Soil erosion is a global environmental problem. The rapid monitoring of the coverage changes in and spatial patterns of photosynthetic vegetation (PV) and non-photosynthetic vegetation (NPV) at regional scales can help improve the accuracy of soil erosion evaluations. Three deep learning semantic segmentation models, DeepLabV3+, PSPNet, and U-Net, are often used to extract features from unmanned aerial vehicle (UAV) images; however, their extraction processes are highly dependent on the assignment of massive data labels, which greatly limits their applicability. At the same time, numerous shadows are present in UAV images. It is not clear whether the shaded features can be further classified, nor how much accuracy can be achieved. This study took the Mu Us Desert in northern China as an example with which to explore the feasibility and efficiency of shadow-sensitive PV/NPV classification using the three models. Using the object-oriented classification technique alongside manual correction, 728 labels were produced for deep learning PV/NVP semantic segmentation. ResNet 50 was selected as the backbone network with which to train the sample data. Three models were used in the study; the overall accuracy (OA), the kappa coefficient, and the orthogonal statistic were applied to evaluate their accuracy and efficiency. The results showed that, for six characteristics, the three models achieved OAs of 88.3–91.9% and kappa coefficients of 0.81–0.87. The DeepLabV3+ model was superior, and its accuracy for PV and bare soil (BS) under light conditions exceeded 95%; for the three categories of PV/NPV/BS, it achieved an OA of 94.3% and a kappa coefficient of 0.90, performing slightly better (by ~2.6% (OA) and ~0.05 (kappa coefficient)) than the other two models. The DeepLabV3+ model and corresponding labels were tested in other sites for the same types of features: it achieved OAs of 93.9–95.9% and kappa coefficients of 0.88–0.92. Compared with traditional machine learning methods, such as random forest, the proposed method not only offers a marked improvement in classification accuracy but also realizes the semiautomatic extraction of PV/NPV areas. The results will be useful for land-use planning and land resource management in the areas.

Better understanding of the spatiotemporal characteristics of precipitation is essential in developing the best management practices for ecological restoration and soil erosion control on China’s Loess Plateau, an arid and semiarid region with severe soil erosion. This study aimed to explore the spatiotemporal trends of precipitation using long-term precipitation data from 1957 to 2018 from the 100 national standard meteorological stations across the Loess Plateau. The nonparametric Mann–Kendall statistical test and geospatial interpolation were used to detect the trends and to analyze spatial patterns of annual and seasonal precipitation. Wavelet analysis was applied to examine periodical variation across the plateau. The results reveal that regional annual precipitation over the Loess Plateau decreased during the 62 years of the study at a mean rate of −1.05 mm/10 years (p > 0.1). The changes in annual precipitation showed a periodical fluctuation with an increasing trend from 1957 to 1969, a decreasing trend from 1970 to 1999, and an increasing trend again in the first 18 years of the 21st century. The annual precipitation decreased in all eight sub-annual periods except for winter. Spatially, a decreasing trend occurred in the southern and eastern parts of the Loess Plateau, whereas a slight increase existed in the northwest in all periods. The decrease in six stations was statistically significant (p < 0.05), and a significant increase occurred in four stations (p < 0.1). These changes can be explained by an evident southward shift of the precipitation isohyets especially for 350 mm, 450 mm and 550 mm from the 1960s to the 1990s, and a clearly northward shift after the 1990s. Findings from this study facilitate an understanding of the spatial temporal trends of precipitation so appropriate countermeasures can be developed for effective vegetation restoration and soil erosion control across the Loess Plateau.

Natural solutions by which humans can overcome challenges have been severely hampered by biodiversity losses. It is essential to understand the key natural variables that influence changes in community diversity to maintain ecosystem function. The Ziwuling area has a natural recovery succession history of 150 years. Therefore, a survey was conducted to compare species composition characteristics across different vegetation recovery stages while also providing a phylogenetic and taxonomic response to the correlation between beta diversity and soil stoichiometry. The results showed that beta diversity and endemic plants had a similar single-peak temporal pattern. Soil organic carbon (SOC) accumulation was significantly positively correlated with total nitrogen (TN) and was also negatively correlated with total phosphorus (TP). Overall, soil TN, time since vegetation restoration (TVR in years), and W-SS (endemic woody plants at each stage) were able to explain 94.3% of the total variation in beta diversity. Temperate species such as Carex lanceolata, Lespedeza bicolor, and Sophora davidii are the basis for community construction. Community beta diversity patterns are the result of a mixture of ecological (e.g., climate patterns and soil nutrients) and evolutionary processes. This study combined plant resource needs with how they respond to natural recovery times in order to provide useful knowledge to protect biodiversity, the nutrient cycle, and the function of restoration ecology.

