ORIGINAL RESEARCH article
Front. Sustain. Cities
Sec. Smart Technologies and Cities
This article is part of the Research TopicSmart Energy Solutions for Sustainable Urban GrowthView all articles
UrbanAgri: A Transfer Learning-Based Plant Stress Identification Framework for Sustainable Smart Urban Growth
Provisionally accepted
- 1Akal University, Bathinda, India
- 2Nirma University, Ahmedabad, Gujarat, India
- 3baba farid group of institutes, bathinda, India
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
The rapid trend of global urbanization is substantially diminishing arable land, heightening difficulties to global food security as the population is predicted to reach 9.7 billion by 2050. Urban agriculture presents a promising avenue for sustainable urban food production but faces acute challenges in effective plant disease monitoring due to fragmented growing spaces, variable microclimates, and limited resources typical of city environments. However, plant health monitoring in this ecosystem is complicated due to several biotic and abiotic stressors. This research proposed a novel technique for sustainable urban agriculture using a deep learning-based framework, combining ResNet101 and the Sparrow Search Optimization (SSO) algorithm, to identify plant stress with high precision. Leveraging transfer learning, our model detects both biotic and abiotic stress factors accurately, achieving an F1-score of 98.9% and ROC-AUC of 0.989, outperforming traditional methods such as RandomForest and KNN. Our contributions enable the sustainable city strategy by decreasing crop waste in urban farming through early stress detection. The optimised ResNet101+SSO model is specifically built for urban agriculture, giving an innovative solution to the unique difficulties of limited space and data availability. By addressing data scarcity and the intricacies of multifactorial plant stress detection in urban farming contexts, this approach enables scalable, precise, and early stress monitoring systems aligned with smart city sustainability and food security objectives.
Keywords: sustainable agriculture, Biotic and Abiotic Plant Stressors, deep learning, Sparrow SearchAlgorithm, CNN - convolutional neural network
Received: 27 Apr 2025; Accepted: 22 Sep 2025.
Copyright: © 2025 Kaur, Kaur, Kumari, Shukla, Datt and Chand. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Upinder Kaur, upinder_cs@auts.ac.in
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.