Estimation of yield and quality of legume and grass mixtures using partial least squares and support vector machine analysis of spectral data

Zhenjiang Zhou, Julien Morel, David Parsons, Sergey Kucheryavskiy, Anne-Maj Gustavsson

Research output: Contribution to journalJournal articleResearchpeer-review

Abstract

The project aim was to estimate N uptake (Nup), dry matter yield (DMY) and crude protein concentration (CP) of forage crops both during typical harvest times and at a very early developmental stage. Canopy spectral reflectance of legume and grass mixtures was measured in Sweden using a commercialized radiometer (400–1000 nm range). In total, 377 plant samples were tested in-situ in different grass and legume mixtures (6 grass species and 2 clover species) across two years, two locations and five N rates. Two mathematical methods, namely partial least squares (PLS) and support vector machine (SVM) were used to build prediction models between Nup, DMY and CP, and canopy spectral reflectance. Of the total 377 samples, 251 were randomly selected and used for calibration, and the remaining 126 samples were used as an independent dataset for validation. Results showed that the performance of SVM was better than PLS (based on mean absolute error (MAE) for both calibration and validation datasets) for the estimation of all investigated variables. Results for the validation set showed that the MAEs of PLS and SVM for Nup estimation were 17 and 9.2 kg/ha, respectively. The MAEs of PLS and SVM for DMY estimation were 587 and 283 kg/ha, respectively. The MAEs of PLS and SVM for CP estimation were 2.8 and 1.8%, respectively. In addition, a subsample, which corresponded to an early developmental stage, was analysed separately with PLS and SVM as for the whole dataset. Results showed that SVM was better than PLS for the estimation of all investigated variables. The high performance of SVM to estimate legume and grass mixture N uptake and dry matter yield could provide support for varying management decisions including fertilization and timing of harvest.
Original languageEnglish
JournalComputers and Electronics in Agriculture
Volume162
Pages (from-to)246-253
Number of pages8
ISSN0168-1699
DOIs
Publication statusPublished - 1 Jul 2019

Fingerprint

spectral analysis
Support vector machines
least squares
legumes
grass
grasses
dry matter
uptake mechanisms
canopy reflectance
crude protein
spectral reflectance
Proteins
developmental stage
reflectance
protein
calibration
developmental stages
Calibration
canopy
radiometers

Keywords

  • Dry matter yield
  • Forage crop
  • Grass
  • Hyperspectral reflectance
  • Nitrogen uptake
  • Nutritive value
  • Partial least squares
  • Red and white clover
  • Support vector machine

Cite this

@article{163eef2a9cc84435aff3ee7e907bacd4,
title = "Estimation of yield and quality of legume and grass mixtures using partial least squares and support vector machine analysis of spectral data",
abstract = "The project aim was to estimate N uptake (Nup), dry matter yield (DMY) and crude protein concentration (CP) of forage crops both during typical harvest times and at a very early developmental stage. Canopy spectral reflectance of legume and grass mixtures was measured in Sweden using a commercialized radiometer (400–1000 nm range). In total, 377 plant samples were tested in-situ in different grass and legume mixtures (6 grass species and 2 clover species) across two years, two locations and five N rates. Two mathematical methods, namely partial least squares (PLS) and support vector machine (SVM) were used to build prediction models between Nup, DMY and CP, and canopy spectral reflectance. Of the total 377 samples, 251 were randomly selected and used for calibration, and the remaining 126 samples were used as an independent dataset for validation. Results showed that the performance of SVM was better than PLS (based on mean absolute error (MAE) for both calibration and validation datasets) for the estimation of all investigated variables. Results for the validation set showed that the MAEs of PLS and SVM for Nup estimation were 17 and 9.2 kg/ha, respectively. The MAEs of PLS and SVM for DMY estimation were 587 and 283 kg/ha, respectively. The MAEs of PLS and SVM for CP estimation were 2.8 and 1.8{\%}, respectively. In addition, a subsample, which corresponded to an early developmental stage, was analysed separately with PLS and SVM as for the whole dataset. Results showed that SVM was better than PLS for the estimation of all investigated variables. The high performance of SVM to estimate legume and grass mixture N uptake and dry matter yield could provide support for varying management decisions including fertilization and timing of harvest.",
keywords = "Dry matter yield, Forage crop, Grass, Hyperspectral reflectance, Nitrogen uptake, Nutritive value, Partial least squares, Red and white clover, Support vector machine",
author = "Zhenjiang Zhou and Julien Morel and David Parsons and Sergey Kucheryavskiy and Anne-Maj Gustavsson",
year = "2019",
month = "7",
day = "1",
doi = "10.1016/j.compag.2019.03.038",
language = "English",
volume = "162",
pages = "246--253",
journal = "Computers and Electronics in Agriculture",
issn = "0168-1699",
publisher = "Elsevier",

}

Estimation of yield and quality of legume and grass mixtures using partial least squares and support vector machine analysis of spectral data. / Zhou, Zhenjiang; Morel, Julien; Parsons, David; Kucheryavskiy, Sergey; Gustavsson, Anne-Maj.

