The oil palm industry is vital for the Malaysian economy. However, it is threatened by the Ganoderma boninense fungus, which causes basal stem rot (BSR) disease. Foliar symptoms of the disease include the appearance of several unopened spears, flat crowns, and small crown size. The effect of this disease depends on the severity of the infection. Currently, the disease can be detected manually by analyzing the oil palm tree’s physical structure. Terrestrial laser scanning (TLS) is an active ranging method that uses laser light, which can directly represent the tree’s external structure. This study aimed to classify the healthiness levels of the BSR disease using a machine learning (ML) approach. A total of 80 oil palm trees with four different healthiness levels were pre-determined by the experts during data collection with 40 each for training and testing. The four healthiness levels are T0 (healthy), T1 (mildly infected), T2 (moderately infected), and T3 (severely infected), with 10 trees in each level. A terrestrial scanner was mounted at a height of 1 m, and each oil palm was scanned at four positions at a distance of 1.5 m around the tree. Five tree features were extracted from the TLS data: C200 (crown slice at 200 cm from the top), C850 (crown slice at 850 cm from the top), crown area (number of pixels inside the crown), frond angle, and frond number. C200 and C850 were obtained using the crown stratification method, while the other three features were obtained from the top-down image. The obtained features were then analyzed by principal component analysis (PCA) to reduce the dimensionality of the dataset and increase its interpretability while at the same time minimizing information loss. The results showed that the kernel naïve Bayes (KNB) model developed using the input parameters of the principal components (PCs) 1 and 2 had the best performance among 90 other models with a multiple level accuracy of 85% and a Kappa coefficient of 0.80. Furthermore, the combination of the two highest PC variance with the most weighted to frond number, frond angle, crown area, and C200 significantly contributed to the classification success. The model also could classify healthy and mildly infected trees with 100% accuracy. Therefore, it can be concluded that the ML approach using TLS data can be used to predict early BSR infection with high accuracy.

Basal stem rot (BSR) disease of oil palm (Elaeis guineensis Jacq.) spreads through the contact of the plant roots with Ganoderma boninense (G. boninense) Pat. inoculum in the soil. The soil properties can be altered by growing seedlings with or without G. boninense inoculum. In the early stage of infection, the symptoms are difficult to detect. Therefore, an understanding of the environmental soil conditions of the plant is crucial in order to indicate the presence of the fungus. This paper presents an analysis of the temporal changes of the soil properties associated with the G. boninense infection in oil palm seedlings. A total of 40 seedlings aged five months were used in the study, comprising 20 inoculated (infected seedlings: IS) and 20 control (healthy seedlings: HS) seedlings. The seedlings were grown in a greenhouse for six months (24 weeks) under a controlled environmental temperature and humidity. The data of the soil moisture content (MC in %), electrical conductivity (EC in µS/cm), and temperature (T in °C) for each seedling were collected daily using three MEC10 soil sensors every hour and then transferred to the ThingSpeak cloud using a 3G Internet connection. Based on the results, the mean MC and EC showed a decreasing trend, while the mean T showed an increasing trend in both HS and IS during the six-month monitoring period. The overall mean in both the monthly and weekly analysis of MC, EC, and T was higher in HS than IS. However, in the monthly analysis, a Student’s t-test at a 5% significance level showed that only the soil MC and EC were significantly different between HS and IS, while in the weekly analysis, HS was significantly different from IS in all parameters. This study suggests that soil MC, EC, and T can be used as indicators of the G. boninense infection, especially for the weekly data.

The oil palm grown around the world to meet the demand for food and bio-fuels, is threatened by a fatal disease known as basal stem rot (BSR). Application of machine learning (ML) in agriculture keeps increasing with the advancement of technology, especially in disease detection. This manuscript presents a mini-review of the different methods relevant to BSR disease classification and detection using ML. The steps were discussed, including pre-processing and approaches used. Various algorithms, feature extractions and classification methods were discussed in the review. The review results revealed that the adoption of disease detection and classification methods for BSR disease in oil palm using ML approaches is still in its early stages of research. Hence, new tools are needed to fully automate the detection and classification processes for practical, operational, fast and accurate systems to be used in vast oil palm plantations.