Marco de aprendizaje profundo basado en MapReduce para la detección de enfermedades en hojas de papa en agricultura...

Sustainable precision agriculture has become increasingly vital for enhancing crop productivity, minimizing environmental impact, and ensuring global food security. Potato leaf diseases, such as blight, pose significant threats to crop yield. The accurate and timely detection of potato leaf diseases is critical for minimizing yield losses. This study proposes a pair a lightweight MobileNetV3 classifier with a MapReduce-style data pipeline that parallelizes preprocessing and batch inference across nodes. The model utilizes a dataset comprising 2152 images categorized into three classes. The preprocessing pipeline includes image resizing, normalization, and data augmentation to enhance model generalization. MobileNetV3 is employed for high-level feature extraction and classification, while MapReduce enables parallel processing and efficient handling of large datasets. The experimental results achieved a detection accuracy of 98.6% across the training phase, 96.9% in the validation phase, and 96.8% in the testing phase, and testing sensitivity (95.3%), Specificity (97.7%), and F1-Score (96.4%) While training for this dataset is performed on GPU, the MapReduce pipeline makes the system horizontally extensible for larger deployments and continuous image ingest. We report per-class confusion matrices and standard clinical metrics, and analyze when MapReduce provides throughput gains versus a single-node baseline. The proposed model significantly outperforms several state-of-the-art methods, as validated through statistical measures such as sensitivity, specificity, and misclassification rate. Its high accuracy, scalability, and robustness make it suitable for large-scale agricultural disease monitoring and precision farming applications.