In: Computers and Electronics in Agriculture, Vol. 162, 01.07.2019, p. 246-253.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Estimation of yield and quality of legume and grass mixtures using partial least squares and support vector machine analysis of spectral data

AU - Zhou, Zhenjiang

AU - Morel, Julien

AU - Parsons, David

AU - Kucheryavskiy, Sergey

AU - Gustavsson, Anne-Maj

PY - 2019/7/1

Y1 - 2019/7/1

N2 - The project aim was to estimate N uptake (Nup), dry matter yield (DMY) and crude protein concentration (CP) of forage crops both during typical harvest times and at a very early developmental stage. Canopy spectral reflectance of legume and grass mixtures was measured in Sweden using a commercialized radiometer (400–1000 nm range). In total, 377 plant samples were tested in-situ in different grass and legume mixtures (6 grass species and 2 clover species) across two years, two locations and five N rates. Two mathematical methods, namely partial least squares (PLS) and support vector machine (SVM) were used to build prediction models between Nup, DMY and CP, and canopy spectral reflectance. Of the total 377 samples, 251 were randomly selected and used for calibration, and the remaining 126 samples were used as an independent dataset for validation. Results showed that the performance of SVM was better than PLS (based on mean absolute error (MAE) for both calibration and validation datasets) for the estimation of all investigated variables. Results for the validation set showed that the MAEs of PLS and SVM for Nup estimation were 17 and 9.2 kg/ha, respectively. The MAEs of PLS and SVM for DMY estimation were 587 and 283 kg/ha, respectively. The MAEs of PLS and SVM for CP estimation were 2.8 and 1.8%, respectively. In addition, a subsample, which corresponded to an early developmental stage, was analysed separately with PLS and SVM as for the whole dataset. Results showed that SVM was better than PLS for the estimation of all investigated variables. The high performance of SVM to estimate legume and grass mixture N uptake and dry matter yield could provide support for varying management decisions including fertilization and timing of harvest.

AB - The project aim was to estimate N uptake (Nup), dry matter yield (DMY) and crude protein concentration (CP) of forage crops both during typical harvest times and at a very early developmental stage. Canopy spectral reflectance of legume and grass mixtures was measured in Sweden using a commercialized radiometer (400–1000 nm range). In total, 377 plant samples were tested in-situ in different grass and legume mixtures (6 grass species and 2 clover species) across two years, two locations and five N rates. Two mathematical methods, namely partial least squares (PLS) and support vector machine (SVM) were used to build prediction models between Nup, DMY and CP, and canopy spectral reflectance. Of the total 377 samples, 251 were randomly selected and used for calibration, and the remaining 126 samples were used as an independent dataset for validation. Results showed that the performance of SVM was better than PLS (based on mean absolute error (MAE) for both calibration and validation datasets) for the estimation of all investigated variables. Results for the validation set showed that the MAEs of PLS and SVM for Nup estimation were 17 and 9.2 kg/ha, respectively. The MAEs of PLS and SVM for DMY estimation were 587 and 283 kg/ha, respectively. The MAEs of PLS and SVM for CP estimation were 2.8 and 1.8%, respectively. In addition, a subsample, which corresponded to an early developmental stage, was analysed separately with PLS and SVM as for the whole dataset. Results showed that SVM was better than PLS for the estimation of all investigated variables. The high performance of SVM to estimate legume and grass mixture N uptake and dry matter yield could provide support for varying management decisions including fertilization and timing of harvest.

KW - Dry matter yield

KW - Forage crop

KW - Grass

KW - Hyperspectral reflectance

KW - Nitrogen uptake

KW - Nutritive value

KW - Partial least squares

KW - Red and white clover

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=85064318666&partnerID=8YFLogxK

U2 - 10.1016/j.compag.2019.03.038

DO - 10.1016/j.compag.2019.03.038

M3 - Journal article

VL - 162

SP - 246

EP - 253

JO - Computers and Electronics in Agriculture

JF - Computers and Electronics in Agriculture

SN - 0168-1699

ER -