文献类型： 外文期刊

作者： Wang, Shibin ¹ ; Li, Yi ¹ ; Li, Tanyi ¹ ; Lu, Wenlong ¹ ; Qi, Xingyun ¹ ; Xie, Xiangwen ² ; Sa, Renna ² ; Guo, Tongkai ³ ; Pulatov, Alim ⁴ ; Javlonbek, Ishchanov ⁴ ; Tang, Darrell W. S. ⁵ ; Siddique, Kadambot H. M. ⁶ ;

作者机构： 1.Northwest Agr & Forestry Univ, Coll Water Resources & Architectural Engn, Key Lab Agr Soil & Water Engn Arid & Semiarid Area, Minist Educ, Yangling 712100, Shaanxi, Peoples R China

2.Xinjiang Acad Agr Sci, Inst Agr Resources & Environm, Urumqi 830091, Peoples R China

3.China Agr Univ, Ctr Agr Water Res China, Beijing 100083, Peoples R China

4.Tashkent Inst Irrigat & Agr Mechanizat Engineers, Qoriy Niyoziy 39, Tashkent 100000, Uzbekistan

5.Univ Oulu, Water Energy & Environm Engn, Oulu, Finland

6.Univ Western Australia, UWA Inst Agr, Perth, WA 6001, Australia

关键词： Maize; Soil water and salt contents inversion; Water-salinity suitability index; Machine learning; Transfer learning

期刊名称：SOIL & TILLAGE RESEARCH （ 影响因子：6.8； 五年影响因子：7.8 ）

ISSN： 0167-1987

年卷期： 2025 年 254 卷

页码：

收录情况： SCI

摘要： Soil water content (SWC) and salt content (SSC) are critical factors affecting maize growth. Remote sensing technology has become an effective tool for regional SWC and SSC estimation, but challenges remain in improving estimation accuracy and cross-scale model transfer. In this study, the feature sets were optimized using correlation clustering analysis and full subset selection, and five machine learning models, including the bat-optimized random forest (BA-RF), were compared to estimate SWC and SSC. Further, the inversion model constructed based on UAV features was transferred to satellite scale using transfer component analysis (TCA) and its accuracy was verified. The key findings were as follows: (1) Feature optimization improved estimation accuracy (SWC: R-2 >= 0.541, RMSE <= 0.021 cm(3) cm(-3); SSC: R-2 >= 0.574, RMSE <= 0.816 g kg(-1)). (2) The BA-RF model achieved high estimation performance for SWC (R-2 = 0.705-0.899, RMSE = 0.010-0.020 cm(3) cm(-3)) and SSC (R-2 = 0.700-0.897, RMSE = 0.466-0.737 g kg(-1)). (3) TCA enabled effective transfer of the BARF-TCA model from UAV to satellite scale, maintaining a high estimation accuracy (SWC: R-2 >= 0.764 RMSE <= 0.015cm(3) cm(-3), SSC: R-2 >= 0.667, RMSE <= 0.672 g kg(-1)). (4) A water-salinity suitability index was developed to generate dynamic maize suitability maps across growth stages. This study presented an integrated framework for large-scale, high-precision estimation of SWC and SSC, as well as water-salinity-based crop suitability zoning, providing valuable guidance for maize farmland SWC and SSC management in arid and saline-alkaline regions.