Scholarlink

<p>To address soil salinization’s significant impact on human production and livelihood in arid regions, especially in high-salinity areas like salt lake regions, this study used multi-source remote sensing data to extract 52 surface factors. Combined with measured soil salinity data, correlation analysis, multicollinearity testing, and projection importance analysis identified eight dominant factors. Subsequently, four machine learning algorithms were applied for modeling, and the optimal models were selected to study the spatiotemporal variation of soil salinization. The results indicate that the average soil salt content in the study area was 20.74% in 2020. LST (land surface temperature) can effectively identify areas with high salinity, such as saline-alkali land and salt flats. Among inversion models, the GBDT (gradient boosting decision trees) model demonstrated the highest predictive ability and minimal errors. The optimal inversion results revealed that soil salinization distribution was influenced by topographic elevation, distance from Qarhan Salt Lake, and river network density. Over the past 21 years, there was significant fluctuation in soil salinity observed in the concentrated area of grassland within the groundwater overflow zone, indicating strong variation in salinization. This fluctuation correlates with changes in groundwater levels in the groundwater overflow zone, which are influenced by temperature variations that determine the amount of snow and ice meltwater, and the precipitation in the upstream area. This study enhances understanding of soil salinization and its drivers in extremely arid salt lake regions.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Quantitative inversion of soil salinization in salt lake regions: Spatiotemporal variation and driving mechanisms

  • 期刊论文

  • 发表日期：

    2026年3月18日

查看全文
  • Jinjun Han,
  • Zitao Wang,
  • Jianping Wang,
  • Chuntao Zhao,
  • Dongmei Yu,
  • Zhaofeng Liu

摘要

To address soil salinization’s significant impact on human production and livelihood in arid regions, especially in high-salinity areas like salt lake regions, this study used multi-source remote sensing data to extract 52 surface factors. Combined with measured soil salinity data, correlation analysis, multicollinearity testing, and projection importance analysis identified eight dominant factors. Subsequently, four machine learning algorithms were applied for modeling, and the optimal models were selected to study the spatiotemporal variation of soil salinization. The results indicate that the average soil salt content in the study area was 20.74% in 2020. LST (land surface temperature) can effectively identify areas with high salinity, such as saline-alkali land and salt flats. Among inversion models, the GBDT (gradient boosting decision trees) model demonstrated the highest predictive ability and minimal errors. The optimal inversion results revealed that soil salinization distribution was influenced by topographic elevation, distance from Qarhan Salt Lake, and river network density. Over the past 21 years, there was significant fluctuation in soil salinity observed in the concentrated area of grassland within the groundwater overflow zone, indicating strong variation in salinization. This fluctuation correlates with changes in groundwater levels in the groundwater overflow zone, which are influenced by temperature variations that determine the amount of snow and ice meltwater, and the precipitation in the upstream area. This study enhances understanding of soil salinization and its drivers in extremely arid salt lake regions.