Efficient IoT-Based Framework for Predicting Crop Damage in Smart Agricultural Systems

Strategic Insights -

Researchers at Kafr El-Shaikh University in Egypt have developed an efficient IoT-based framework for predicting crop damage in smart agricultural systems. The framework uses Internet of Things (IoT) sensor data and advanced machine learning and ensemble learning techniques to predict crop health status. The primary objective of the framework is to develop a reliable decision support system that can classify crops as healthy, pesticide-damaged, or affected by other stressors. The framework incorporates robust data imputation strategies using traditional machine learning methods and powerful ensemble learning models to address the challenge of missing data in real-time agricultural datasets.

Key Takeaways:

  • The proposed framework uses IoT sensor data and machine learning techniques to predict crop damage in smart agricultural systems.
  • The primary objective of the framework is to develop a reliable decision support system that can classify crops as healthy, pesticide-damaged, or affected by other stressors.
  • The framework incorporates robust data imputation strategies using traditional machine learning methods and powerful ensemble learning models.
  • The proposed approach includes the use of XGBoost, CatBoost, and LightGBM ensemble-based classifiers, which achieve high accuracy, precision, and F1-score.
  • The imputation capability of the XGBoost model is validated through low Mean Squared Error (MSE) and high R-squared value.
  • The key contributions of this innovative work include the design of a low-cost, power-efficient, and scalable crop damage prediction system.

Statistics:

  • The XGBoost model achieves an average sensitivity of 88.1%, accuracy of 89.56%, precision of 83.4%, and F1-score of 84.8%.
  • CatBoost achieves 90.50% accuracy, while LGBM reaches 90.23%.
  • The XGBoost model has a low Mean Squared Error (MSE) of 0.0213, and a high R-squared value of 0.99.
  • The framework is particularly suited for deployment in resource-constrained agricultural environments.

Sources:

  • An efficient IoT-based crop damage prediction framework in smart agricultural systems. Scientific Reports, 2025;15(1):27742.
  • Nature Portfolio (www.nature.com/; Scientific Reports - www.nature.com/srep/)
  • Scientific Reports can be contacted at: Nature Portfolio, Heidelberger Platz 3, Berlin, 14197, Germany.