Qinghai Lake Basin is the largest endorheic basin in the northeastern part of the Qinghai-Tibet Plateau (QTP). The vegetation dynamics are subject to dual pressures from climate change and human activities. Previous studies have neglected the interactions among driving factors, as well as the impact of climate factors on vegetation under the regulatory role of topographic elements. The present study utilises MODIS-EVI data from 2001 to 2022 to estimate Fractional Vegetation cover (FVC) and to reveal the spatiotemporal dynamics of vegetation cover through trend analysis and other methods. Furthermore, it elucidates the effect of topographical factors on vegetation distribution. Finally, geographic detectors and the partial least squares structural equation model (PLS-SEM) were employed to quantify the impact intensity of driving factors (including climate, human activities, topography, and soil) and analyze their interactive effects and influence pathways on vegetation cover. The results suggested that (1) FVC in the Qinghai Lake Basin increased significantly (1.38×10^-³/a); notably, low-grade FVC areas exhibiting high volatility. (2) The terrain effect displays clear differentiation characteristics. FVC peaks in the elevation range of 3500–3800 m, FVC dispersion increased with slope, and semishady/shady slopes dominated FVC distribution. The vegetation improvement type is concentrated on low-elevation, flat slopes and shady slopes, whereas the vegetation degradation type is distributed on middle- and low-elevation slopes and semipositive slopes. (3) Climatic factors primarily exert a direct positive influence on FVC. As far as climate factors are concerned, the effects of temperature and precipitation on FVC do not act independently, but act together through synergistic effects, with temperature showing a more significant driving effect. Topography primarily affects FVC indirectly by regulating water and heat conditions (temperature and precipitation). Each factor possesses an optimal range (elevation: 3400–4100 m, precipitation: 325–550 mm, temperature: −6 to 0°C). When changes in these driving factors exceed the optimal range, FVC is suppressed. On a temporal scale, climate change and human activities are the dominant factors influencing the FVC in the Qinghai Lake Basin. The positive effects of human factors on FVC have strengthened.

Soil erosion has been significantly exacerbated by climate change and urbanization, posing serious threats to environmental protection and sustainable development. In this study, soil erosion in the Daqing River Basin from 2000 to 2022 was assessed using the revised universal soil loss equation (RUSLE) model, which incorporates data from digital elevation model (DEM), normalized vegetation index (NDVI), and land-use sources, and the spatiotemporal evolution of soil erosion was subsequently analyzed. The impacts of natural and anthropogenic factors on erosion and their interactions with soil erosion were analyzed via random forest and partial least squares-structural equation modeling (PLS-SEM). The results revealed that soil erosion in the Daqing River Basin averaged 159 t/(km²·a) from 2000 to 2022, with averages of 386 t/(km²·a) in the mountains and 1.1 t/(km²·a) in the plains. The erosion intensity increased from southeast to northwest, with higher levels in mountains than in plains. The soil erosion level initially improved but then deteriorated sharply after a significant turning point in 2015. Natural factors, particularly precipitation, were the largest drivers of soil erosion throughout the Daqing River Basin, whereas anthropogenic factors had the greater impact on erosion in plains than in mountains. There was strong synergy among various anthropogenic factors throughout the basin. In the mountains, anthropogenic factors were antagonistic to vegetation coverage, whereas in the plains, they were synergistic with vegetation coverage and meteorological factors.

