Estimating soil heavy metal concentration using hyperspectral data and weighted K-NN method

Weibo Ma; Kun Tan; Qian Du; Jianwei Ding; Qingwu Yan

doi:10.1109/WHISPERS.2016.8071813

Estimating soil heavy metal concentration using hyperspectral data and weighted K-NN method

Weibo Ma
, Kun Tan
, Qian Du
, Jianwei Ding
, Qingwu Yan

China University of Mining and Technology
Mississippi State University
The Second Surveying and Mapping Institute of Hebei Province

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Scopus citations

Abstract

The potential hazard of heavy metals in reclaimed mine soil has influenced on the human health. The inversion analysis of hyperspectral data can be used to estimate heavy metal content of the soil effectively. In this paper, the characteristic bands are extracted by spectral pretreatment, including Savitzky-Golay (SG), Standard Normal Variety (SNV), First Derivative (FD), Second Derivative (SD), or Continuum Removal (CR) etc. Then, the weighted k-Nearest Neighbor (weighted k-NN) method is applied in the heavy metal inversion modeling to estimate the content of heavy metal with hyperspectral data. Compared with the widely used partial least squares regression (PLS), support vector machine (SVM) and k-Nearest Neighbor method (k-NN), the experimental results shown that the accuracy of weighted k-NN method was higher than other methods in the inversion of heavy Zinc (Zn), Chromium (Cr) and Plumbum (Pb).

Original language	English
Title of host publication	2016 8th Workshop on Hyperspectral Image and Signal Processing
Subtitle of host publication	Evolution in Remote Sensing, WHISPERS 2016
Publisher	IEEE Computer Society
ISBN (Electronic)	9781509006083
DOIs	https://doi.org/10.1109/WHISPERS.2016.8071813
State	Published - 28 Jun 2016
Externally published	Yes
Event	8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2016 - Los Angeles, United States Duration: 21 Aug 2016 → 24 Aug 2016

Publication series

Name	Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing
Volume	0
ISSN (Print)	2158-6276

Conference

Conference	8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2016
Country/Territory	United States
City	Los Angeles
Period	21/08/16 → 24/08/16

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Hyperspectral inversion
Soil heavy metal
Weighted k-NN

Access to Document

10.1109/WHISPERS.2016.8071813

Cite this

Ma, W., Tan, K., Du, Q., Ding, J., & Yan, Q. (2016). Estimating soil heavy metal concentration using hyperspectral data and weighted K-NN method. In 2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2016 Article 8071813 (Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing; Vol. 0). IEEE Computer Society. https://doi.org/10.1109/WHISPERS.2016.8071813

@inproceedings{9715233d76854cb2af9a19501e5fa833,

title = "Estimating soil heavy metal concentration using hyperspectral data and weighted K-NN method",

abstract = "The potential hazard of heavy metals in reclaimed mine soil has influenced on the human health. The inversion analysis of hyperspectral data can be used to estimate heavy metal content of the soil effectively. In this paper, the characteristic bands are extracted by spectral pretreatment, including Savitzky-Golay (SG), Standard Normal Variety (SNV), First Derivative (FD), Second Derivative (SD), or Continuum Removal (CR) etc. Then, the weighted k-Nearest Neighbor (weighted k-NN) method is applied in the heavy metal inversion modeling to estimate the content of heavy metal with hyperspectral data. Compared with the widely used partial least squares regression (PLS), support vector machine (SVM) and k-Nearest Neighbor method (k-NN), the experimental results shown that the accuracy of weighted k-NN method was higher than other methods in the inversion of heavy Zinc (Zn), Chromium (Cr) and Plumbum (Pb).",

keywords = "Hyperspectral inversion, Soil heavy metal, Weighted k-NN",

author = "Weibo Ma and Kun Tan and Qian Du and Jianwei Ding and Qingwu Yan",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2016 ; Conference date: 21-08-2016 Through 24-08-2016",

