Abstract. Banana crops are highly susceptible to Fusarium wilt, a disease that can cause significant crop losses if not detected early. This study aimed to develop a classification model to detect Fusarium-infected banana plants using multispectral images. The dataset consisted of labeled images categorized into two classes: healthy and diseased (Fusarium). A convolutional neural network (CNN) was trained and evaluated, achieving an overall test accuracy of 81.25%. Class-wise evaluation showed a precision of 70%, recall of 100%, and F1 score of 82% for healthy plants, while the diseased class achieved 100% precision, recall of 67%, and F1 score of 80%. These results indicate strong precision performance but highlight the need to improve recall for effective disease monitoring. Comparisons with recent studies show that greater accuracy can be achieved through larger datasets and data augmentation. Following this approach, when other techniques were applied to the network (such as k-fold, class balancing, and spectral index segmentation), the model achieved maximum values (100%) for all evaluated metrics. This research demonstrates the potential of using multispectral images and deep learning for banana disease classification, with improvements focused on expanding the data volume and applying advanced training techniques to increase recall and overall robustness.
Zanchetta et al. (Fri,) studied this question.