19 February 2018 Mapping soil total nitrogen of cultivated land at county scale by using hyperspectral image
Author Affiliations +
Proceedings Volume 10607, MIPPR 2017: Multispectral Image Acquisition, Processing, and Analysis; 106070J (2018) https://doi.org/10.1117/12.2283065
Event: Tenth International Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR2017), 2017, Xiangyang, China
Abstract
Monitoring total nitrogen content (TNC) in the soil of cultivated land quantitively and mastering its spatial distribution are helpful for crop growing, soil fertility adjustment and sustainable development of agriculture. The study aimed to develop a universal method to map total nitrogen content in soil of cultivated land by HSI image at county scale. Several mathematical transformations were used to improve the expression ability of HSI image. The correlations between soil TNC and the reflectivity and its mathematical transformations were analyzed. Then the susceptible bands and its transformations were screened to develop the optimizing model of map soil TNC in the Anping County based on the method of multiple linear regression. Results showed that the bands of 14th, 16th, 19th, 37th and 60th with different mathematical transformations were screened as susceptible bands. Differential transformation was helpful for reducing the noise interference to the diagnosis ability of the target spectrum. The determination coefficient of the first order differential of logarithmic transformation was biggest (0.505), while the RMSE was lowest. The study confirmed the first order differential of logarithm transformation as the optimal inversion model for soil TNC, which was used to map soil TNC of cultivated land in the study area.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xiaohe Gu, Xiaohe Gu, Li Yan Zhang, Li Yan Zhang, Meiyan Shu, Meiyan Shu, Guijun Yang, Guijun Yang, } "Mapping soil total nitrogen of cultivated land at county scale by using hyperspectral image", Proc. SPIE 10607, MIPPR 2017: Multispectral Image Acquisition, Processing, and Analysis, 106070J (19 February 2018); doi: 10.1117/12.2283065; https://doi.org/10.1117/12.2283065
PROCEEDINGS
7 PAGES


SHARE
Back to Top