Hyperspectral Input-Based Neural Network Model for Predicting Chlorophyll Status in Corn

Siza D. Tumbo, David G. Wagner, Paul Heinz Heinemann

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

2 Citations (Scopus)

Abstract

The use of spectral reflectance techniques for predicting nitrogen in corn at V6 growth stage has been limited by the soil background, and changes in cloud cover and solar angles. Measurement and prediction techniques, which are independent of these factors, are needed for fast and accurate prediction of nitrogen deficiency at V6 growth stage for site-specific side dressing of nitrogen. Spectral reflectance response patterns (SRRPs) from individual corn plants were collected under variable cloud cover and solar angles using a fiber optic spectrometer. Chlorophyll levels, which are strong indicators of nitrogen status in plants, were also measured on each corn plant using a SPAD chlorophyll meter. The back-propagation neural network model was trained using spectral channels of the SRRPs as inputs and chlorophyll readings as outputs. The model showed strong correlation between predicted and actual chlorophyll meter readings (r 2=0.91, root mean square prediction error = 1.30 in SPAD units with validation set).

Original languageEnglish (US)
Title of host publication2000 ASAE Annual International Meeting, Technical Papers: Engineering Solutions for a New Century
Pages1627-1642
Number of pages16
Volume1
StatePublished - 2000
Event2000 ASAE Annual International Meeting, Technical Papers: Engineering Solutions for a New Century - Milwaukee, WI., United States
Duration: Jul 9 2000Jul 12 2000

Other

Other2000 ASAE Annual International Meeting, Technical Papers: Engineering Solutions for a New Century
CountryUnited States
CityMilwaukee, WI.
Period7/9/007/12/00

Fingerprint

Chlorophyll
Nitrogen
Neural networks
Backpropagation
Fiber optics
Spectrometers
Soils

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Tumbo, S. D., Wagner, D. G., & Heinemann, P. H. (2000). Hyperspectral Input-Based Neural Network Model for Predicting Chlorophyll Status in Corn. In 2000 ASAE Annual International Meeting, Technical Papers: Engineering Solutions for a New Century (Vol. 1, pp. 1627-1642)
Tumbo, Siza D. ; Wagner, David G. ; Heinemann, Paul Heinz. / Hyperspectral Input-Based Neural Network Model for Predicting Chlorophyll Status in Corn. 2000 ASAE Annual International Meeting, Technical Papers: Engineering Solutions for a New Century. Vol. 1 2000. pp. 1627-1642
@inproceedings{02eb7f5cf54b4c2d80999dcce503698b,
title = "Hyperspectral Input-Based Neural Network Model for Predicting Chlorophyll Status in Corn",
abstract = "The use of spectral reflectance techniques for predicting nitrogen in corn at V6 growth stage has been limited by the soil background, and changes in cloud cover and solar angles. Measurement and prediction techniques, which are independent of these factors, are needed for fast and accurate prediction of nitrogen deficiency at V6 growth stage for site-specific side dressing of nitrogen. Spectral reflectance response patterns (SRRPs) from individual corn plants were collected under variable cloud cover and solar angles using a fiber optic spectrometer. Chlorophyll levels, which are strong indicators of nitrogen status in plants, were also measured on each corn plant using a SPAD chlorophyll meter. The back-propagation neural network model was trained using spectral channels of the SRRPs as inputs and chlorophyll readings as outputs. The model showed strong correlation between predicted and actual chlorophyll meter readings (r 2=0.91, root mean square prediction error = 1.30 in SPAD units with validation set).",
author = "Tumbo, {Siza D.} and Wagner, {David G.} and Heinemann, {Paul Heinz}",
year = "2000",
language = "English (US)",
volume = "1",
pages = "1627--1642",
booktitle = "2000 ASAE Annual International Meeting, Technical Papers: Engineering Solutions for a New Century",

}

Tumbo, SD, Wagner, DG & Heinemann, PH 2000, Hyperspectral Input-Based Neural Network Model for Predicting Chlorophyll Status in Corn. in 2000 ASAE Annual International Meeting, Technical Papers: Engineering Solutions for a New Century. vol. 1, pp. 1627-1642, 2000 ASAE Annual International Meeting, Technical Papers: Engineering Solutions for a New Century, Milwaukee, WI., United States, 7/9/00.

Hyperspectral Input-Based Neural Network Model for Predicting Chlorophyll Status in Corn. / Tumbo, Siza D.; Wagner, David G.; Heinemann, Paul Heinz.

2000 ASAE Annual International Meeting, Technical Papers: Engineering Solutions for a New Century. Vol. 1 2000. p. 1627-1642.

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

TY - GEN

T1 - Hyperspectral Input-Based Neural Network Model for Predicting Chlorophyll Status in Corn

AU - Tumbo, Siza D.

AU - Wagner, David G.

AU - Heinemann, Paul Heinz

PY - 2000

Y1 - 2000

N2 - The use of spectral reflectance techniques for predicting nitrogen in corn at V6 growth stage has been limited by the soil background, and changes in cloud cover and solar angles. Measurement and prediction techniques, which are independent of these factors, are needed for fast and accurate prediction of nitrogen deficiency at V6 growth stage for site-specific side dressing of nitrogen. Spectral reflectance response patterns (SRRPs) from individual corn plants were collected under variable cloud cover and solar angles using a fiber optic spectrometer. Chlorophyll levels, which are strong indicators of nitrogen status in plants, were also measured on each corn plant using a SPAD chlorophyll meter. The back-propagation neural network model was trained using spectral channels of the SRRPs as inputs and chlorophyll readings as outputs. The model showed strong correlation between predicted and actual chlorophyll meter readings (r 2=0.91, root mean square prediction error = 1.30 in SPAD units with validation set).

AB - The use of spectral reflectance techniques for predicting nitrogen in corn at V6 growth stage has been limited by the soil background, and changes in cloud cover and solar angles. Measurement and prediction techniques, which are independent of these factors, are needed for fast and accurate prediction of nitrogen deficiency at V6 growth stage for site-specific side dressing of nitrogen. Spectral reflectance response patterns (SRRPs) from individual corn plants were collected under variable cloud cover and solar angles using a fiber optic spectrometer. Chlorophyll levels, which are strong indicators of nitrogen status in plants, were also measured on each corn plant using a SPAD chlorophyll meter. The back-propagation neural network model was trained using spectral channels of the SRRPs as inputs and chlorophyll readings as outputs. The model showed strong correlation between predicted and actual chlorophyll meter readings (r 2=0.91, root mean square prediction error = 1.30 in SPAD units with validation set).

UR - http://www.scopus.com/inward/record.url?scp=2342465495&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=2342465495&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:2342465495

VL - 1

SP - 1627

EP - 1642

BT - 2000 ASAE Annual International Meeting, Technical Papers: Engineering Solutions for a New Century

ER -

Tumbo SD, Wagner DG, Heinemann PH. Hyperspectral Input-Based Neural Network Model for Predicting Chlorophyll Status in Corn. In 2000 ASAE Annual International Meeting, Technical Papers: Engineering Solutions for a New Century. Vol. 1. 2000. p. 1627-1642