Land use/land cover (LULC) change has greatly altered ecosystem carbon storage capacity and may eventually profoundly impact global climate change. Characterizing the LULC change and its impact on wetland ecosystem carbon stock provides useful data and insights that can guide decision-making procedures aimed at achieving sustainable development objectives. The Yellow River Delta (YRD) represents the most intact coastal wetland and is considered to be the most recent wetland ecosystem in China. It exhibits significant carbon stock capacity and ecological value. Based on the LULC data of the YRD in 2002, 2007, 2012, 2017, and 2022, this paper quantitatively evaluates the spatiotemporal changes in LULC and carbon stock in the region and analyzes the response characteristics of carbon stock to LULC change. The results show significant reductions in cropland and tidal flat wetland areas from 2002 to 2022, resulting in a decrease of 1,428,735.77 t and an increase of 139,856.58 t in carbon stock, respectively. The built-up land area expanded considerably, and carbon stock was lost by 1,467,915.82 t. Spatially, the carbon stock exhibited a pattern of “low along the coast, high inland; low in the center, high around the periphery”. In addition, protecting cropland, reducing building, facilitating the conversion of reservoirs and ponds to forest, and transforming tidal flat wetlands into reservoirs and ponds can increase the region’s carbon storage capacity. These findings provide valuable insights for regional carbon management strategies and ecological protection policies, supporting the sustainable development goals of the Yellow River Delta.

Ponds constitute a pivotal component of aquatic ecosystems. The aquatic ecosystem of the Huai River Basin (HRB) in China was once damaged by severe pollution, and numerous ponds in the basin have not been secured. In this paper, Shenqiu County, a typical county in HRB with many ponds, is selected. Based on high-resolution images with ALOS in 2010, GF-2 in 2016, and GF-1 in 2022, we employed discriminant analysis (DA), classification and regression tree, support vector machine, and random forest to extract the ponds based on object-oriented and further analyzed the spatial-temporal variations of the ponds in this county. The results of the DA in these three years exhibited a higher kappa coefficient (>0.7), and overall accuracy (>75%), signifying superior performance when compared to the other three methods. There were 4625, 5315, and 4748 ponds in 2010, 2016, and 2022, with a total area of 12.87, 11.99, and 9.37 km², respectively. The number of ponds had a trend of rising in the initial period (2010–2016) and falling later (2016–2022), while the total area revealed a continuous decline. Meanwhile, these ponds showed a clustering phenomenon with three main clustering areas, and the scope of the clustering areas also changed to a certain extent from 2010 to 2022. Our study offers valuable methodological support for the ecological monitoring and management of water environments in regions characterized by a dense concentration of ponds. The crucial data related to ponds in this study will help inform both environmental and social development initiatives within the area.

Accurate prediction of geological hazard susceptibility forms the foundation of effective risk management, yet small-sample constraints often limit model generalization. In order to address this issue, this study applied an ensemble method based on predictive symmetry quantification, using Mount Tai, China, as a test case. Thirteen influencing factors were integrated using six machine learning algorithms—Logistic Regression (LR), Multilayer Perceptron (MLP), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), eXtreme Gradient Boosting (XGB), and Support Vector Machine (SVM)—trained on 34 hazard sites. Symmetry breaking in model outputs was quantified, and XGB and MLP, which showed the lowest correlation (0.59), were selected for dynamic weighted integration. Symmetry-adjusted weighting counteracts bias from individual models. For hyperparameter tuning, grid search was employed, while SHapley Additive exPlanations (SHAP) was used to quantify factor contributions. The performance of each model was evaluated using AUC and AP metrics. The key results show that all base models performed robustly (AUC > 0.8), with XGB showing high consistency (AUC = 0.927), and the performance of the symmetry-optimized ensemble (MLP + XGB) exceeded that of all the individual models (AUC = 0.964). The dominant drivers of Geohazards included elevation, slope, the topographic wetness index, and road adjacency, with high-susceptibility zones clustered in southeastern high-altitude terrain, central mountains, and road-intensive north-central sectors. The approach presented here provides an ensemble method based on predictive symmetry quantification that is effective under the constraints of small sample sizes.

Accurately estimating large-scale crop yields amid climate change is increasingly critical for crop management, marketing, and storage. Remote sensing data — especially from Moderate Resolution Imaging Spectroradiometer (MODIS) — are integral to such estimations, yet MODIS's coarse spatial resolution causes notable mixed pixel issues. Crop-specific masks can improve accuracy by filtering out non-agricultural pixels to obtain pure crop pixels, but the optimal mask percentage remains unclear. We evaluated six crop-mask thresholds (50%–100%) to define pure corn pixels for multiple MODIS-derived vegetation indices (VIs) (Two Band Enhanced Vegetation Index (EVI2)/Normalized Difference Vegetation Index (NDVI) from MOD09Q1 at 250m/8-day; Enhanced Vegetation Index (EVI)/NDVI from MOD09A1, MOD13Q1, and MOD13A1 at 500m/8-day, 250m/16-day, and 500m/16-day), and integrated these VIs with regression and machine/deep-learning algorithms for county-level corn yield estimation across the U.S. Corn Belt. Results showed that the seasonal trajectories and inter-annual variabilities of VI–yield correlations derived from different mask thresholds were similar in both pattern and intensity. Importantly, mask threshold selection had a clear influence on corn yield estimation performance and was primarily governed by spatial resolution: for 250m VIs, higher thresholds (80%–100%) generally achieved lower errors, whereas for 500m VIs, lower thresholds (50%–60%) were more robust. In the extreme drought year (2012), 250m VIs benefitted from higher thresholds and 500m VIs achieved optimal performance at intermediate thresholds (70%–80%). These findings provide practical guidance for selecting crop-mask thresholds to improve MODIS-based large-scale corn yield estimation.

The coupling coordination of production, living, and ecological (PLE) spaces is central to territorial spatial optimization, yet its assessment may vary substantially with spatial scale. Using 2020 land use/land cover data for Shandong Province, China, this study evaluated PLE functions at four levels: 2 km grid, township, county, and city. The coupling coordination degree model is then used to measure the coupling coordination level of PLE spaces at these scales, and Global Moran’s I and local spatial autocorrelation analysis are further employed to examine spatial associations. The results showed clear scale-dependent variation in PLE functions, coupling coordination, and spatial clustering. Although the relative ordering of PLE functions remained consistent across all four analytical levels, their mean values varied across scales. Production and living functions reached their highest mean values at the township level, whereas ecological function was lowest at this level and highest at the city level. Spatial variability also differed across levels, with the city level showing the lowest variability for all three functions. Mean coupling degrees remained high across the four levels (0.878–0.968), while mean coupling coordination degrees (0.623–0.670) remained within the moderate-coordination category. Both indicators were lowest at the township level and highest at the city level, although coupling coordination was most variable among townships. Significant positive spatial autocorrelation was observed at all four levels, with Global Moran’s I ranging from 0.285 to 0.732 (p < 0.05); spatial dependence was strongest at the township level and weakest at the city level. Local clusters and spatial outliers also became less detectable at broader levels. These findings show that analytical-unit selection influences estimates of PLE functions, coordination, and spatial dependence. A multi-level framework can therefore support hierarchical and spatially differentiated territorial governance, thereby contributing to regional sustainable development.