Search

Nebkhas are distinctive biogeomorphological landforms prevalent in global drylands and coastal environments. They play a crucial role in supporting local biodiversity and preventing land desertification and often serve as an indicator of local environmental change. Despite their significance, the environmental factors that affect their geographical distribution and how they respond to climate change have not been fully explored. This study represents a novel application of machine learning models to quantifying the biogeomorphological niche of Nitraria nebkhas in northern China and simulating their geographical distribution under future climate change conditions. Findings underscore that climatic variables influence the growth of formative shrub species on nebkhas, whereas climate, soil and geomorphological conditions, along with their spatial configuration, determine the probability of nebkha occurrence. Predictions under medium and high greenhouse gas emission scenarios indicate a northward shift in the potential distribution of nebkhas in northern China by the end of the century, accompanied by a decrease in the south due to rising temperatures. Given the potential impact of nebkha field degradation on biodiversity and soil hydrological conditions, adaptive land use strategies should be designed to protect nebkhas and mitigate the impact of climate change. Our study not only provides valuable insights for informing policy‐making and conservation initiatives but also serves as an example for quantifying the niche of biogeomorphological landforms and simulating their dynamics by integrating machine learning approaches into empirical geomorphological studies. [ABSTRACT FROM AUTHOR]

The human‐environmental system in drylands is centered on oases. Despite its extent and socio‐ecological importance, understanding the dynamic changes of global oases and their human and environmental driving forces is imperative for sustainable development in drylands under global warming. Nevertheless, the dynamic changes of global oases and how they respond to the evolving environment are not well established. In this study, three criteria were summarized (i.e., existing in dryland climates, surrounded or partially surrounded by desert terrain, having a reliable source of freshwater and forming landscape units with higher vegetation coverage/productivity). A global oasis distribution map from 1995 to 2020 was generated using European Space Agency Climate Change Initiative Land Cover and GIMMS‐3G+ data (overall accuracy within a 95% confidence interval is 0.85 ± 0.01) based on overlay analysis and visual interpretation. In addition, we used geographic and temporal weighted regression methods to evaluate the potential macro‐level elements affecting both global and local oasis growth. The result showed that the global oases area in 2020 occupied an area of 191.91 Mha, and most oases existed in Asia (77.3%). The global oases area has significantly increased from 1995 to 2020 (+8.65 Mha). However, about 13.43 Mha of the global oases are desertified, indicating a high risk of desertification. Water resources, contributing 51.36% to the total driver's contribution, are key to the global oasis expansion. In the context of climate (climate variability and climate change), this research highlights the need for improved holistic water resource management for long‐term global oasis growth, particularly in developing countries where the oases' development is threatened by water scarcity and desertification. Plain Language Summary: In recent decades, global oases have exhibited an expanding trend. Under the backdrop of climate (climate variability and climate change), water resources profoundly influence this trend. We comprehensively assessed the distribution, dynamic changes, and factors driving the expansion of global oases. The research findings indicate that from 1995 to 2020, the global oasis area significantly increased by 8.65 Mha. However, approximately 13.43 Mha of global oases degraded into deserts, highlighting the extremely high risk of desertification. The abundance of water resources, accounting for 51.36% of the overall effect, emerges as the key determinant in global oasis growth. These findings emphasize the need for improved global comprehensive water resource management, particularly in developing countries' oasis regions, to address water scarcity and achieve the sustainable development of the oasis. Key Points: Global oases changed significantly from 1995 to 2020, yet desertification risk remains severeWater resources comprise 51.36% of all drivers and are the key to the world oasis's growthIn developing countries oases, climate (climate variability and climate change) will increase the demand for water resources [ABSTRACT FROM AUTHOR]

Precise vegetation restoration is critical in drylands, as some inappropriate restoration attempts have even increased water scarcity and degradation in afforestation areas. Potential natural vegetation (PNV) is widely used to provide a reference for the appropriate location and vegetation type of restoration programs while the appropriate restored areas remain unknown. Therefore, we proposed a PNV–potential normalized difference vegetation index (PNDVI) coupling framework based on multiple machine learning (ML) algorithms for precise dryland vegetation restoration. Taking the lower Tarim River Basin (LTRB) with a total area of 1,182 km2 as a case study, its present suitable restoration locations, area, and appropriate planting species were quantitatively estimated. The results showed that the model developed by incorporating PNDVI into PNV with easily measurable and available data such as temperature and soil properties can accurately identify dryland restoration patterns. In LTRB, the potentially suitable habitats of trees and grass are closer to the riverbank, while shrubby habitats are further away from the course, covering 1.88, 2.96, and 25.12 km2, respectively. There is still enormous land potential for further expansion of the current trees and grass in the LTRB, with 2.56 and 1.54% of existing land supposed to be trees and grass, respectively. This study's novel aspect is combining PNV and PNDVI to quantify and estimate precise restoration patterns through multiple ML algorithms. The model developed here can be used to evaluate the suitable reforestation locations, area, and vegetation types in drylands and to provide a basis for precise vegetation restoration. [ABSTRACT FROM AUTHOR]