Enhancing soil profile analysis with soil spectral libraries and laboratory hyperspectral imaging
Yuwei Zhou,
Asim Biswas,
Yongsheng Hong,
Songchao Chen,
Bifeng Hu,
Zhou Shi,
Yan Guo,
Shuo Li
Affiliations
Yuwei Zhou
Key Laboratory for Geographical Process Analysis & Simulation of Hubei Province, College of Urban & Environmental Sciences, Central China Normal University, Wuhan 430079, China; Key Laboratory of Huang-Huai-Hai Smart Agricultural Technology, Ministry of Agriculture and Rural Affairs, Zhengzhou 450002, China
Asim Biswas
School of Environmental Sciences, University of Guelph, Ontario N1G2W1, Canada
Yongsheng Hong
State Key Laboratory of Soil and Sustainable Agriculture, Institute of Soil Science, Chinese Academy of Sciences, Nanjing 210008, China
Songchao Chen
Institute of Applied Remote Sensing and Information Technology, College of Environmental and Resource Sciences, Zhejiang University, Hangzhou 310058, China; ZJU-Hangzhou Global Scientific and Technological Innovation Center, Hangzhou 311200, China
Bifeng Hu
Department of Land Resource Management, School of Tourism and Urban Management, Jiangxi University of Finance and Economics, Nanchang 330013, China
Zhou Shi
Institute of Applied Remote Sensing and Information Technology, College of Environmental and Resource Sciences, Zhejiang University, Hangzhou 310058, China
Yan Guo
Institute of Agricultural Information Technology, Henan Academy of Agricultural Sciences, Zhengzhou 450002, China; Key Laboratory of Huang-Huai-Hai Smart Agricultural Technology, Ministry of Agriculture and Rural Affairs, Zhengzhou 450002, China
Shuo Li
Key Laboratory for Geographical Process Analysis & Simulation of Hubei Province, College of Urban & Environmental Sciences, Central China Normal University, Wuhan 430079, China; Key Laboratory of Huang-Huai-Hai Smart Agricultural Technology, Ministry of Agriculture and Rural Affairs, Zhengzhou 450002, China; Corresponding author at: Key Laboratory for Geographical Process Analysis & Simulation of Hubei Province, College of Urban & Environmental Sciences, Central China Normal University, Wuhan 430079, China.
Soil visible-near-infrared (vis–NIR) spectroscopy offers a rapid, uncontaminated, and cost-efficient method for estimating physicochemical properties such as soil organic carbon (SOC). The development of soil spectral libraries (SSLs) and localized modeling methods has significantly improved the selection of appropriate modeling sets from SSLs for soil analysis. Nevertheless, most studies assume that the SSLs sufficiently cover the target samples for prediction. This study challenges this assumption by investigating the feasibility of using an SSL to predict SOC accurately in a local area when the dataset to be predicted (156,800 samples) vastly exceeds the SSL capacity (3755 samples). We utilized 1-meter-deep whole-soil profile and employed spectral similarity and continuum-removal (SS-CR) calculation to construct a Local dataset from the SSL, with a Global subset serving as a baseline for comparison. The effectiveness of partial least-squares regression (PLSR) and random forest (RF) algorithms in establishing quantitative relationships between spectra and SOC content was evaluated. Our results demonstrated that the Local model, with significantly fewer samples (1116), achieved higher predictive accuracy than the Global model. Both Global (R2 = 0.80, RMSE = 0.74 %) and Local (R2 = 0.83, RMSE = 0.75 %) models, developed using the RF algorithm, not only exhibited excellent accuracy but also enabled detailed and cost-effective characterization of the spatial distribution of SOC. Thus, leveraging SSLs enhances the cost-efficiency and predictive capacity of vis–NIR spectral analysis, particularly in handling large datasets at a local scale, underscoring the value of localized approaches in soil spectroscopy.
