Enhancing Crop Yield Prediction Using IoT-Based Soil Moisture and Nutrient Sensors

Strategic Insights -

Researchers at Islamic University have developed an IoT-based crop yield prediction system that integrates advanced sensing technologies, communication protocols, machine learning algorithms, and real-time monitoring to optimize crop production. The system measures essential soil nutrients and climatic conditions, allowing for data-driven decision-making and efficient resource management. By analyzing the data, the system generates actionable insights, such as optimal irrigation and fertilization schedules, which are communicated to farmers in real-time. The study found that the system achieved high accuracy in yield predictions, with confidence intervals close to actual yields.

Key Takeaways:

  • The IoT-based crop yield prediction system integrates advanced sensing technologies, communication protocols, machine learning algorithms, and real-time monitoring to optimize crop production.
  • The system measures essential soil nutrients (NPK), soil moisture, and climatic conditions to provide accurate crop yield predictions.
  • The Random Forest model takes the purified data and predicts crop yield based on inputs in historical and real-time, with patterns revealed that are complex and can make accurate estimated yield predictions.
  • Actionable insights, such as optimal irrigation and fertilization schedules, are generated by the system and communicated to farmers in real-time via mobile devices.
  • The system had achieved high accuracy in yield predictions matching the actual yields, with confidence intervals close to those yields.
  • Critical factors, such as nutrient levels and soil moisture, were found to influence yields greatly, with the application of these factors helping in efficient resource management and sustainable agricultural practices.
  • The system is capable of running continuously and collecting, processing, and analyzing data at specific intervals for ongoing optimization.
  • The study was conducted by researchers from Islamic University, Al Diwaniyah, Iraq, and was published in the SHS Web of Conferences.

Statistics:

  • The IoT-based crop yield prediction system achieved high accuracy in yield predictions, with accuracy rates not specified.
  • Confidence intervals provided by the system were close to actual yields, but specific percentages were not mentioned.
  • The system measures essential soil nutrients (NPK), soil moisture, and climatic conditions.
  • The Random Forest model takes purified data and predicts crop yield based on inputs in historical and real-time.
  • The system generates actionable insights, such as optimal irrigation and fertilization schedules, which are communicated to farmers in real-time via mobile devices.

Sources:

  • Enhancing Crop Yield Prediction Using IoT-Based Soil Moisture and Nutrient Sensors. SHS Web of Conferences, 2025,216():01029.
  • SHS Web of Conferences - http://www.shs-conferences.org
  • EDP Sciences - publisher for SHS Web of Conferences
  • https://doi-org.sdpl.idm.oclc.org/10.1051/shsconf/202521601029 - free version of the journal article
  • NewsRx. Islamic University Researchers Publish New Studies and Findings in the Area of Social Science (Enhancing Crop Yield Prediction Using IoT-Based Soil Moisture and Nutrient Sensors). Science Letter. July 18, 2025; p 223.