(IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 13, No. 6, 2022 Classification of Palm Trees Diseases using Convolution Neural Network Marwan Abu-zanona 1 , Said Elaiwat 2 , Shayma’a Younis 3 , Nisreen Innab 4 , M. M. Kamruzzaman 5 Department of Computer Sciences, College of Shari’a and Islamic Studies in Al Ahsaa, Al Imam Mohammad IbnSaud Islamic University, Al Ahsaa, Saudi Arabia 1 Department of Computer Science, College of Computer and Information Sciences, Jouf University, Sakakah, Saudi Arabia 2, 5 Department Biomedical Informatics engineering, Yarmouk University, Irbid, Jordan 3 Department of Computer Science and Information Systems, College of Applied Sciences, AlMaarefa University, Riyadh, Saudi Arabia 4 Abstract—The palm tree is considered one of the most durable trees , and it occupies an advanced position as one of the most famous and most important trees that are planted in different regions around the world, which enter into many uses and have a number of benefits. In the recent years , date palms have been exposed to a large number of diseases. These diseases differ in their symptoms and causes, and sometimes overlap, making the diagnosing process with the naked eye difficult, even by an expert in this field. This paper proposes a CNN-model to detect and classify four common diseases threatening palms today, Bacterial leaf blight, Brown spots, Leaf smut, white scale in addition to healthy leaves. The proposed CNN structure includes four convolutional layers for feature extraction followed by a fully connected layer for classification. For performance evaluation, we investigate the performance of the proposed model and compare to other CNN- structures, VGG-16 and MobileNet, using four evaluation metrics: Accuracy, Precision, Recall and F1 Score. Our proposed model achieves 99.10% accuracy rate while VGG- 16 and MobileNet achieve 99.35% and 99.56% accuracy rates, respectively. In general, the performance of our model and other models are very close with a minor advantage to MobileNet over others. In contrast, our model characterized by simplicity and shows low computational training time comparing to others. Keywords—Palm trees diseases; convolutional neural networks; mobileNet; VGG-16 I. I NTRODUCTION The date palm is considered one of the most important fruit trees in the Arab and Islamic world, as Arab countries account for 71% of its trees in the world, and 81% of the total global production, while this percentage rises to 99% (103.95 million trees) of the number of trees. The world’s date palm, amounting to 105 million, when combining the Arab and Islamic worlds, according to the Food and Agriculture Organization of the United Nations. According to the latest statistics adopted in the world, including the statistic conducted by the Egyptian Embassy in Brazil in 1990 as shown in table I, it was found that the palm tree is one of the main agricultural products produced by the Arab countries and is considered a major element in supporting the macro economy in these countries, so it is very important to pay attention to the quality and quantity of production Palm trees, but unfortunately, the quality, quality and quantity of palm trees are greatly threatened with confinement due to the common palm diseases these days, where in general palm trees are threatened by 4 main types of diseases, which are, Bacterial leaf blight, Brown spots, Leaf smut, white scale, the nature and symptoms of these diseases are different in their form, in the area of their appearance and distribution on palm trees, so it is very important to reveal modern techniques that contribute greatly to discovering them before they cause tremendous pressure on the quality and quantity of palm trees produced. Symptoms of leaf smut Small irregular brown to black spots occurred on the upper and bottom surfaces of rachis and fronds, ranging in size from 3 to 7 mm [1]. Bacterial Leaf blight symptoms were elongated brown to black patches that grew in size and spread across a considerable region, creating cankers on the midrib [1]. Brown spot disease is characterized by the appearance of non-specific dark spots, and as the infection progresses, the center of the spot turns to a pale color, but the edges remain brown to gray. The spots appear on the leaves, thorns, and the middle vein (the leaves). The size of the spots ranges from one to several centimeters, but their size and color may vary according to the fungus that causes them..Another serious risk is a lethal pest called white scale .White palm Scale is a species of armoured scale insect. This means that they produce a hard outer coating that covers the body, which protects them from pathogens. They’re also well protected from topical pesticides. White Scale insects attack palm by sucking the sap through a fine, thin feeding-tubes. Infestations rarely kill plants but can impact vigour [2]. The methods usually used by farmers depend mainly on observing the affected foliage with the naked eye by experts. Unfortunately, this method is not effective because of the distance of the palm tree from the ground and at the same time due to the somewhat similarity between the symptoms of the four palm diseases mentioned previously. In addition to that, the manual examination of palm leaves is time-consuming, especially in the case of large farms. In this paper, a CNN-based model is proposed to detect four of the most frequent palm illnesses is suggested. These illnesses are, Bacterial leaf blight, brown spots, Leaf smut, white scale. The proposed model model characterized by simplicity( easy www.ijacsa.thesai.org 943 | Page