year = "2016",

month = jun,

day = "28",

doi = "10.1109/WHISPERS.2016.8071813",

language = "英语",

series = "Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing",

publisher = "IEEE Computer Society",

booktitle = "2016 8th Workshop on Hyperspectral Image and Signal Processing",

address = "美国",

}

Ma, W, Tan, K, Du, Q, Ding, J & Yan, Q 2016, Estimating soil heavy metal concentration using hyperspectral data and weighted K-NN method. in 2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2016., 8071813, Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing, vol. 0, IEEE Computer Society, 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2016, Los Angeles, United States, 21/08/16. https://doi.org/10.1109/WHISPERS.2016.8071813

Estimating soil heavy metal concentration using hyperspectral data and weighted K-NN method. / Ma, Weibo; Tan, Kun; Du, Qian et al.
2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2016. IEEE Computer Society, 2016. 8071813 (Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing; Vol. 0).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Estimating soil heavy metal concentration using hyperspectral data and weighted K-NN method

AU - Ma, Weibo

AU - Tan, Kun

AU - Du, Qian

AU - Ding, Jianwei

AU - Yan, Qingwu

PY - 2016/6/28

Y1 - 2016/6/28

N2 - The potential hazard of heavy metals in reclaimed mine soil has influenced on the human health. The inversion analysis of hyperspectral data can be used to estimate heavy metal content of the soil effectively. In this paper, the characteristic bands are extracted by spectral pretreatment, including Savitzky-Golay (SG), Standard Normal Variety (SNV), First Derivative (FD), Second Derivative (SD), or Continuum Removal (CR) etc. Then, the weighted k-Nearest Neighbor (weighted k-NN) method is applied in the heavy metal inversion modeling to estimate the content of heavy metal with hyperspectral data. Compared with the widely used partial least squares regression (PLS), support vector machine (SVM) and k-Nearest Neighbor method (k-NN), the experimental results shown that the accuracy of weighted k-NN method was higher than other methods in the inversion of heavy Zinc (Zn), Chromium (Cr) and Plumbum (Pb).

AB - The potential hazard of heavy metals in reclaimed mine soil has influenced on the human health. The inversion analysis of hyperspectral data can be used to estimate heavy metal content of the soil effectively. In this paper, the characteristic bands are extracted by spectral pretreatment, including Savitzky-Golay (SG), Standard Normal Variety (SNV), First Derivative (FD), Second Derivative (SD), or Continuum Removal (CR) etc. Then, the weighted k-Nearest Neighbor (weighted k-NN) method is applied in the heavy metal inversion modeling to estimate the content of heavy metal with hyperspectral data. Compared with the widely used partial least squares regression (PLS), support vector machine (SVM) and k-Nearest Neighbor method (k-NN), the experimental results shown that the accuracy of weighted k-NN method was higher than other methods in the inversion of heavy Zinc (Zn), Chromium (Cr) and Plumbum (Pb).

KW - Hyperspectral inversion

KW - Soil heavy metal

KW - Weighted k-NN

UR - https://www.scopus.com/pages/publications/85037530006

U2 - 10.1109/WHISPERS.2016.8071813

DO - 10.1109/WHISPERS.2016.8071813

M3 - 会议稿件

AN - SCOPUS:85037530006

T3 - Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing

BT - 2016 8th Workshop on Hyperspectral Image and Signal Processing

PB - IEEE Computer Society

T2 - 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2016

Y2 - 21 August 2016 through 24 August 2016

ER -

Ma W, Tan K, Du Q, Ding J, Yan Q. Estimating soil heavy metal concentration using hyperspectral data and weighted K-NN method. In 2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2016. IEEE Computer Society. 2016. 8071813. (Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing). doi: 10.1109/WHISPERS.2016.8071813

Estimating soil heavy metal concentration using hyperspectral data and weighted K-NN method

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this