RESUMEN
Agriculture is considered the backbone of Tanzania's economy, with more than 60% of the residents depending on it for survival. Maize is the country's dominant and primary food crop, accounting for 45% of all farmland production. However, its productivity is challenged by the limitation to detect maize diseases early enough. Maize streak virus (MSV) and maize lethal necrosis virus (MLN) are common diseases often detected too late by farmers. This has led to the need to develop a method for the early detection of these diseases so that they can be treated on time. This study investigated the potential of developing deep-learning models for the early detection of maize diseases in Tanzania. The regions where data was collected are Arusha, Kilimanjaro, and Manyara. Data was collected through observation by a plant. The study proposed convolutional neural network (CNN) and vision transformer (ViT) models. Four classes of imagery data were used to train both models: MLN, Healthy, MSV, and WRONG. The results revealed that the ViT model surpassed the CNN model, with 93.1 and 90.96% accuracies, respectively. Further studies should focus on mobile app development and deployment of the model with greater precision for early detection of the diseases mentioned above in real life.
RESUMEN
Maize Lethal Necrosis (MLN) and Maize Streak Virus (MSV) are among maize diseases which affect productivity in Tanzania and Africa at large. These diseases can be detected early for timely interventions and minimal losses. Machine learning (ML) has emerged as a powerful tool for automated diseases detection, offering several advantages over traditional methods. This article presents the updated dataset of 9356 imagery maize leaves to assist researchers in developing technological solutions for addressing crop diseases. The high-resolution imagery data presented in this dataset were captured using smartphone cameras in farm fields which were not selected in the previously published dataset. Also, data collection was taken in the range of three months from November 2022 to January 2023 to incorporate farming season not covered in the previously published dataset. The presented dataset can be used by researchers in the field of Artificial Intelligence (AI) to develop ML solutions and eliminate the need of manual inspection and reduce human bias. Developing ML solutions require large amount of data therefore, the updated and previously published datasets can be combined to accommodate diverse and wider applicability.