UAV-based real-time detection of corn earworm using EfficientNet and machine learning.

Early detection of corn earworm (Helicoverpa zea) is crucial for subsiding corn crop losses and make sure supportable agricultural productivity. Traditional monitoring methods, composed of manual field inspections and pheromone traps, are often time-consuming, labor-intensive, and prone to hindered detection. This study develops an unmanned aerial vehicle (UAV)-based, real-time detection system for corn earworm infestations using progressive artificial intelligence techniques. Multispectral and thermal images were collected from three corn fields throughout the 2024 growing season, including numerous pest life stages. The dataset includes 2,000 high-resolution images, with metadata as well as geographical coordinates, collection date, and pest stage annotations, authorized by entomological experts. Image preprocessing, as well as normalization, augmentation, and segmentation, was smeared to develop data quality and model generalization. EfficientNet, a convolutional neural network, was engaged for feature extraction, and its outputs were classified using a hybrid method combining Random Forest and Support Vector Machine algorithms to improve detection accuracy and robustness. The system succeeded 90% classification accuracy, with inference times suitable for real-time field application. Field trials recognized the practical applicability of the method under variable ecological conditions. This research shows that fitting UAV imaging with AI-based models can be responsible for suitable, accurate detection of corn earworm, assisting proactive pest management decisions. The methodology can be adjusted to other pest species and crop systems, posturing a scalable solution for precision agriculture and backing sustainable crop protection practices. These findings highlight the potential of connecting AI, remote sensing, and entomological validation for modern, data-driven pest management.