Detection and Mitigation of Fruit Leaf Plant Diseases Using IoT with Machine Learning Techniques

Healthy crops can be effectively grown through effective proactive practices in monitoring and managing plant diseases. Good plans can slow the spread of plant pathogens and even increase crop production. Moribund leaves on the fruits have a negative impact on crop integrity, thus undermining product quality. Carrying out early warnings of ills is in itself a difficult task. Plant pathogens are found to be highly diverse and intricate. The aim of the present work is the creation of an integrated system based on the combination of Internet-of-Things (IoT) sensors and machine learning methods to identify and prevent fruit leaf diseases. The research observes the symptoms, wilting and chlorosis, which may be used to determine the exact disease that is afflicting an Avocado plant. Image preprocessing can enhance the accuracy of the diagnosis by enhancing the quality of raw image data to emphasize the features that correspond with the disease and to reduce noise level; this is achieved with image preprocessing algorithms such as region-specific Adaptive Filters. The Hybrid Spectral “Thermal Sensor Fusion with Adaptive Thresholding” represents a new approach to the synthesis of thermal and spectral data. This leads to the earlier identification and treatment of diseases. The combination of Hybrid Vision Transformers and Convoluted Neural Networks also enhances the diagnosis of the avocado disease in order to detect those salient nuances and give a more global picture of the situation to quickly intervene. The study indicates that a combination of AI, machine learning, and remote sensing can provide more accurate and faster solutions to detect and control plant pathogens.