Salinization is a growing global problem, particularly in arid and semi-arid areas, where salt concentration interferes with the soil structure, altering natural cycling, decreasing agricultural outputs, and threatening food security. Although many soil amendments have been studied, there is still a limited understanding of their interaction with soil after mixture application and the geochemical processes and long-term sustainability that govern their effects. To address this knowledge gap, this review elucidated the effectiveness and sustainability of soil amendments, biochar, humic substances, and mineral additives in restoring saline and sodic soils of arid and semi-arid region to explore the geochemical processes that underlie their impact. A systematic search of 174 peer-reviewed studies was conducted across multiple databases (Web of Science, Google Scholar, and Scopus) using relevant keywords and the findings were converted into quantitative values to evaluate the effects of biochar, gypsum, zeolite, and humic substances on key soil properties. Biochar significantly improved cation exchange capacity, nutrient retention, microbial activity, and water retention by enhancing soil porosity and capillarity, thereby increasing plant-available water. Gypsum improved phosphorus availability, while zeolite facilitated the removal of sodium and supported microbial activity. Humic substances enhanced soil porosity, water retention, and aggregate stability. When applied together, these amendments improved soil health by regulating salinity, enhancing nutrient cycling, while also stabilizing soil conditions and ensuring long-term sustainability through improved geochemical balance and reduced environmental impacts. The findings highlight the critical role of multi-functional amendments in promoting climate-resilient agriculture and long-term soil health restoration in saline-degraded regions. Further research and field implementation are crucial to optimize their effectiveness and ensure sustainable soil management across diverse agricultural environments.

Accurate mapping of wetland vegetation is essential for ecological monitoring and conservation, yet it remains challenging due to the spatial heterogeneity of wetlands, the scarcity of ground-truth data, and the spread of invasive species. Invasive plants alter native vegetation patterns, making their early detection critical for preserving ecosystem integrity. This study proposes a novel framework that integrates self-supervised learning (SSL), supervised segmentation, and multi-sensor data fusion to enhance vegetation classification in the Bayinbuluke Alpine Wetland, China. High-resolution satellite imagery from PlanetScope-3 and Jilin-1 was fused, and SSL methods—including BYOL, DINO, and MoCo v3—were employed to learn transferable feature representations without extensive labeled data. The results show that SSL methods exhibit consistent variations in classification performance, while multi-sensor fusion significantly improves the detection of rare and fragmented vegetation patches and enables the early identification of invasive species. Overall, the proposed SSL–fusion strategy reduces reliance on labor-intensive field data collection and provides a scalable, high-precision solution for wetland monitoring and invasive species management.