Introduction: Global warming is reshaping species’ distributions, threatening the habitats of three medicinal lianas in the genus Trichosanthes , and highlighting the need to predict their potential suitable areas under future climate conditions. This study focuses on Trichosanthes rubriflos, Trichosanthes rosthornii, and Trichosanthes kirilowii (T. rubriflos, T. rosthornii, and T. kirilowii) , aiming to understand how climate change will affect their distributions and which climatic drivers primarily influence their habitat suitability. Methods: Present and future suitability patterns were delineated using an optimized MaxEnt model, driven by contemporary climate data and four Shared Socioeconomic Pathway (SSP) scenarios (SSP1-2.6, SSP2-4.5, SSP3-7.0, SSP5-8.5). Model performance was enhanced through parameter tuning and evaluation, and the principal climatic drivers of habitat suitability were identified from the fitted models. Results: The tuned MaxEnt models reliably predicted habitat suitability. T. rubriflos showed largely contiguous suitability across the low-mountain and hilly belts of South and Southwest China. T. rosthornii was concentrated along the eastern Loess Plateau and the mountains of North China, while T. kirilowii exhibited a patchy distribution across the middle-lower Yangtze region. Temperature seasonality emerged as the primary driver for T. rubriflos , while annual precipitation was the most influential factor for T. rosthornii and T. kirilowii . Across all scenarios, habitat expansions generally outpaced contractions, with species shifting poleward and upslope. Scenario-specific responses included the expansion of T. rubriflos in South China and the northward movement of T. rosthornii under SSP3-7.0, as well as the expansion of T. kirilowii into southwestern mountain systems, coupled with partial contraction on the North China Plain under SSP5-8.5. Discussion: Distributions of the three Trichosanthes species are chiefly shaped by temperature seasonality (TS) and annual precipitation (AP), with species-specific sensitivities: TS dominates T. rubriflos , AP (plus cold stress) constrains T. rosthornii , and T. kirilowii shows mid-range (double-threshold) responses. Across 2061–2080, ranges generally expand and shift poleward and upslope; suitability peaks under SSP3-7.0 for T. rubriflos and T. rosthornii , and under SSP5-8.5 for T. kirilowii .These findings provide a scientific basis for identifying future conservation priorities, guiding in situ protection in persistent or newly suitable regions, and informing climate-adaptive management of medicinal Trichosanthes species.

Machine learning (ML) is widely used in the field of crop-growing information identification based on high-resolution remote sensing images. With Baoying County in Jiangsu Province, China, as the study area, this paper used Sentinel-2 images during the winter wheat growth period to construct its spectral, textural, and topographic features during its growth period and proposes a winter wheat-growing area extraction method based on the extreme gradient boosting (XGBoost) algorithm, which was compared with traditional ML algorithms such as the support vector machine (SVM), classification and regression tree (CART), and random forest (RF) algorithms. The results indicated that (1) a winter wheat-growing area identification model based on the XGBoost algorithm was successfully constructed based on Sentinel-2 images, considering 27 spectral, textural, and topographic features; (2) the constructed model could effectively extract winter wheat in the study area with an overall accuracy of 93.43% and only a small error compared with the actual winter wheat-growing area in Baoying County, meeting the accuracy requirement for crop identification in the study area; and (3) the deep learning algorithm XGBoost outperformed the three traditional ML algorithms, among which the RF algorithm was better than the SVM and CART algorithms, both of which had poor identification performance and a large error compared with the actual growing area. This paper provides a scientific basis for the accurate extraction of winter wheat-growing areas and further research on winter wheat growth monitoring and yield estimation.

Wrong content There was a mistake in table 3 as published. In the published article, there was a mistake in table 3. The unit shown in parentheses was displayed as "(×10+ km²)". The correct unit is "(×10 4 km²).". There was a mistake in figure 6 as published. In the published article, there was a mistake in figure 6. The inner sub-panels of this figure were arranged in the wrong order. The sequence has now been corrected. The corrected figure 6 appears below.The original version of this article has been updated.There was a mistake in the caption of table 3 as published. In the published article, there was a mistake in table 3. The unit shown in parentheses was displayed as "(×10 + km²)". The correct unit is "(×10 4 km²)". The corrected caption of table 3 appears below. TABLE 3. Suitable habitat areas for the three Trichosanthes species under different SSP scenarios (×10⁴ km²)The original version of this article has been updated.The figures were in the wrong order in the PDF/HTML version of this paper. In the published article, there was a mistake in Figures 9 and10. The two figures were presented in reverse order in the published version. Please swap Figure 9 and Figure 10 (the image sections).The correct presentation is that Figures 9 and 10 are displayed in their intended proper order. The order has now been corrected. The original version of this article has been updated.Reminder: Figures, tables, and images will be published under a Creative Commons CC-BY license and permission must be obtained for use of copyrighted material from other sources (including re-published/adapted/modified/partial figures and images from the internet). It is the responsibility of the authors to acquire the licenses, to follow any citation instructions requested by third-party rights holders, and cover any supplementary charges.for a reason not seen here, please contact the journal's editorial office.