EUVIMEDEUVIMED entdecken
Crossref

Optimization of Water Use in Precision Agriculture Through IoT-Enabled Multi-Sensor Fusion and Machine Learning-Based Smart Irrigation Scheduling

Amritpal Kaur, Devershi Pallavi Bhatt, Linesh Raja

Agris on-line Papers in Economics and Informatics · 30.06.2026 · 18 (2) · 33-45

DOI: 10.7160/aol.2026.180203 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Agris on-line Papers in Economics and Informatics, online erschienen am 30.06.2026. Verfasst von Amritpal Kaur und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This research presents a smart irrigation system that integrates Internet of Things (IoT) and machine learning (ML) to optimize water usage in agriculture. The system consists of a wireless sensor network that continuously monitors real-time environmental parameters such as soil moisture, temperature, humidity, wind speed, and rainfall. A Node-MCU microcontroller processes sensor data and transmits it to the Thing-Speak cloud for predictive analysis. The system follows a structured irrigation scheduling method, dynamically adjusting water distribution based on sensor feedback and environmental conditions. The proposed irrigation framework integrates an inverted U-shaped structure with a T-shaped hybrid irrigation system, enabling efficient water management through solenoid valves and sub-pipelines. This system, previously developed for sprinkler irrigation, was evaluated using machine learning models to assess its performance based on soil moisture and temperature parameters. In the present study, several machine learning algorithms, including Decision Tree, XG-Boost, Gradient Boosting, and Random Forest, were employed to predict irrigation requirements. The models consider multiple factors, such as soil moisture, rainfall, wind speed, and water availability, to forecast future irrigation demands, thereby facilitating optimal water utilization. Gradient Boosting achieved the highest accuracy (98.38%) and the lowest RMSE (0.1272), while Decision Tree and XG-Boost also performed strongly, with accuracy of 98.24% each. For controlling and monitoring the developed system, an android-based mobile application developed, allowing farmers to monitor and control irrigation remotely. The results demonstrate significant improvements in water conservation, reduced manual intervention, and enhanced crop yield. Future work will focus on refining predictive models, integrating additional environmental factors, and expanding system capabilities for broader adoption in precision agriculture.

Zitieren

APA

Kaur, A., Bhatt, D. P., & Raja, L. (2026). Optimization of Water Use in Precision Agriculture Through IoT-Enabled Multi-Sensor Fusion and Machine Learning-Based Smart Irrigation Scheduling. Agris on-line Papers in Economics and Informatics, 18(2), 33-45. https://doi.org/10.7160/aol.2026.180203

Vancouver

Kaur A, Bhatt DP, Raja L. Optimization of Water Use in Precision Agriculture Through IoT-Enabled Multi-Sensor Fusion and Machine Learning-Based Smart Irrigation Scheduling. Agris on-line Papers in Economics and Informatics. 2026;18(2):33-45. doi:10.7160/aol.2026.180203

BibTeX
@article{Kaur2026,
  author = {Kaur, Amritpal and Bhatt, Devershi Pallavi and Raja, Linesh},
  title = {Optimization of Water Use in Precision Agriculture Through IoT-Enabled Multi-Sensor Fusion and Machine Learning-Based Smart Irrigation Scheduling},
  journal = {Agris on-line Papers in Economics and Informatics},
  year = {2026},
  volume = {18},
  number = {2},
  pages = {33--45},
  doi = {10.7160/aol.2026.180203}
}
Kostenlos starten →