A non-linear model of nondestructive estimation of anthocyanin content in grapevine leaves with visible/red-infrared hyperspectral

Jiang Lin Qin, Donald Rundquist, Anatoly Gitelson, Zongkun Tan, Mark Steele

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

The anthocyanin(Anth) content in leaves provides valuable information about the physiologocal status of plant. Thus, there is a need for accurate, efficient, practical methodologies to estimate this biochemical parameter. Hyperspectral measurement is a means of quickly and nondestructively assessing leaf Anth in situ. Wet chemical methods has traditionally been used for this purpose. Recently, NIR(near-infrared)/green, red/green, anthocyanin reflectance index(ARI), and a modified anthocyanin refelctance index(MARI) was been used to estimate the anthocyanin content. In this paper, a an artificial-intelligence technique model was introduced to establish the relationship between the anthocyanin content and reflectance of 400-750nm spectum, variation of species and growth stages. The objective of this study was to test the overall performance and accuracy of this new nondestructive techniques for estimating Anth content in grapevine leaves. Although Anth in validation data set was widely variable, the new methods were capable of accurate predicting Anth content in grapevine leaves with a root mean square error below 1.65 mg/m 2, which is lower than that of MARI or ARI [20]. It documents the facts that such an approach is more suitable for developing simple hand-held field instrumentation for accurate nondestructive Anth estimation and for analyzing digital airborne or satellite imagery to assist in making informed decisions vineyard management.

Original languageEnglish (US)
Title of host publicationComputer and Computing Technologies in Agriculture IV - 4th IFIP TC 12 Conference, CCTA 2010, Selected Papers
PublisherSpringer New York LLC
Pages47-62
Number of pages16
EditionPART 4
ISBN (Print)9783642183683
DOIs
StatePublished - Jan 1 2011

Publication series

NameIFIP Advances in Information and Communication Technology
NumberPART 4
Volume347 AICT
ISSN (Print)1868-4238

Fingerprint

Infrared
Artificial intelligence
Methodology
Management decisions
Imagery

Keywords

  • Anthocyanin
  • Grapes
  • Hyperspectral
  • SVM (Support Vector Machine)

ASJC Scopus subject areas

  • Information Systems and Management

Cite this

Qin, J. L., Rundquist, D., Gitelson, A., Tan, Z., & Steele, M. (2011). A non-linear model of nondestructive estimation of anthocyanin content in grapevine leaves with visible/red-infrared hyperspectral. In Computer and Computing Technologies in Agriculture IV - 4th IFIP TC 12 Conference, CCTA 2010, Selected Papers (PART 4 ed., pp. 47-62). (IFIP Advances in Information and Communication Technology; Vol. 347 AICT, No. PART 4). Springer New York LLC. https://doi.org/10.1007/978-3-642-18369-0_6

A non-linear model of nondestructive estimation of anthocyanin content in grapevine leaves with visible/red-infrared hyperspectral. / Qin, Jiang Lin; Rundquist, Donald; Gitelson, Anatoly; Tan, Zongkun; Steele, Mark.

Computer and Computing Technologies in Agriculture IV - 4th IFIP TC 12 Conference, CCTA 2010, Selected Papers. PART 4. ed. Springer New York LLC, 2011. p. 47-62 (IFIP Advances in Information and Communication Technology; Vol. 347 AICT, No. PART 4).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Qin, JL, Rundquist, D, Gitelson, A, Tan, Z & Steele, M 2011, A non-linear model of nondestructive estimation of anthocyanin content in grapevine leaves with visible/red-infrared hyperspectral. in Computer and Computing Technologies in Agriculture IV - 4th IFIP TC 12 Conference, CCTA 2010, Selected Papers. PART 4 edn, IFIP Advances in Information and Communication Technology, no. PART 4, vol. 347 AICT, Springer New York LLC, pp. 47-62. https://doi.org/10.1007/978-3-642-18369-0_6
Qin JL, Rundquist D, Gitelson A, Tan Z, Steele M. A non-linear model of nondestructive estimation of anthocyanin content in grapevine leaves with visible/red-infrared hyperspectral. In Computer and Computing Technologies in Agriculture IV - 4th IFIP TC 12 Conference, CCTA 2010, Selected Papers. PART 4 ed. Springer New York LLC. 2011. p. 47-62. (IFIP Advances in Information and Communication Technology; PART 4). https://doi.org/10.1007/978-3-642-18369-0_6
Qin, Jiang Lin ; Rundquist, Donald ; Gitelson, Anatoly ; Tan, Zongkun ; Steele, Mark. / A non-linear model of nondestructive estimation of anthocyanin content in grapevine leaves with visible/red-infrared hyperspectral. Computer and Computing Technologies in Agriculture IV - 4th IFIP TC 12 Conference, CCTA 2010, Selected Papers. PART 4. ed. Springer New York LLC, 2011. pp. 47-62 (IFIP Advances in Information and Communication Technology; PART 4).
@inproceedings{f6a26f3ac48343ed9b0c23dd67b82cab,
title = "A non-linear model of nondestructive estimation of anthocyanin content in grapevine leaves with visible/red-infrared hyperspectral",
abstract = "The anthocyanin(Anth) content in leaves provides valuable information about the physiologocal status of plant. Thus, there is a need for accurate, efficient, practical methodologies to estimate this biochemical parameter. Hyperspectral measurement is a means of quickly and nondestructively assessing leaf Anth in situ. Wet chemical methods has traditionally been used for this purpose. Recently, NIR(near-infrared)/green, red/green, anthocyanin reflectance index(ARI), and a modified anthocyanin refelctance index(MARI) was been used to estimate the anthocyanin content. In this paper, a an artificial-intelligence technique model was introduced to establish the relationship between the anthocyanin content and reflectance of 400-750nm spectum, variation of species and growth stages. The objective of this study was to test the overall performance and accuracy of this new nondestructive techniques for estimating Anth content in grapevine leaves. Although Anth in validation data set was widely variable, the new methods were capable of accurate predicting Anth content in grapevine leaves with a root mean square error below 1.65 mg/m 2, which is lower than that of MARI or ARI [20]. It documents the facts that such an approach is more suitable for developing simple hand-held field instrumentation for accurate nondestructive Anth estimation and for analyzing digital airborne or satellite imagery to assist in making informed decisions vineyard management.",
keywords = "Anthocyanin, Grapes, Hyperspectral, SVM (Support Vector Machine)",
author = "Qin, {Jiang Lin} and Donald Rundquist and Anatoly Gitelson and Zongkun Tan and Mark Steele",
year = "2011",
month = "1",
day = "1",
doi = "10.1007/978-3-642-18369-0_6",
language = "English (US)",
isbn = "9783642183683",
series = "IFIP Advances in Information and Communication Technology",
publisher = "Springer New York LLC",
number = "PART 4",
pages = "47--62",
booktitle = "Computer and Computing Technologies in Agriculture IV - 4th IFIP TC 12 Conference, CCTA 2010, Selected Papers",
edition = "PART 4",

