Soil Biochar Quantification via Hyperspectral Unmixing

Lei Tong; Jun Zhou; Cheng Yuan Xu; Yuntao Qian; Yongsheng Gao

doi:10.1109/DICTA.2013.6691529

Back

Soil Biochar Quantification via Hyperspectral Unmixing

Conference paper

Open access

Peer reviewed

Soil Biochar Quantification via Hyperspectral Unmixing

Lei Tong, Jun Zhou, Cheng Yuan Xu, Yuntao Qian and Yongsheng Gao

Proceedings of the 2013 Digital Image Computing Techniques and Applications International Conference, pp.1-8

Digital Image Computing Techniques and Applications (DICTA) International Conference, 2013 (Hobart, Australia, 26-Nov-2013–28-Nov-2013)

IEEE Publishing Inc.

2013

DOI: https://doi.org/10.1109/DICTA.2013.6691529

Files and links (2)

pdf

PDF - Author's Accepted Version595.72 kBDownload View

Accepted VersionPDF - Author Accepted Version Open Access

url

https://doi.org/10.1109/DICTA.2013.6691529View

Published Version

Abstract

Artificial Intelligence and Image Processing

biological system modeling

biomedical imaging

carbon

hyperspectral imaging

polynomials

soil

vectors

Biochar has unique function to improve soil chemo-physical and biological properties for crop growth. Because changes of biochar in soil may affect its long-term effectiveness as an amendment, it is important to quantify and monitor biochar after application. In this paper, we propose a solution for this problem via hyperspectral image analysis. We treat the soil image as a mixture of soil and biochar signals, and then apply hyperspectral unmixing methods to predict the biochar abundance at each pixel. The final percentage of biochar can be calculated by taking the mean of the abundance of hyperspectral pixels. We have compared several hyperspectral unmixing methods based on least squares estimation and nonnegative matrix factorization with various sparsity constraints. Experimental results are evaluated by polynomial regression and root mean square errors against the ground truth data collected in the environmental labs. The results show that hyperspectral unmixing is a promising method to measure the percentage of biochar in the soil.

Details

Title: Soil Biochar Quantification via Hyperspectral Unmixing
Authors: Lei Tong (Author) - Griffith University
Jun Zhou (Author) - Griffith University
Cheng Yuan Xu (Author) - Griffith University
Yuntao Qian (Author) - Zhejiang University, China
Yongsheng Gao (Author) - Griffith University
Contributors: P de Souza (Editor)
U Engelke (Editor)
A Rahman (Editor)
Publication details: Proceedings of the 2013 Digital Image Computing Techniques and Applications International Conference, pp.1-8
Conference details: Digital Image Computing Techniques and Applications (DICTA) International Conference, 2013 (Hobart, Australia, 26-Nov-2013–28-Nov-2013)
Publisher: IEEE Publishing Inc.
Date published: 2013
DOI: 10.1109/DICTA.2013.6691529
ISBN: 9781479921263
Organisation Unit: University of the Sunshine Coast, Queensland
Language: English
Record Identifier: 99448828302621
Output Type: Conference paper
Research Statement: false

Metrics

194 File views/ downloads

1140 Record Views