction land into ecological space. Habitat quality and connectivity markedly improved, resulting in the highest ecosystem stability. By contrast, the PUD scenario experienced an 851.46 km² expansion of construction land, resulting in the shrinkage of ecological source areas and intensified fragmentation, consequently increasing ecological security risks. The BAU scenario demonstrated moderate outcomes, with a moderately balanced spatial configuration. In conclusion, this study introduces an ecological restoration strategy of “five zones, one belt, one center, and multiple corridors” based on multi-scenario ecological security patterns. This provides a scientific foundation for ecological restoration and territorial spatial planning in the Yellow River Delta, while the proposed multi-scenario statistical comparison method provides a replicable methodological framework for ecological security pattern research in other delta regions.

Estimating forest aboveground biomass (AGB) in mountainous forest ecosystems remains a significant challenge due to complex terrain, the high cost and limited applicability of traditional field-based methods. To address this issue, a remote sensing-based AGB estimation framework integrating intelligent optimization and machine learning was developed for Mount Tai in eastern China. Sentinel-2 multispectral data were selected to derive 105 candidate variables, including spectral bands, vegetation indices, texture features, and topographic factors, from which 17 key variables were selected using Pearson correlation analysis for model construction. A Support Vector Machine (SVM) optimized by the Pigeon-inspired optimization (PIO) algorithm was developed to adaptively determine optimal hyperparameters, and its performance was compared with that of Random Forest (RF) and standard SVM models. Among the three models, PIO-SVM produced the highest numerical accuracy. For the training dataset, it obtained an R² of 0.85 and an RMSE of 46.12 t/hm². For the testing dataset, it achieved an R² of 0.73 and an RMSE of 62.19 t/hm², compared with 0.72 and 66.25 t/hm² for the standard SVM model and 0.70 and 65.19 t/hm² for the RF model. The spatial distribution of AGB derived from the optimal model shows higher AGB values in the central and northern regions characterized by dense forest cover, in close agreement with field observations. Overall, the results suggest that PIO-based parameter optimization can improve SVM performance for AGB estimation in mountainous forests. This study provides a reliable and efficient framework for regional-scale monitoring of forest biomass and carbon sink dynamics.

Accurate estimation of aboveground biomass (AGB) in mountainous forest ecosystem remains a significant challenge due to complex terrain, the high cost and limited applicability of traditional field-based methods. To address this issue, a remote sensing–based AGB estimation framework integrating intelligent optimization and machine learning was developed for Mount Tai in eastern China. Sentinel-2 multispectral data were selected to derive 105 candidate variables, including spectral bands, vegetation indices, texture features, and topographic factors, from which 17 key variables were selected using Pearson correlation analysis for model construction. A Support Vector Machine (SVM) optimized by the Pigeon-inspired optimization (PIO) algorithm was developed to adaptively determine optimal hyperparameters, and its performance was compared with that of Random Forest (RF) and standard SVM models. The results demonstrate that the PIO-SVM model achieved the best overall performance. For the training dataset, the model obtained an R² of 0.85. For the test dataset, the R² reached 0.73, outperforming RF (0.70) and standard SVM (0.72). The spatial distribution of AGB derived from the optimal model shows higher AGB values in the central and northern regions characterized by dense forest cover, in close agreement with field observations. These findings indicate that the PIO algorithm effectively enhances SVM hyperparameter optimization in complex parameter spaces, significantly improving the accuracy and stability of AGB estimation in mountainous forest. This study provides a reliable and efficient framework for regional-scale monitoring of forest biomass and carbon sink dynamics.