}

TY - GEN

T1 - A non-linear model of nondestructive estimation of anthocyanin content in grapevine leaves with visible/red-infrared hyperspectral

AU - Qin, Jiang Lin

AU - Rundquist, Donald

AU - Gitelson, Anatoly

AU - Tan, Zongkun

AU - Steele, Mark

PY - 2011/1/1

Y1 - 2011/1/1

N2 - The anthocyanin(Anth) content in leaves provides valuable information about the physiologocal status of plant. Thus, there is a need for accurate, efficient, practical methodologies to estimate this biochemical parameter. Hyperspectral measurement is a means of quickly and nondestructively assessing leaf Anth in situ. Wet chemical methods has traditionally been used for this purpose. Recently, NIR(near-infrared)/green, red/green, anthocyanin reflectance index(ARI), and a modified anthocyanin refelctance index(MARI) was been used to estimate the anthocyanin content. In this paper, a an artificial-intelligence technique model was introduced to establish the relationship between the anthocyanin content and reflectance of 400-750nm spectum, variation of species and growth stages. The objective of this study was to test the overall performance and accuracy of this new nondestructive techniques for estimating Anth content in grapevine leaves. Although Anth in validation data set was widely variable, the new methods were capable of accurate predicting Anth content in grapevine leaves with a root mean square error below 1.65 mg/m 2, which is lower than that of MARI or ARI [20]. It documents the facts that such an approach is more suitable for developing simple hand-held field instrumentation for accurate nondestructive Anth estimation and for analyzing digital airborne or satellite imagery to assist in making informed decisions vineyard management.

AB - The anthocyanin(Anth) content in leaves provides valuable information about the physiologocal status of plant. Thus, there is a need for accurate, efficient, practical methodologies to estimate this biochemical parameter. Hyperspectral measurement is a means of quickly and nondestructively assessing leaf Anth in situ. Wet chemical methods has traditionally been used for this purpose. Recently, NIR(near-infrared)/green, red/green, anthocyanin reflectance index(ARI), and a modified anthocyanin refelctance index(MARI) was been used to estimate the anthocyanin content. In this paper, a an artificial-intelligence technique model was introduced to establish the relationship between the anthocyanin content and reflectance of 400-750nm spectum, variation of species and growth stages. The objective of this study was to test the overall performance and accuracy of this new nondestructive techniques for estimating Anth content in grapevine leaves. Although Anth in validation data set was widely variable, the new methods were capable of accurate predicting Anth content in grapevine leaves with a root mean square error below 1.65 mg/m 2, which is lower than that of MARI or ARI [20]. It documents the facts that such an approach is more suitable for developing simple hand-held field instrumentation for accurate nondestructive Anth estimation and for analyzing digital airborne or satellite imagery to assist in making informed decisions vineyard management.

KW - Anthocyanin

KW - Grapes

KW - Hyperspectral

KW - SVM (Support Vector Machine)

UR - http://www.scopus.com/inward/record.url?scp=79951623035&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79951623035&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-18369-0_6

DO - 10.1007/978-3-642-18369-0_6

M3 - Conference contribution

AN - SCOPUS:79951623035

SN - 9783642183683

T3 - IFIP Advances in Information and Communication Technology

SP - 47

EP - 62

BT - Computer and Computing Technologies in Agriculture IV - 4th IFIP TC 12 Conference, CCTA 2010, Selected Papers

PB - Springer New York LLC

ER -