Enhancing agricultural classification models through data augmentation and advanced deep learning techniques

In the field of agricultural data analysis, achieving high quality classification modeling remains a significant challenge due to the inherent variability and complexity of agricultural datasets. This study investigated cutting-edge approaches to enhance model performance through data augmentation techniques and the application of advanced deep learning models to artificially enlarge the training dataset, thereby improving model generalizability and robustness. Additionally, the study evaluated the efficacy of state-of-the-art models (i.e., ViT-Ti/16, CaiT-XXS-24, XCiT-T12, Resnet26, ConvNeXt-T) for agricultural data analysis. The experimental results revealed a marked improvement in terms of accuracy and F1-Score when applied data augmentation into the training session. This underscored the potential of these techniques to significantly advance the field of agricultural informatics. Briefly, the findings contributed to the development of more reliable and high performance models for agricultural practices.