Rapid Determination of Soil Class Based on Visible-Near Infrared, Mid-Infrared Spectroscopy and Data Fusion

Hanyi Xu,Zhou Shi,Songchao Chen,Dongyun Xu,Wanzhu Ma

doi:10.3390/rs12091512

Abstract

Wise soil management requires detailed soil information, but conventional soil class mapping in a rather coarse spatial resolution cannot meet the demand for precision agriculture. With the advantages of non-destructiveness, rapid cost-efficiency, and labor savings, the spectroscopic technique has proved its high potential for success in soil classification. Previous studies mainly focused on predicting soil classes using a single sensor. In this study, we attempted to compare the predictive ability of visible near infrared (vis-NIR) spectra, mid-infrared (MIR) spectra, and their fused spectra for soil classification. A total of 146 soil profiles were collected from Zhejiang, China, and the soil properties and spectra were measured by their genetic horizons. Along with easy-to-measure auxiliary soil information (soil organic matter, soil texture, color and pH), four spectral data, including vis-NIR, MIR, their simple combination (vis-NIR-MIR), and outer product analysis (OPA) fused spectra, were used for soil classification using a multiple objectives mixed support vector machine model. The independent validation results showed that the classification model using MIR (accuracy of 64.5%) was slightly better than that using vis-NIR (accuracy of 64.2%). The predictive model built on vis-NIR-MIR did not improve the classification accuracy, having the lowest accuracy of 61.1%, which likely resulted from an over-fitting problem. The model based on OPA fused spectra performed best with an accuracy of 68.4%. Our results prove the potential of fusing vis-NIR and MIR using OPA for improving prediction ability for soil classification.

Highlights

It is well known that soils have high spatial heterogeneity with different intrinsic and morphological characteristics
For visible near infrared (vis-NIR) spectra, it can contain the information on water (1400, 1900 nm), kaolinite (1400, 2200 nm), illite (2200, 2340, 2445 nm), smectite (2200 nm), carbonate (2335 nm), iron oxides (400, 450, 500, 650, 900 nm) and organic matter (1100, 1600, 1700, 1800, 2000, 2200–2400 nm) [8,57]
For other properties, such as soil organic carbon, pH, cation exchanged capacity (CEC), and total nitrogen, MIR did not perform better than vis-NIR because some useful information might be masked by the strong absorptance of soil minerals [8]

Summary

Introduction

It is well known that soils have high spatial heterogeneity with different intrinsic and morphological characteristics. It is necessary to have a good understanding of soil on a local scale for better soil management. Soil class is a good indicator for characterizing soil information and provides a basis for subsequent land management, land resource evaluation, crop planting, and fertilization [1]. Soil classification depends on field surveys, laboratory analyses, and expert knowledge [2]. Conventional laboratory analyses are complex, time-consuming, expensive, and destructive [3,4,5]. Fast and non-destructive methods are needed for soil classification. Spectroscopic technology, with the advantages of being efficient, fast, convenient, and inexpensive, is widely applied in pedology [6,7,8,9]

Objectives

Methods

Findings

Discussion

Conclusion