An Intelligent Neural Networks Approach for Monitoring of Soilless Urban Farms

Year : 2025 | Volume : 12 | 03 | Page :
    By

    Aditi Bhardwaj,

  • Neena Batra,

Abstract

Urban agriculture is increasingly recognized as a sustainable approach to addressing food security challenges in rapidly growing and densely populated cities. Conventional soil-based farming often faces limitations such as space scarcity, excessive water consumption, and environmental degradation. To overcome these challenges, soilless farming techniques such as hydroponics and aeroponics have gained significant attention due to their efficient utilization of space, reduced water requirements, and potential for year-round crop production. However, despite these advantages, the effective management of soilless farming systems requires continuous monitoring of plant health and environmental conditions, which can be labor-intensive and dependent on expert knowledge. This paper proposes a real-time intelligent monitoring framework that integrates advanced image processing techniques with environmental sensor data to automate plant health assessment in soilless urban farms. The framework employs a hybrid neural network model that combines convolutional neural networks (CNN) for visual feature extraction with long short-term memory (LSTM) networks for temporal analysis of sensor data, including pH, electrical conductivity (EC), temperature, and humidity. By leveraging the complementary strengths of CNN and LSTM, the proposed system is capable of accurately identifying plant stress, nutrient deficiencies, and disease symptoms while simultaneously analyzing environmental fluctuations that influence crop growth. Preliminary experimental results demonstrate that the proposed framework achieves higher accuracy and efficiency compared to conventional manual observation methods. Moreover, the system enables better resource utilization by minimizing water and nutrient wastage, thereby contributing to sustainable urban farming practices. The research highlights the potential of integrating artificial intelligence with urban agriculture to create scalable, automated, and resource-efficient farming solutions that can enhance food production in smart cities of the future.

Keywords: Neural network, soilless farming, hydroponics, aeroponics, urban agriculture, CNN, LSTM, IoT, smart farming, precision agriculture

How to cite this article:
Aditi Bhardwaj, Neena Batra. An Intelligent Neural Networks Approach for Monitoring of Soilless Urban Farms. Journal of Water Resource Engineering and Management. 2025; 12(03):-.
How to cite this URL:
Aditi Bhardwaj, Neena Batra. An Intelligent Neural Networks Approach for Monitoring of Soilless Urban Farms. Journal of Water Resource Engineering and Management. 2025; 12(03):-. Available from: https://journals.stmjournals.com/jowrem/article=2025/view=234984


References

  1. Nabaei SH, Zheng Z, Chen D, Heydarian A. Multimodal data integration for sustainable indoor gardening: Tracking any plant with time series foundation model. arXiv. 2025. Available from: https://arxiv.org/abs/2503.21932.
  2. Ali NA, Jaafar AS, Hashim NMZ, Mohamad NR. Enhanced wireless end-to-end IoT hydroponic system. Int J Acad Res Bus Soc Sci. 2024;14:1112–23. doi:10.6007/IJARBSS/v14-i12/24401.
  3. Khalid M, Sarfraz MS, Iqbal U, Aftab MU, Niedbała G, Rauf HT. Real-time plant health detection using deep convolutional neural networks. Agriculture. 2023;13:510. doi:10.3390/agriculture13020510.
  4. Slimani H, Mhamdi JE, Jilbab A. Deep learning structure for real-time crop monitoring based on neural architecture search and UAV. Braz Arch Biol Technol. 2024;67. doi:10.1590/1678-4324-2024231141.
  5. Rahman M, Hossain MS, Muhammad A. Greening urban living: Designing an intelligent hydroponic system with automatic nutrient regulation for small-space agriculture. In: Proc IEEE Int Conf SMART Agriculture (ICSA); 2024. p. 45–50.
  6. Singh S, Verma R, Kumar A. IoT-based smart hydroponics system. IEEE Access. 2020;8:123456–67.
  7. Zhang M, Lee T, Liu Q. Deep learning for plant health monitoring. Comput Electron Agric. 2019;150:456–68.
  8. Dietrich S, Kusnezoff M, Michaelis A. Studies of indium tin oxide-based sensing electrodes in potentiometric zirconia solid electrolyte gas sensors. Sensors. 2021;21(7):2345. doi:10.3390/s21072345. PubMed: 33801748.
  9. Mahapatra J, Nair S, Dutta R. IoT-based real-time farm management system. In: Proc Int Conf Intelligent Computing and Control Systems (ICICICT); 2017. p. 134–8.
  10. Wang J, Damevski K, Chen H. Sensor data modeling and validating for wireless soil sensor network. Comput Electron Agric. 2015;112:75–82. doi:10.1016/j.compag.2014.12.016.
  11. Aggelopoulou AD, Bochtis D, Fountas S, Swain KC, Gemtos TA, Nanos GD. Yield prediction in apple orchards based on image processing. Precision Agric. 2011;12:448–56. doi:10.1007/s11119-010-9187-0.
  12. Fernández-Ahumada L, Torres-Sánchez J, Rodríguez D. Monitoring and operating irrigation networks using IoT and cloud. Sensors. 2019;19.
  13. Kumar A, Sharma N, Singh P. IoT-based smart irrigation using regression algorithm. In: Proc Int Conf Intelligent Computing and Control Systems (ICICICT); 2017. p. 102–7.
  14. Tamura Y. LSTM back propagation: Following the flows of variables. Applied AI Blog [Online]. 2020. Available from: https://appliedai.blog/lstm-backpropagation.
Ahead of Print Subscription Original Research
Volume 12
03
Received 20/06/2025
Accepted 08/09/2025
Published 18/09/2025
Publication Time 90 Days
102

Login


My IP

PlumX Metrics