Leveraging IoT-Enabled Sensor Networks and Machine Learning for Early Detection and Management of Wheat Rust

¹ Department of computers Techniques engineering, College of technical engineering, The Islamic University, Najaf, NajafIraq The Islamic University of Al Diwaniyah, Al Diwaniyah, Iraq The Islamic University of Babylon, Babylon, Iraq
² College of Islamic Science, Ahl Al Bayt University, Karbala, Iraq
³ Department of CSE, GRIET, Hyderabad, Telangana, India

^* Corresponding author: Maiser.monther@iunajaf.edu.iq

Abstract

The early discovery and qualification of wheat corrosion, an upsetting mycological disease, and heart-rending wheat crops, are dangerous for guaranteeing agricultural efficiency and food safety. This education discovers the incorporation of IoT-enabled sensor systems and machine learning methods to statement the encounters accompanying with wheat corrosion management. Applying a wide-ranging sensor complex controlled across farming pitches, the organization accumulates immediate data on recyclable conditions and crop strength boundaries, including temperature, moisture, soil dampness, and spectral reflectance. Progressive remote sensing technologies, such as the Normalized Difference Vegetation Index (NDVI) and Leaf Area Index (LAI), are active in displaying plant health and recognizing primary symbols of disease. To augment exposure accuracy, the study integrates data fusion procedures that assimilate evidence from numerous sensors, cultivating the dependability of disease documentation. Machine learning demonstrations, counting Convolutional Neural Networks (CNNs), and Support Vector Machines (SVMs), are functional to analyze sensor and copy data for accurate recognition and organization of wheat rust symptoms. ARIMA representations are used to predict disease tendencies and rust chances created on antique data, as long as appreciated understanding of protective procedures. The scheme accomplished a discovery exactness of 92% for wheat rust indications using Convolutional Neural Networks (CNNs) and Support Vector Machines (SVMs). ARIMA (Autoregressive Integrated Moving Average) models forecasted rust prospects with a typical fault border of ±5%>, empowering directed involvements that condensed disease frequency by 20% and augmented crop harvest by 15%). These consequences highlight the efficiency of the projected system in cultivating disease management and crop strength.