Recent Advances in Pest Identification and Control in Smart Agriculture Using Scalable Quantum Convolutional Neural Networks and Wireless Sensor Networks: A Systematic Review

Abstract

Pest infestation is a major challenge in agriculture, causing significant crop losses and threatening global food security. Traditional pest identification methods are labor-intensive, time-consuming, and often inaccurate, necessitating the development of intelligent and automated solutions. This paper presents a systematic review of recent advances in pest identification and control using scalable Quantum Convolutional Neural Networks (QCNN) integrated with Wireless Sensor Networks (WSNs). WSNs enable real-time environmental monitoring, while QCNN and deep learning techniques enhance pest detection accuracy through advanced feature extraction and classification. Recent studies demonstrate that deep learning models such as CNN and hybrid architectures achieve high accuracy in pest detection, often exceeding 90%, while IoT-enabled systems facilitate real-time monitoring and decision-making. Quantum machine learning approaches further improve performance by efficiently processing high-dimensional agricultural data. This review covers research, highlighting key methodologies, comparative performance, and emerging trends. The findings indicate that hybrid AI and quantum-based approaches outperform traditional methods in terms of accuracy, scalability, and efficiency. However, challenges such as computational complexity, energy consumption, and deployment constraints remain. Future research should focus on lightweight quantum models and edge-based intelligent systems for sustainable smart agriculture.