• 研究报告 •

黄土丘陵沟壑区土壤养分含量的高光谱预测模型

1. 1西北大学城市与环境学院, 西安 710127;
2水利部黄土高原水土流失过程与控制重点实验室, 郑州 450003;
3陕西省地表系统与环境承载力重点实验室, 西安 710127;
4西北大学数学学院, 西安 710127
• 收稿日期:2018-01-29 出版日期:2018-09-20 发布日期:2018-09-20
• 通讯作者: E-mail: liuym@nwu.edu.cn
• 作者简介:张 超, 男, 1993年生, 硕士研究生.主要从事高光谱遥感与GIS应用研究. E-mail: czhang@stumail.nwu.edu.cn
• 基金资助:

本文由水利部黄土高原水土流失过程与控制重点实验室开放课题基金项目(2017002)资助

Hyperspectral prediction model of soil nutrient content in the loess hilly-gully region, China.

ZHANG Chao1,2,3, LIU Yong-mei1,2,3*, SUN Ya-nan4, WANG Lei1,3, LIU Jian-hong1,3

1. 1College of Urban and Environmental Science, Northwest University, Xi’an 710127, China;
2Ministry of Water Resources Key Laboratory of Soil Erosion Process and Control on the Loess Plateau, Zhengzhou 450003, China;
3Shaanxi Key Laboratory of Surface System and Environmental Carrying Capacity, Xi’an 710127, China;
4School of Mathematics, Northwest University, Xi’an 710127, China .
• Received:2018-01-29 Online:2018-09-20 Published:2018-09-20
• Supported by:

This work was supported by the Open Foundation of Key Laboratory of Soil Erosion Process and Control on the Loess Plateau of the Ministry of Water Resources, China (2017002).

Abstract: Rapid and accurate estimation of soil nutrient content based on hyperspectral data is an optimal method for the monitoring of soil nutrient and inversion of soil physical and chemical characters. The relationship between soil nutrient content and spectral reflectance was analyzed with soil samples being collected from the loess hilly-gully region of northern Shaanxi Province. The prediction models of the content of soil organic matter, total nitrogen, total phosphorus and total potassium were constructed by the combination of three techniques, including partial least squares (PLS), multiple linear regression (MLR), and support vector machine (SVM). Then, the optimal model was selected by comparison analysis. The results showed good correlations between the content of soil nutrients and spectral reflectance in visible region (400-760 nm) and near infrared region (760-1100 nm). The maximum values of correlation coefficient located in both spectral regions. The SPA-SVM model had the best applicability and highest inversion accuracy for the contents of all soil nutrients, with simple and efficient modeling process. Our results provided a reference for applying machine learning algorithm in the construction of hyperspectral prediction model of soil nutrient content in the loess hilly-gully region.