Early detection of Ganoderma basal stem rot of oil palms using artificial neural network spectral analysis

Ganoderma boninense is a causal agent of basal stem rot (BSR) and is responsible for a significant portion of oil palm (Elaeis guineensis) losses, which can reach US$500 million a year in Southeast Asia. At the early stage of this disease, infected palms are symptomless, which imposes difficulties i...

Full description

Bibliographic Details
Main Authors: Ahmadi, Seyedeh Parisa, Muharam, Farrah Melissa, Ahmad, Khairulmazmi, Mansor, Shattri, Abu Seman, Idris
Format: Article
Language:English
Published: American Phytopathological Society 2017
Online Access:http://psasir.upm.edu.my/id/eprint/64736/
http://psasir.upm.edu.my/id/eprint/64736/1/Early%20detection%20of%20Ganoderma%20basal%20stem%20rot%20of%20oil%20palms%20using%20artificial%20neural%20network%20spectral%20analysis.pdf
_version_ 1848855084889276416
author Ahmadi, Seyedeh Parisa
Muharam, Farrah Melissa
Ahmad, Khairulmazmi
Mansor, Shattri
Abu Seman, Idris
author_facet Ahmadi, Seyedeh Parisa
Muharam, Farrah Melissa
Ahmad, Khairulmazmi
Mansor, Shattri
Abu Seman, Idris
author_sort Ahmadi, Seyedeh Parisa
building UPM Institutional Repository
collection Online Access
description Ganoderma boninense is a causal agent of basal stem rot (BSR) and is responsible for a significant portion of oil palm (Elaeis guineensis) losses, which can reach US$500 million a year in Southeast Asia. At the early stage of this disease, infected palms are symptomless, which imposes difficulties in detecting the disease. In spite of the availability of tissue and DNA sampling techniques, there is a particular need for replacing costly field data collection methods for detecting Ganoderma in its early stage with a technique derived from spectroscopic and imagery data. Therefore, this study was carried out to apply the artificial neural network (ANN) analysis technique for discriminating and classifying fungal infections in oil palm trees at an early stage using raw, first, and second derivative spectroradiometer datasets. These were acquired from 1,016 spectral signatures of foliar samples in four disease levels (T1: healthy, T2: mildly-infected, T3: moderately infected, and T4: severely infected). Most of the satisfactory results occurred in the visible range, especially in the green wavelength. The healthy oil palms and those which were infected by Ganoderma at an early stage (T2) were classified satisfactorily with an accuracy of 83.3%, and 100.0% in 540 to 550 nm, respectively, by ANN using first derivative spectral data. The results further indicated that the sensitive frond number modeled by ANN provided the highest accuracy of 100.0% for frond number 9 compared with frond 17. This study showed evidence that employment of ANN can predict the early infection of BSR disease on oil palm with a high degree of accuracy.
first_indexed 2025-11-15T11:20:09Z
format Article
id upm-64736
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T11:20:09Z
publishDate 2017
publisher American Phytopathological Society
recordtype eprints
repository_type Digital Repository
spelling upm-647362018-08-14T02:38:41Z http://psasir.upm.edu.my/id/eprint/64736/ Early detection of Ganoderma basal stem rot of oil palms using artificial neural network spectral analysis Ahmadi, Seyedeh Parisa Muharam, Farrah Melissa Ahmad, Khairulmazmi Mansor, Shattri Abu Seman, Idris Ganoderma boninense is a causal agent of basal stem rot (BSR) and is responsible for a significant portion of oil palm (Elaeis guineensis) losses, which can reach US$500 million a year in Southeast Asia. At the early stage of this disease, infected palms are symptomless, which imposes difficulties in detecting the disease. In spite of the availability of tissue and DNA sampling techniques, there is a particular need for replacing costly field data collection methods for detecting Ganoderma in its early stage with a technique derived from spectroscopic and imagery data. Therefore, this study was carried out to apply the artificial neural network (ANN) analysis technique for discriminating and classifying fungal infections in oil palm trees at an early stage using raw, first, and second derivative spectroradiometer datasets. These were acquired from 1,016 spectral signatures of foliar samples in four disease levels (T1: healthy, T2: mildly-infected, T3: moderately infected, and T4: severely infected). Most of the satisfactory results occurred in the visible range, especially in the green wavelength. The healthy oil palms and those which were infected by Ganoderma at an early stage (T2) were classified satisfactorily with an accuracy of 83.3%, and 100.0% in 540 to 550 nm, respectively, by ANN using first derivative spectral data. The results further indicated that the sensitive frond number modeled by ANN provided the highest accuracy of 100.0% for frond number 9 compared with frond 17. This study showed evidence that employment of ANN can predict the early infection of BSR disease on oil palm with a high degree of accuracy. American Phytopathological Society 2017 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/64736/1/Early%20detection%20of%20Ganoderma%20basal%20stem%20rot%20of%20oil%20palms%20using%20artificial%20neural%20network%20spectral%20analysis.pdf Ahmadi, Seyedeh Parisa and Muharam, Farrah Melissa and Ahmad, Khairulmazmi and Mansor, Shattri and Abu Seman, Idris (2017) Early detection of Ganoderma basal stem rot of oil palms using artificial neural network spectral analysis. Plant Disease, 101 (6). pp. 1009-1016. ISSN 0191-2917; ESSN: 1943-7692 https://apsjournals.apsnet.org/doi/abs/10.1094/PDIS-12-16-1699-RE 10.1094/PDIS-12-16-1699-RE
spellingShingle Ahmadi, Seyedeh Parisa
Muharam, Farrah Melissa
Ahmad, Khairulmazmi
Mansor, Shattri
Abu Seman, Idris
Early detection of Ganoderma basal stem rot of oil palms using artificial neural network spectral analysis
title Early detection of Ganoderma basal stem rot of oil palms using artificial neural network spectral analysis
title_full Early detection of Ganoderma basal stem rot of oil palms using artificial neural network spectral analysis
title_fullStr Early detection of Ganoderma basal stem rot of oil palms using artificial neural network spectral analysis
title_full_unstemmed Early detection of Ganoderma basal stem rot of oil palms using artificial neural network spectral analysis
title_short Early detection of Ganoderma basal stem rot of oil palms using artificial neural network spectral analysis
title_sort early detection of ganoderma basal stem rot of oil palms using artificial neural network spectral analysis
url http://psasir.upm.edu.my/id/eprint/64736/
http://psasir.upm.edu.my/id/eprint/64736/
http://psasir.upm.edu.my/id/eprint/64736/
http://psasir.upm.edu.my/id/eprint/64736/1/Early%20detection%20of%20Ganoderma%20basal%20stem%20rot%20of%20oil%20palms%20using%20artificial%20neural%20network%20spectral%20analysis.pdf