A review on automated plant disease detection: motivation, limitations, challenges, and recent advancements for future research

Developing countries face significant challenges in healthcare, education, technological advancement, and farming, with agriculture playing an important role in economic growth. Ensuring adequate food production is essential for citizens' survival and economic stability. Early detection of plant disease is critical for increasing agricultural yields through efficient control methods. As a result, autonomous plant disease detection models are vital for reducing labor-intensive tasks. Machine learning and deep learning models have recently been introduced to automate disease identification in plants by detecting symptoms on their leaves. This study reviews various publications that use machine learning and deep learning approaches to detect plant and crop diseases. This review provides (i) an automated plant disease detection system, (ii) an automated wheat leaf rust detection system, (iii) publicly available plant disease datasets, (iv) an overview of machine learning and deep learning methods for plant disease detection, (v) remote sensing technology in plant disease detection, and (vi) future trends and research directions. This review is contributing to the literature by establishing a solid foundation for the development of more valuable machine learning and deep learning methods for plant disease detection. This review study critically examines various problems, including model generalization, dataset diversity, and computing factors, to assist prospective researchers in developing robust and scalable solutions. Additionally, this review presented a detailed overview of the limitations, challenges, and recent advancements in plant disease detection, especially in wheat leaf rust detection and remote sensing technology. Furthermore, current challenges and future directions in wheat disease detection are thoroughly discussed. This study provides a fundamental guide for the development of AI-driven algorithms, providing strategies to enhance production, profitability, and sustainability against climate change and population growth.