Chen Rui-Hua, Shang Tiao-Hao, Zhang Jun-Hua, Wang Yi-Jing, Jia Ke-Li
College of Geography and Planning, Ningxia University, Yinchuan 750021, China.
Breeding Base for Sate Key Laboratory of Land Degradation and Ecological Restoration in Northwest China/Key Laboratory for Restoration and Reconstruction of Degraded Ecosystems in Northwestern China of Ministry of Education, School of Ecology and Environment, Ningxia University, Yinchuan 750021, China.
Ying Yong Sheng Tai Xue Bao. 2022 Apr;33(4):922-930. doi: 10.13287/j.1001-9332.202204.025.
Soil salinization is one of key drivers for the degradation of soil quality and yield in arable land. To accurately and quickly evaluate soil salt content in Yinchuan Plain, field and indoor hyperspectral data were processed with first order differential (FDR) transformation, then the feature bands were identified by stepwise regression (SR). Partial least squares regression (PLSR) and support vector machines (SVM) were used to build models, which were verified to figure out the optimal hyperspectral type for the study area. Moreover, segmented and global corrections were performed to process poor hyperspectral, aiming to improve the accuracy of soil salt content inversion. The results showed that the accuracy of soil salt content inversion model based on field hyperspectral data was 58.9% higher than that of the indoor hyperspectral data. The accuracy of the inversion was improved through the segmented and global correction of the indoor hyperspectral. We found that the segmented correction is more accurate for the PLSR model (=0.790, =0.633, RPD=1.64) and the global correction is more accurate for the SVM model (=0.927, =0.947, RPD=3.87). The SVM models' inversion accuracy was higher than that of PLSR, with the field hyperspectral model fitted the best, followed by the indoor hyperspectral processed with the global correction and the indoor hyperspectral processed with the segmented correction, while the indoor hyperspectral the worst. Our results suggest that field hyperspectral data could contribute to the quantitative inversion of soil salt content in Yinchuan Plain. The corrected indoor hyperspectral could significantly enhance the inversion accuracy of soil salt content, which could guarantee food security and ecological quality development.
土壤盐渍化是耕地土壤质量退化和产量下降的关键驱动因素之一。为了准确快速地评估银川平原土壤盐分含量，对野外和室内高光谱数据进行一阶微分（FDR）变换处理，然后通过逐步回归（SR）识别特征波段。利用偏最小二乘回归（PLSR）和支持向量机（SVM）建立模型，并对模型进行验证，以确定研究区域的最佳高光谱类型。此外，对质量较差的高光谱进行分段和全局校正处理，旨在提高土壤盐分含量反演的精度。结果表明，基于野外高光谱数据的土壤盐分含量反演模型精度比室内高光谱数据高58.9%。通过对室内高光谱进行分段和全局校正，提高了反演精度。我们发现，分段校正对PLSR模型更准确（ =0.790， =0.633，RPD=1.64），全局校正对SVM模型更准确（ =0.927， =0.947，RPD=3.87）。SVM模型的反演精度高于PLSR模型，其中野外高光谱模型拟合效果最佳，其次是经过全局校正的室内高光谱和经过分段校正的室内高光谱，而室内高光谱最差。我们的结果表明，野外高光谱数据有助于银川平原土壤盐分含量的定量反演。校正后的室内高光谱能够显著提高土壤盐分含量的反演精度，这可以保障粮食安全和生态质量发展。