Coexistence between species within plant communities is a key issue in the practice of revegetation, forest management, and biodiversity conservation. Vegetation restoration is critical to control soil erosion and improve the ecological environment on the Loess Plateau. Here, we investigate the interspecific relationships of dominant plants during natural vegetation succession on the Loess Plateau. The results suggest that, under the ecological process of environmental filtering, species within communities can reduce interspecific competition and promote species coexistence via spatial heterogeneity and temporal asynchronous differences. The ecological niche overlap index (O_ik) significantly and positively correlated with the strength of interspecific associations. Most species pairs had weak competition and more stable interspecific relationships. The results of the χ² test showed that 317 species pairs were positively associated and 118 were negatively associated. The community is in a positive succession process, and the interaction relationship between species tends to be neutral. We should enhance the protection of positively associated species and pay attention to negatively associated species during forest management. Results revealed that Carex lanceolata Boott and Lespedeza bicolor Turcz coexisted easily with other species for mutual benefit, which could help build artificial forestland of native species to improve the ecological function.

A better understanding of the spatiotemporal variation characteristics of rainfall erosivity and effects of extreme rainfall events on soil erosion is the basis for improved water resource planning, protection, and ecological restoration in the Qinling Mountains. Using long-term daily precipitation data from 19 national standard meteorological stations from 1957 to 2018, the spatiotemporal variation trend of rainfall erosivity was explored. A linear regression analysis method was used to detect trends in rainfall erosivity. The spatial pattern of rainfall erosivity, which is based on annual, seasonal, and extreme rainfall indices, was analyzed via a geospatial interpolation method. Effects of natural factors and human activities on soil erosion at different stages were examined via the double cumulative curve method. The average annual rainfall erosivity in the Shangluo area is 2306 MJ mm ha⁻¹ h⁻¹ year⁻¹ and generally displays a gradual decreasing trend from southeast to northwest. Over the last 60 years, the annual R exhibited a nonsignificant increasing trend (p > 0.05). Overall, rainfall erosivity showed a phased trend with an increasing trend after 2000. Rainfall erosivity from June to September accounts for 78.5% of the annual total, while the annual R is mainly determined by a few rainfall events during the year. RX1d and RX5d account for 20–40% and 60–80%, respectively, of the total annual R and are likely to result in severe soil erosion in sloping cultivated land areas, agricultural lands, and dirt roads with continued climate change. Implementation of the National Natural Forest Protection Project and the ‘Grain for Green’ Project significantly reduced the intensity and scope of soil erosion in the area. This study aids in understanding the ecohydrological processes and soil erosion and sediment transport characteristics in the Qinling Mountains and promotes water resource protection and management along the middle route of the South-to-North Water Diversion Project.

The East Qinling Mountains serve as a key national ecological security barrier and the core water source area of the Middle Route of the South-to-North Water Diversion Project in China, where vegetation restoration is a core measure for regional ecological conservation. However, existing studies have mostly focused on the individual hydrological characteristics of either the litter layer or soil layer, with limited understanding of their synergistic effects and the functional differences among typical restored vegetation types. In this study, we investigated the hydrological functions of the litter layer and 0~40 cm soil layer across seven vegetation restoration types (five forest stands, grassland and farmland control) in the upper Danjiang River Basin, southern foot of the East Qinling Mountains. Key hydrological indicators, including litter biomass, water-holding capacity, effective interception capacity, soil porosity, organic matter content, and water storage capacity, were measured and comprehensively evaluated. Furthermore, we explored the underlying mechanisms by which vegetation restoration enhances the hydrological functions of the litter layer and soil profile. The results showed that vegetation restoration in the East Qinling Mountains significantly altered the litter characteristics, with broad-leaved, coniferous and mixed forests exhibiting higher litter thickness and biomass than grassland and farmland. Litter water-holding capacity varied markedly across vegetation types: Pinus tabuliformis-Quercus variabilis mixed forest (Pt-Qvmf) and Quercus variabilis Blume (Qv) showed the highest 24 h water-holding rate, water-holding depth, and effective retention depth, while grassland had the lowest values. Litter water retention followed a logarithmic function with soaking time, and water absorption rate exhibited exponential decay, with the semi-decomposed layer showing stronger water retention performance. Vegetation restoration effectively improved the soil bulk density, porosity, and water-holding capacity, with more pronounced amelioration in the topsoil layer, and significant differences were observed among vegetation types. Comprehensive evaluation via the entropy weight method revealed that Robinia pseudoacacia L. (Rp) and Pinus tabuliformis Carrière (Pt) had the optimal integrated hydrological functions of the litter-soil profile, while grassland and Platycladus orientalis (L.) Franco (Po) performed the poorest. Structural equation modeling further quantified the driving mechanisms: soil porosity was the dominant direct driver of soil hydrological function, while litter biomass exerted an indirect effect through a significant serial mediation pathway via root biomass, soil organic matter (SOM), and aggregate stability, with the model explaining 83% of the total variance in soil hydrological function. This study provides targeted theoretical support and practical guidance for vegetation restoration, optimal tree species configuration, and forest ecosystem management in the water source area of the South-to-North Water Diversion Project.