The AutoAero emerges as a pioneering solution to the multifaceted challenges confronting modern agriculture, offering a transformative approach to address inefficiencies, labor intensiveness, and environmental degradation inherent in conventional farming practices. Successfully executing stable takeoff and landing procedures, the drone’s autonomous flight operations lay a robust foundation for its practical application in agricultural settings. Integrated machine learning models, including EfficientNetB3 for disease detection, EfficientNetV2- L for pest detection and ResNet152V2 for unwanted animal detection showcase impressive accuracies of 95.24 percentage, 87.90 percentage and 93.76 percentage respectively, with low losses on test datasets. These models exhibit a high proficiency in generalization of unseen data, underscoring their reliability in real world scenarios. The AutoAero’s functionalities encompass critical tasks in wheat crop farming operations from pest, disease and animal detection to crop harvest detection, field nutrition management and precision spraying. Results demonstrate the drone’s capacity to minimize human intervention, reduce labor costs, and optimize resource usage, thereby contributing to enhanced agricultural productivity and sustainability. Despite encountering technical challenges in construction, sensor integration, and machine learning algorithm development, the comprehensive plan outlined in this study serves as a strategic roadmap towards refining the AutoAero and realizing its potential as a powerful and sustainable tool for modern agriculture.

Index Terms- AutoAero, Machine Learning Models