Classification of Non-Infected and Infected with Basal Stem Rot Disease Using Thermal Images and Imbalanced Data Approach

Basal stem rot (BSR) disease occurs due to the most aggressive and threatening fungal attack of the oil palm plant known as Ganoderma boninense (G. boninense). BSR is a disease that has a significant impact on oil palm crops in Malaysia and Indonesia. Currently, the only sustainable strategy available is to extend the life of oil palm trees, as there is no effective treatment for BSR disease. This study used thermal imagery to identify the thermal features to classify non-infected and BSR-infected trees. The aims of this study were to (1) identify the potential temperature features and (2) examine the performance of machine learning (ML) classifiers (naïve Bayes (NB), multilayer perceptron (MLP), and random forest (RF) to classify oil palm trees that are non-infected and BSR-infected. The sample size consisted of 55 uninfected trees and 37 infected trees. We used the imbalance data approaches such as random undersampling (RUS), random oversampling (ROS) and synthetic minority oversampling (SMOTE) in these classifications due to the different sample sizes. The study found that the Tmax feature is the most beneficial temperature characteristic for classifying non-infected or infected BSR trees. Meanwhile, the ROS approach improves the curve region (AUC) and PRC results compared to a single approach. The result showed that the temperature feature Tmax and combination feature TmaxTmin had a higher correct classification for the G. boninense non-infected and infected oil palm trees for the ROS-RF and had a robust success rate, classifying correctly 87.10% for non-infected and 100% for infected by G. boninense. In terms of model performance using the most significant variables, Tmax, the ROS-RF model had an excellent receiver operating characteristics (ROC) curve region (AUC) of 0.921, and the precision–recall curve (PRC) region gave a value of 0.902. Therefore, it can be concluded that the ROS-RF, using the Tmax, can be used to predict BSR disease with relatively high accuracy.

Download Full-text

Machine-Learning Approach Using SAR Data for the Classification of Oil Palm Trees That Are Non-Infected and Infected with the Basal Stem Rot Disease

Agronomy ◽

10.3390/agronomy11030532 ◽

2021 ◽

Vol 11 (3) ◽

pp. 532

Author(s):

Izrahayu Che Hashim ◽

Abdul Rashid Mohamed Shariff ◽

Siti Khairunniza Bejo ◽

Farrah Melissa Muharam ◽

Khairulmazmi Ahmad

Keyword(s):

Machine Learning ◽

Success Rate ◽

Oil Palm ◽

Model Comparison ◽

Stem Rot ◽

Operating Characteristics ◽

Basal Stem Rot ◽

Palm Trees ◽

Rot Disease ◽

Mlp Model

Basal stem rot disease (BSR) in oil palm plants is caused by the Ganoderma boninense (G. boninense) fungus. BSR is a major disease that affects oil palm plantations in Malaysia and Indonesia. As of now, the only available sustaining measure is to prolong the life of oil palm trees since there has been no effective treatment for the BSR disease. This project used an ALOS PALSAR-2 image with dual polarization, Horizontal transmit and Horizontal receive (HH) and Horizontal transmit and Vertical receive (HV). The aims of this study were to (1) identify the potential backscatter variables; and (2) examine the performance of machine learning (ML) classifiers (Multilayer Perceptron (MLP) and Random Forest (RF) to classify oil palm trees that are non-infected and infected by G. boninense. The sample size consisted of 55 uninfected trees and 37 infected trees. We used the imbalance data approach (Synthetic Minority Over-Sampling Technique (SMOTE) in these classifications due to the differing sample sizes. The result showed backscatter variable HV had a higher correct classification for the G. boninense non-infected and infected oil palm trees for both classifiers; the MLP classifier model had a robust success rate, which correctly classified 100% for non-infected and 91.30% for infected G. boninense, and RF had a robust success rate, which correctly classified 94.11% for non-infected and 91.30% for infected G. boninense. In terms of model performance using the most significant variables, HV, the MLP model had a balanced accuracy (BCR) of 95.65% compared to 92.70% for the RF model. Comparison between the MLP model and RF model for the receiver operating characteristics (ROC) curve region, (AUC) gave a value of 0.92 and 0.95, respectively, for the MLP and RF models. Therefore, it can be concluded by using only the HV polarization, that both the MLP and RF can be used to predict BSR disease with a relatively high accuracy.

