Author
Abstract
Rapid urbanization, climate change, and increasing global food demand have led to a pressing urgency to realize intelligent and resource-efficient agricultural practices that can accelerate the transition to sustainable food production within the cities of tomorrow. Urban agriculture in the form of rooftop, balcony, and vertical gardening can become key to this transition, yet its potential is hampered by highly variable microclimates, sub-optimal water management, and lack of decision support for the urban gardener. Recent developments in machine learning and sensing technologies through the Internet-of-Things (IoT) have enabled the emergence of intelligent agricultural systems that can monitor and control environmental and cultivation parameters. Data-driven irrigation control and environmental management systems can significantly improve water use efficiency, crop yields, and climate adaptability in agriculture. “Machine Learning-Based Climate-Adaptive Smart Gardening System for Sustainable Urban Agriculture” was proposed to predict soil moisture, sun exposure, and other environmental effects based on machine learning supervised predictive models of gardening sensor data. This research aimed to design and implement an energy-efficient smart urban garden system that adjusts gardening conditions to mitigate climate impacts such as drought and elevated temperature. The smart garden includes multiple environmental sensors, an edge server for data integration, machine learning predictive models, and an automated control subsystem. Sensors record soil moisture, air temperature, humidity, solar exposure, and light intensity in real-time and use machine learning supervised models such as Gradient Boosting, Random Trees, and LSTM to predict irrigation needs, plant stress, and environmental changes. Machine-learning-based irrigation prediction using environmental sensing data is well-studied with high accuracy, where a recent study reported over 95% accuracy using Gradient Boosting models for irrigation prediction. There are climate-based decisions that are expected to be integrated into the proposed system to modify irrigation and nutrient feeding based on climate prediction. The proposed system can use sensor values coupled with past climate data and crop growth data to anticipate the impact of climate change, such as heat waves, droughts, or erratic precipitation patterns. Smart irrigation and environmental sensors can play a significant role in reducing water consumption while enhancing productivity. Some researchers have conducted experiments and used intelligent irrigation systems to reduce water usage by 28–50% compared with traditional irrigation methods. To show the capacity of the proposed model, a virtual smart garden scenario is created for experimental testing using environmental data influenced by sensors. Prediction accuracy, water efficiency, crop growth, and system reaction to changing climate data are evaluated in the experiments. Preliminary results indicate that the machine learning-based decision-making system significantly improves irrigation and water efficiency and stabilizes plant growth in an urban garden environment. On top of that, the proposed system that uses machine learning at the edge reduces the need for network dependency for autonomous operation, making it both scalable and adaptable for urban families, community gardens, and smart city agriculture.
Suggested Citation
Zakhro Sodikova, 2025.
"Machine Learning–Based Climate-Adaptive Smart Gardening System for Sustainable Urban Agriculture,"
International Journal of Scientific Research in Computer Science, Engineering and Information Technology, International Journal of Scientific Research in Computer Science, Engineering and Information Technology, vol. 11(3), pages 1096-1110, June.
Handle:
RePEc:jbh:ijsrcs:v11:y2025:i3:id:1892
DOI: 10.32628/CSEIT25111182
Note: Article URL: https://ijsrcseit.com/home/article/view/CSEIT25111182
Download full text from publisher
Corrections
All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:jbh:ijsrcs:v11:y2025:i3:id:1892. See general information about how to correct material in RePEc.
If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.
We have no bibliographic references for this item. You can help adding them by using this form .
If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Pankaj Sharma (USA) (email available below). General contact details of provider: https://ijsrcseit.com/home .
Please note that corrections may take a couple of weeks to filter through
the various RePEc services.