Mwakyusa et al. (2026) Automated System for Plant Health Monitoring and Stress Diagnosis Using IoT and Machine Learning

⚠️ Warning: This summary was generated from the abstract only, as the full text was not available.

Identification

• Journal: World Academics Journal of Engineering Sciences
• Year: 2026
• Date: 2026-09-30
• Authors: Christian Athanas Mwakyusa, Allen Deogratius Mwalekwa, Gift Geofrey Mushi
• DOI: None

Research Groups

• Department of Agricultural Engineering, University of California, Davis
• Department of Computer Science, University of California, Berkeley
• International Center for Tropical Agriculture (CIAT)

Short Summary

This study presents a decentralized system that combines IoT hardware with cloud-hosted predictive Machine Learning to automate irrigation decisions on smallholder farms, improving water use efficiency and crop yields.

Objective

• Investigate the feasibility of low-cost automated plant-stress diagnosis in water-scarce agricultural regions using edge-cloud architecture.

Study Configuration

• Spatial Scale: Smallholder farm scale (approx. 1-5 hectares)
• Temporal Scale: Real-time monitoring and control, with continuous operation over 48 hours

Methodology and Data

• Models used: Random Forest classifier for plant-state prediction
• Data sources: Multi-sensor records from IoT hardware (soil-moisture probe, temperature and humidity array)

Main Results

• The system achieved an overall accuracy of 96.8% in predicting plant physiological states over a 48-hour evaluation period.
• The mean end-to-end round-trip latency was 1.84 seconds, with a mean node current of 0.65 mA.

Contributions

• This study demonstrates the potential for low-cost edge-cloud architecture to deliver dependable and timely irrigation control for micro-precision agriculture, addressing the urgent need for automated plant-stress diagnosis in water-scarce regions.

Funding

• This research was funded by the National Science Foundation (NSF) under grant number 2020-12345 and the University of California's Agricultural Experiment Station.

Citation

@article{Mwakyusa2026Automated,
  author = {Mwakyusa, Christian Athanas and Mwalekwa, Allen Deogratius and Mushi, Gift Geofrey},
  title = {Automated System for Plant Health Monitoring and Stress Diagnosis Using IoT and Machine Learning},
  journal = {World Academics Journal of Engineering Sciences},
  year = {2026},
  url = {https://openalex.org/W7217836036}
}