Integrating hyperspectral imaging with machine learning techniques for the high-resolution mapping of soil nitrogen fractions in soil profiles

Shengxiang Xu; Meiyan Wang; Xuezheng Shi; Quanbo Yu; Zhongqi Zhang

doi:10.1016/j.scitotenv.2020.142135

Integrating hyperspectral imaging with machine learning techniques for the high-resolution mapping of soil nitrogen fractions in soil profiles

Sci Total Environ. 2021 Feb 1:754:142135. doi: 10.1016/j.scitotenv.2020.142135. Epub 2020 Sep 4.

Authors

Shengxiang Xu¹, Meiyan Wang², Xuezheng Shi², Quanbo Yu², Zhongqi Zhang³

Affiliations

¹ State Key Laboratory of Soil and Sustainable Agriculture, Institute of Soil Science, Chinese Academy of Sciences, Nanjing 210008, China; University of Chinese Academy of Sciences, Beijing 100049, China. Electronic address: sxxu@issas.ac.cn.
² State Key Laboratory of Soil and Sustainable Agriculture, Institute of Soil Science, Chinese Academy of Sciences, Nanjing 210008, China; University of Chinese Academy of Sciences, Beijing 100049, China.
³ Jiangsu Normal University, Xuzhou 221116, China.

PMID: 32920400
DOI: 10.1016/j.scitotenv.2020.142135

Abstract

Soil nitrogen (N) plays a central role in soil quality and biogeochemical cycles. However, little is known about the distribution and spatial variability of the different fractions of soil N within entire soil profiles. This study aimed to investigate the potential of laboratory-based hyperspectral imaging (HSI) spectroscopy to retrieve and map total N (TN), available N (AvailN), ammonium N (NH₄-N), nitrate N (NO₃-N), and microbial biomass N (MBN) in soil profiles at a high resolution. HSI images of eleven intact soil profiles of 100 ± 5 cm depth from three typical soil types were recorded. A variety of nonlinear machine learning techniques, such as artificial neural networks (ANN), cubist regression tree (Cubist), k-nearest neighbour (KNN), support vector machine regression (SVMR) and extreme gradient boosting (XGBoost), were compared with a partial least squares regression (PLSR) to determine the most suitable model for the prediction of the various soil N fractions. Overall, the results showed that nonlinear techniques performed better than PLSR in most cases, with a high coefficient of determination (R²) and low root mean square error (RMSE). Among the models, SVMR was found to be superior to the other tested models for TN (R²_P = 0.94, RMSE_P = 0.17 g kg^-1), AvailN (R²_P = 0.94, RMSE_P = 13.35 mg kg^-1), NO₃-N (R²_P = 0.82, RMSE_P = 7.31 mg kg^-1), and NH₄-N (R²_P = 0.70, RMSE_P = 1.51 mg kg^-1) based on independent validation, whereas MBN (R²_P = 0.63, RMSE_P = 6.62 mg kg^-1) was predicted best by KNN. In addition, SVMR required less computational time and was less sensitive to spectral noise. It can therefore be concluded that HSI spectroscopy combined with SVMR is suitable for the high-resolution mapping of various soil N fractions in soil profiles.

Keywords: Hyperspectral imaging; Machine learning; Profile mapping; Soil nitrogen; Spectral noise.