Download Full-text

Deteksi Ganoderma secara molekuler pada kebun kelapa sawit yang diberi perlakuan biofungisida Ganor (Molecular detection of Ganoderma on oil palm plantation treated with Ganor biofungicide)

E-Journal Menara Perkebunan ◽

10.22302/iribb.jur.mp.v1i1.289 ◽

2018 ◽

Vol 86 (1) ◽

Author(s):

Hayati MINARSIH ◽

Happy WIDIASTUTI ◽

Djoko SANTOSO

Keyword(s):

Sex Ratio ◽

Molecular Analysis ◽

Oil Palm ◽

Pathogenic Fungus ◽

Reproductive Organs ◽

Stem Rot ◽

Molecular Technique ◽

Basal Stem Rot ◽

Palm Trees ◽

Rot Disease

AbstractGanor organic fungicide potentially reduces Ganoderma, a pathogenic fungus causing basal stem rot disease. Application of Ganor on oil palm trees in the plantation attacked Ganoderma, inhibits the growth of Ganoderma fruiting bodies, improves rooting and stimulates the opening of the spear leaf. This study aims to identify molecularly the presence of Ganoderma in oil palm trees that have been attacked by Ganoderma routinely treated with Ganor for three months. Molecular analysis was performed by PCR using Ganoderma specific primers. The analysis results of sample from trunks and roots of oil palm, indicating that the Ganoderma infected oil palm which has been treated with Ganor, were relatively free (96.4%) of Ganoderma. Of the 28 samples examined of treated plants, 27 samples did not indicate the presence of Ganoderma specific DNA band. On the other hand, the untreated oil palm trees infected by Ganoderma were still detected by the appearence of DNA bands specific to Ganoderma. The results of molecular analysis indicated that Ganor treatments can effectively reduce the attack rate of Ganoderma in oil palm trees in the plantation infected by Ganoderma. However, the use of the molecular technique for early detection needs to be further tested to evaluate its consistency prior to introduction to the commercial growers. The reproducibility can be confirmed by repeating the experiment using more samples. Ganor effectiveness in curing oil palm trees infected by Ganoderma, maybe indicated by the ability of the reproductive organs to develop, particularly female flowers. The sex ratio of Ganor treated oil palms was clearly higher than that of control palms in 10 to 12 weeks after the treatment.[Keywords: organic fungicides, stem rot, molecular analysis, Elais guinensis Jack.] AbstrakFungisida organik Ganor berpotensi mengurangi serangan Ganoderma, cendawan patogenik penyebab penyakit busuk pangkal batang. Aplikasi Ganor pada tanaman kelapa sawit di kebun yang terserang Ganoderma, menghambat pertumbuhan tubuh buah Ganoderma, memper-baiki perakaran dan merangsang pembukaan daun tombak. Penelitian ini bertujuan untuk mengidentifikasi secara molekuler adanya Ganoderma pada tanaman kelapa sawit terserang Ganoderma yang telah mendapat perlakuan Ganor secara rutin selama tiga bulan. Analisis molekuler dilakukan dengan teknik PCR menggunakan primer DNA spesifik Ganoderma. Hasil analisis sampel batang dan akar tanaman kelapa sawit, menunjukkan bahwa tanaman Perlakuan, yaitu kelapa sawit terserang Ganoderma yang telah mendapat perlakuan Ganor, 96,4% bebas Ganoderma. Dari 28 sampel tanaman Perlakuan yang diperiksa, 27 sampel tidak menunjukkan adanya pita DNA spesfik Ganoderma. Sementara itu pada tanaman Kontrol, yaitu tanaman kelapa sawit terserang Ganoderma dan tidak mendapat perlakuan Ganor, 100% masih terdeteksi adanya Ganoderma. Dari 7 sampel tanaman kontrol yang diperiksa semuanya menunjukkan adanya pita DNA spesifik Ganoderma. Hasil analisis molekuler ini mengindikasikan bahwa perlakuan Ganor efektif mengurangi tingkat serangan Ganoderma pada tanaman kelapa sawit di kebun yang terinfeksi Ganoderma. Namun demikian, untuk lebih meyakinkan praktisi perkebunan, penggunakan teknik molekuler ini masih perlu diuji lebih lanjut terkait konsistensinya. Reprodusibilitas dapat dikonfirmasi dengan mengulangi percobaan menggunakan lebih banyak sampel. Efektivitas Ganor dalam menyehatkan tanaman kelapa sawit terserang Ganoderma ini, terindikasi juga dari perkembangan organ reproduktifnya. Sex ratio meningkat dalam waktu 10 hingga 12 minggu setelah perlakuan.[Kata Kunci: fungisida organik, busuk pangkal batang, analisis molekuler, Elais guinensis Jack. ]

