基于Sentinel-2影像的黄河南岸典型改良示范区土壤含盐量反演模型  

Soil Salt Inversion of Typical Improvement Demonstration Area of South Bank of Yellow River Based on Sentinel-2 Images

作　　者：王宇璇 屈忠义 白燕英[1] 刘霞[1] 刘全明[1] 刘琦 WANG Yuxuan;QU Zhongyi;BAI Yanying;LIU Xia;LIU Quanming;LIU Qi(College of Water Conservation and Civil Engineering,Inner Mongolia Agricultural University,Huhhot O10018,China;School of Energy and Environment,Inner Mongolia University of Science and Technology,Baotou 014010,China)

机构地区：[1]内蒙古农业大学水利与土木建筑工程学院,呼和浩特010018 [2]内蒙古科技大学能源与环境学院,包头014010

出　　处：《农业机械学报》2024年第4期290-299,439,共11页Transactions of the Chinese Society for Agricultural Machinery

基　　金：国家重点研发计划项目(2021YFD1900605);内蒙古自治区科技计划项目(2021GG0369);国家自然科学基金项目(52069020)。

摘　　要：土壤盐渍化严重制约农田土壤环境的循环发展,高效准确地监测土壤盐分动态变化对盐碱地改良利用具有重要意义。为及时、有效地监测盐渍化土壤含盐量,以内蒙古黄河南岸灌区的4个典型盐碱化耕地改良示范区为例,利用Sentinel-2多光谱遥感影像,同步采集示范区内表层土壤的含盐量数据,通过相关性分析筛选敏感光谱指标,基于偏最小二乘回归(PLSR)、逐步回归(SR)、岭回归(RR)3种简单机器学习模型和深度学习Transformer模型建模,最后进行精度评价并优选出最佳含盐量反演模型。结果表明:示范区土壤反射率的可见光、红边、近红外波段反射率均与土壤含盐量呈正相关,短波红外波段反射率与土壤含盐量呈负相关,引入光谱指数能够有效提升Sentinel-2遥感影像与示范区表层土壤含盐量的相关性(相关系数绝对值不小于0.32);对比不同模型发现深度学习Transformer模型优于简单机器学习模型,验证集决定系数R~2和均方根误差(RMSE)分别为0.546和2.687 g/kg;含盐量反演结果与实地结果相吻合,为更精准反演内蒙古黄河南岸灌区盐渍化程度提供了参考。Soil salinization seriously restricts the circular development of farmland economic production,and it is of great significance to monitor the dynamic change of soil salinity efficiently and accurately for the improvement and utilization of saline-alkali land.To timely and effectively monitor saline content in four typical salinized farmland improvement demonstration areas on the south bank of the Yellow River in Inner Mongolia,for example,using Sentinel-2 multispectral remote sensing image,synchronous collecting the surface soil salt data,screening sensitive spectral index through correlation analysis,based on three simple machine learning models of PLSR,SR and RR and Transformer deep learning model,finally precision evaluation and optimization of the best salt inversion model was carried out.The results showed that the visible light,red edge,and near-red band reflectance values of soil reflectivity in the demonstration area were positively correlated with soil salt content.The reflectivity values of the short-wave infrared band were negatively correlated with soil salt content.Introducing spectral index can effectively improve the correlation between Sentinel-2 remote sensing images and the salt content of the surface soil in the demonstration area(|r|≥0.32).A comparison of different models found that the Transformer deep learning model outperformed the simple machine learning model,and the R~2 and RMSE of the validation set were 0.546 and 2.687 g/kg;the salt inversion results were consistent with the field results,which provided a reference for more accurate inversion and improvement of the salinization degree in the south bank of the Yellow River in Inner Mongolia.

关 键 词：土壤盐渍化 含盐量反演 遥感 Sentinel-2 光谱指数 Transformer 

分 类 号：S155.293[农业科学—土壤学] TP79[农业科学—农业基础科学]