<p>Smart agriculture, coupled with the implementation of modern technologies and artificial intelligence, is one crucial way of responding to the challenge caused by agricultural pests, through which the world loses crop products as pointed out by the Food and Agriculture Organization (FAO). In this manuscript, there is a new smartphone application designed to use cloud computing that implements a cycle-consistent generative adversarial network (CCGAN) used to identify pests in agriculture. The proposed system uses the IP102 public dataset to gather input images that represent different pests. The images are pre-processed using the Gaussian-Adaptive Bilateral Filter (GABF) method, which improves the quality of the images by removing noise. Feature extraction is done using the term frequency-inverse document frequency (TF-IDF) method, which helps in identifying key characteristics of the pests. A CCGAN model is then used for pest classification, targeting five pest categories: Aphids, Cicadellidae, Flax Budworms, Flea Beetles, and Red Spiders. The integration of cloud computing, facilitated through Python, enhances the system’s ability to augment and classify images efficiently. The effectiveness of the proposed model is evaluated using several performance metrics, including accuracy, precision, recall, sensitivity, F1-score, mean squared error (MSE), and computational time. The results show that the proposed method surpasses existing techniques by gaining 10.47%, 12.85%, 9.36%, 14.45%, 11.72%, 7.56%, and 5.56% accuracy compared to IYOLOv7-tiny, CNN-TL, DSS-DL, DCNN-Mnet, YOLOv5x, ResNet50, and EfficientNetB0, respectively. Furthermore, the proposed approach gains 20.59%, 25.47%, 18.64%, 32.5%, 27.03%, 22.75%, and 19.32% less computational time compared to the existing methods. This clearly shows the efficiency and better performance of the proposed method in terms of accuracy and computational efficiency.</p>