Download Full-text

EFFECT OF MICRONUTRIENTS-ENRICHED FERTILIZERS ON BASAL STEM ROT DISEASE INCIDENCE AND SEVERITY ON OIL PALM (ELAEIS GUINEENSIS JACQ.) SEEDLINGS

American Journal of Applied Sciences ◽

10.3844/ajassp.2014.1841.1859 ◽

2014 ◽

Vol 11 (10) ◽

pp. 1841-1859 ◽

Cited By ~ 6

Author(s):

Fabien Fonguimgo Tengoua ◽

Mohamed M. Hanafi ◽

A. S. Idris ◽

Kadir Jugah ◽

Jamaludin Nurul Mayziatul Azwa ◽

...

Keyword(s):

Oil Palm ◽

Elaeis Guineensis ◽

Disease Incidence ◽

Stem Rot ◽

Basal Stem Rot ◽

Rot Disease

Download Full-text

Advances in the Interpretation of Tomographic Images as an Early Detection Method of Oil Palm Affected by Basal Stem Rot in Colombia

Plant Disease ◽

10.1094/pdis-12-15-1473-re ◽

2016 ◽

Vol 100 (8) ◽

pp. 1559-1563 ◽

Cited By ~ 2

Author(s):

M. Arango ◽

G. Martínez ◽

G. Torres

Keyword(s):

Early Detection ◽

Electrical Impedance Tomography ◽

Oil Palm ◽

Electrical Impedance ◽

Disease Incidence ◽

Stem Rot ◽

Internal Damage ◽

Impedance Tomography ◽

Basal Stem Rot ◽

Palm Trees

Basal stem rot, one of the most important diseases of oil palm in Southeast Asia, has also been identified in Colombia. The increase in disease incidence in the last decade has attracted the attention of producers and researchers. In the search for a procedure that allows for the early identification of diseased palm, Cenipalma evaluated the use of electrical impedance tomography to identify the different stages of development of basal stem rot. The tomograms were compared with transversal sections of healthy and diseased oil palm trees. Following Cenipalma’s preliminary studies on early diagnosis of basal stem rot with tomography, the present study improved upon the technique by analyzing the tomograms of 209 diseased palm trees (confirmed by symptomatology), 346 asymptomatic palm trees, and 132 healthy palm trees. The minimum and maximum electric impedance values as well as the ratio between these values was recorded. The range of 1 to 95 Ω was used to represent the internal damage. The ratios averaged 5.1 for diseased, 1.9 for asymptomatic, and 1.5 for healthy palm trees. With the range and the ratio criteria established, it was possible to identify the disease in 100% of asymptomatic sampled palm trees. This study demonstrated that electrical impedance tomography is a powerful tool for early detection of basal stem rot, which can be used to establish an early disease management program.

Download Full-text