Kgopa et al. (2026) Machine Learning Algorithms for Integrating IoT Sensor into a Smart Irrigation system

Identification

• Journal: International Journal on Food Agriculture and Natural Resources
• Year: 2026
• Date: 2026-01-07
• Authors: Alfred Thaga Kgopa, Baakanyang Bessie Monchusi
• DOI: 10.46676/ij-fanres.v6i4.511

Research Groups

• Alfred Thaga Kgopa
• Baakanyang Bessie Monchusi

Short Summary

This study investigates the synergistic application of IoT-enabled sensors alongside machine learning methodologies (Decision Trees and Support Vector Machines) to augment irrigation effectiveness for small-scale farms. Preliminary findings suggest that Support Vector Machines outperform Decision Trees in reducing false positives and negatives, leading to more precise irrigation control, enhanced water conservation, and increased crop yields.

Objective

• To enhance water efficiency, strengthen food security, and support sustainable farming methods for small-scale farms by integrating IoT-enabled sensors with machine learning algorithms (Decision Trees and Support Vector Machines) for improved irrigation effectiveness.

Study Configuration

• Spatial Scale: Small-scale farms.
• Temporal Scale: Real-time sensor data collection and decision modification.

Methodology and Data

• Models used: Decision Trees (DT), Support Vector Machines (SVM), supervised learning techniques, reinforcement learning.
• Data sources: Real-time data collected from IoT-enabled sensors, including soil moisture, temperature, and humidity.

Main Results

• Support Vector Machines (SVM) demonstrated superior performance over Decision Trees (DT) in reducing false positives and negatives, resulting in more precise irrigation control.
• The proposed AI-driven irrigation system leads to enhanced water conservation, higher crop yields, and increased sustainability.
• The study identifies and addresses challenges associated with implementing IoT-based irrigation systems, such as data security, connectivity constraints, and cost considerations.

Contributions

• Adds to the existing literature on precision agriculture by demonstrating the synergistic application of IoT sensors and machine learning for improved irrigation.
• Provides practical insights and a viable solution for small-scale farmers aiming to implement smart irrigation systems.
• Highlights the benefits of AI-driven irrigation systems for sustainable farming practices and food security.

Funding

• Not specified in the provided text.

Citation

@article{Kgopa2026Machine,
  author = {Kgopa, Alfred Thaga and Monchusi, Baakanyang Bessie},
  title = {Machine Learning Algorithms for Integrating IoT Sensor into a Smart Irrigation system},
  journal = {International Journal on Food Agriculture and Natural Resources},
  year = {2026},
  doi = {10.46676/ij-fanres.v6i4.511},
  url = {https://doi.org/10.46676/ij-fanres.v6i4.511}
}