UrbanAgri: a transfer learning-based plant stress identification framework for sustainable smart urban growth

Urban Farm DB summary

This paper proposes a deep learning model, UrbanAgri, integrating ResNet101 and the Sparrow Search Optimization (SSO) algorithm, to identify plant stress in urban agriculture environments. Trained on a heterogeneous dataset of urban crop images, the model achieved an F1-score of 98.9 and ROC-AUC of 0.989, outperforming traditional approaches. This framework aims to reduce crop waste and promote sustainable urban agriculture by accurately detecting biotic and abiotic stress factors.