Soil organic matter content GM(0,N) estimation model based on hyper‐spectral technique

Abstract

Purpose

This paper attempts to establish the grey GM(0,N) estimation model of the soil organic matter content spectral inversion under the uncertainties between soil organic matter contents and spectral characteristics and the theory of grey system.

Design/methodology/approach

At first, based on the uncertainty of the relationship between the soil organic matter content and spectral characteristics, using the ordered grey accumulation generation and grey GM(0, N) model to establish hyper‐spectral grey estimation model of soil organic matter content. Second, the presented model is used to estimate soil organic matter of Hengshan County in Shanxi province in the last part of the paper.

Findings

The results are convincing: not only that soil organic matter content spectral inversion grey GM(0, N) model based on the ordered grey accumulation generation theory is valid, but also the model's prediction accuracy is higher, with the sample's average prediction accuracy being 93.662 per cent.

Practical implications

The method exposed in the paper can be used on soil organic matter content hyper‐spectral inversion and even for other similar forecast problems.

Originality/value

The paper succeeds in realising both prediction pattern and application of soil organic matter content hyper‐spectral inversion by using the newest developed theories: grey GM(0, N) model based on the ordered grey accumulation generation.

Citation

Xi‐can, L., Zheng, Y. and Guangbo, Z. (2013), "Soil organic matter content GM(0,N) estimation model based on hyper‐spectral technique", Grey Systems: Theory and Application, Vol. 3 No. 2, pp. 112-120. https://doi.org/10.1108/GS-02-2013-0002