Understanding the spatiotemporal dynamics of vegetation under the coupled influence of climatic and anthropogenic drivers is crucial for ecological governance at the river basin scale. This study focuses on the Huaihe River Basin (HRB) in China, a climate-sensitive region spanning both northern and southern climatic zones. Previous studies have often overlooked the inherent temporal and spatial autocorrelation in NDVI time series within this region, which may lead to overestimation or underestimation of vegetation trends, as well as misidentification of spurious trends as statistically significant. To address spatial and temporal autocorrelation challenges, we developed a novel hybrid framework combining Univariate Stationary First-order Gaussian Autoregressive (AR1) modeling with spatial autocorrelation analysis (Moran’s I index), enabling robust detection of vegetation trends, stability evaluation, and clustering characteristics. Combined with Geodetector, we quantified the impacts of climatic extremes, land use change, and urbanization on NDVI patterns(2000–2022). Key findings reveal: (1) A significant greening trend with mean annual NDVI increase of 0.00152 yr⁻¹ (p < 0.05), demonstrating basin-wide ecological improvement; (2) Spatially divergent patterns where 42.89% of the basin show significant NDVI growth, contrasted by 9.54% degradation areas. Notably, 47.57% exhibits non-significant increases, emphasizing the necessity of temporal autocorrelation correction in trend detection; (3) Geodetector analysis identifies land use type as the dominant spatial heterogeneity driver (q = 0.35–0.42), while extreme climatic events (particularly the 2000–2001 mega-drought) govern temporal anomalies. Urban expansion reduced vegetation cover, except near water bodies where NDVI remained stable. Interaction analysis revealed nonlinear synergies between anthropogenic activities (e.g., GDP, population) and climatic factors, emphasizing the need for adaptive policies in transitional ecosystems. These findings advocate for tiered management strategies incorporating climate-adaptive zoning, emphasizing riparian corridor conservation and dynamic land-use optimization to balance ecological restoration with urban development. This work offers a replicable framework for regional-scale ecological assessments.

This research seeks to advance the understanding of ecological management in the Huaihe River Basin, China. The spatiotemporal variability of the Normalized Difference Vegetation Index (NDVI) and its underlying driving forces are examined utilizing SPOT-NDVI data covering the period 2000-2019. Linear regression analysis is employed to quantify trends and assess the statistical significance of NDVI variations. A differencing approach is subsequently applied to discern the variability in NDVI. The distribution of its spatial pattern stability over 20 years is explored through the coefficient of variation. Lastly, the Geodetector method is utilized to elucidate the driving factors influencing NDVI dynamics. The results indicate that the overall NDVI is generally high, with an overall growth rate of 0.00148/year, and 2010 is identified as a significant inflection point in the trend. NDVI values are notably lower in urban areas, corresponding to urban expansion, except for regions near rivers and lakes. Land use type emerges as the strongest explanatory factor for NDVI among single factors, with climate factors exhibiting a relatively weaker degree of explanatory force. These findings suggest that the overall NDVI in the Huaihe River Basin is high, indicative of a vegetation condition that continues to improve.

This paper studies the impact of afforestation on the local climate of the Saihanba mechanical forest farm in the recent 45 years. Based on Landsat satellite images from 1975 to 2019, with an average period of 10 years, the change rule of fractional vegetation cover of the area was obtained by Normalized Difference Vegetation Index (NDVI) and Dimidiate Pixel Model. Combined with climate factors including local temperature and precipitation, the correlation analysis was carried out. The results show that the fractional vegetation cover in Saihanba area has been increasing in the recent 45 years. At present, it has high coverage in most areas and the proportion of highest coverage is 72.18% in 2019. The correlation between fractional vegetation cover and temperature (correlation coefficient is -0.62) is higher than that of precipitation (correlation coefficient is 0.30). The relationship between temperature factors and FVC is nonlinear. Equation fitting was carried out for each temperature factor, and the determination coefficients are all above 0.45. Therefore, there is a correlation between afforestation and local temperature and precipitation, and the correlation with temperature is higher.

The word "Digital Township" comes from "Digital Earth", "Digital China", "Digital City" and "Digital Agriculture". According to theory and technology of "Digital Earth", regarding the research all over the world, "Digital Township" means describing the whole village or town with digital information technology. That is built on the basis of computers, networks, multimedia, mass memory store and other technologies. It describes the village or town by abundant information of multi-resolution, multi-scale and multi-dimension with 3S technology, so that it can provide service for scientific management, decision making and sustainable development of the village or town. In this paper, the main configuration of "Digital Township" is discussed. Then, the construction idea of "Digital Township" and the problems we may meet are put forward. At last, a case of Xiangyin town of Shandong province is illustrated. Xiangyin made beneficial attempt to build its "Digital Township" system. This work is a very good demonstration and induction of digital Township construction. However, there is a long way for all constructors of Digital Township.

Soil particle size fractions (PSFs)—sand, silt, and clay—are fundamental determinants of soil hydrological behavior, nutrient retention, and erodibility, yet their spatial prediction remains challenging due to the compositional nature of the data, unquantified prediction uncertainty, and limited interpretability of machine learning models. This study develops an integrated compositional mapping framework incorporating multi-source Sentinel-1/2 and topographic covariates, coupling the isometric log-ratio (ILR) transformation with Quantile Regression Forests (QRFs), a Monte Carlo simulation (MCS)-based latent-to-physical space uncertainty propagation strategy, and a Wrapper-SHAP attribution method to jointly address these challenges. The framework was evaluated across regional croplands in the central Shandong mountain-hilly region of China, using an elevation-stratified spatial cross-validation. Validations achieved R² values of 0.72, 0.61, and 0.59 for sand, silt, and clay, respectively, and a global Aitchison distance of 0.34. Critically, the MCS error propagation strategy effectively compensated for the probability distribution shift introduced by non-linear ILR back-transformation. This ensured that all predicted compositions strictly satisfied compositional closure and the [0, 100%] constraint, while aligning the prediction interval coverage probability (PICP) of each fraction closely with the 90% nominal level. Wrapper-SHAP overcame direct attribution limitations in compositional models, revealing the predictive associations of these multi-source covariates: high remote sensing-derived Bare Soil Index (BSI) and Moisture Stress Index (MSI) values primarily exhibited strong predictive associations with sand enrichment, whereas their lower values, combined with elevated Normalized Difference Moisture Index (NDMI), Enhanced Vegetation Index (EVI), and anthropogenic indicators, favored silt and clay accumulation. The proposed framework provides a transferable methodological reference for remote sensing-integrated compositional soil mapping with reliable uncertainty estimates and interpretable driver identification at regional scales.