Pest insects are a danger to both regional and global food security. In Jordan, the most productive crop is tomato. Jordan's agriculture output is threatened by insect infestations. The study intends to use a deep learning model called convolutional neural networks on a dataset that includes eight categories of insect pest images. A dataset was used and a group of images from reliable sources were added to it. The image collection was analyzed, and an image augmentation technique was used to increase the number of images, which reached 5894 after image augmentation. The data was split among 80 % training and 20 % validation. Convolutional Neural Networks trained on the data achieved 90 % training accuracy, 85 % testing accuracy, and 87 % validation accuracy. A high-accuracy deep learning model was developed that may be utilized on mobile applications to detect pests that affected crops to assist farmers. The original database used was small in size. When tested on deep learning and machine learning systems, the accuracy was very low, reaching 50–60 % without image augmentation, despite image enhancement techniques.

In the realm of global food security, plants serve as the primary source of sustenance. However, plant diseases pose a significant threat to this security. The process for diagnosing these diseases forms the bedrock of disease control efforts. The precision and expediency of these diagnoses wield substantial influence over disease management and the consequent reduction of economic losses. This research endeavors to diagnose the prevalent crops in Jordan, as identified by the Jordanian Department of Statistics for the year 2019. These crops encompass four key agricultural varieties: cucumbers, tomatoes, lettuce, and cabbage. To facilitate this, a novel dataset known as “Jordan22” was meticulously curated. Jordan22 was compiled by collecting images of diseased and healthy plants captured on Jordanian farms. These images underwent meticulous classification by a panel of three agricultural specialists well-versed in plant disease identification and prevention. The Jordan22 dataset comprises a substantial size, amounting to 3210 images. The results yielded by the CNN were remarkable, with a test accuracy rate reaching an impressive 0.9712. Optimal performance was observed when images were resized to 256 × 256 dimensions, and max pooling was used instead of average pooling. Furthermore, the initial convolutional layer was set at a size of 32, with subsequent convolutional layers standardized at 128 in size. In conclusion, this research represents a pivotal step towards enhancing plant disease diagnosis and, by extension, global food security. Through the creation of the Jordan22 dataset and the meticulous training of a CNN model, we have achieved substantial accuracy in disease detection, paving the way for more effective disease management strategies in agriculture.