Intelligent detection for sustainable agriculture: A review of IoT-based embedded systems, cloud platforms, DL, and ML for plant disease detection

• Published in: Multimedia tools and applications Vol. 83; no. 28; pp. 70961 - 71000
• Main Authors: Morchid, Abdennabi, Marhoun, Marouane, El Alami, Rachid, Boukili, Bensalem
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.08.2024; Springer Nature B.V
• Subjects: Agriculture; Computer Communication Networks; Computer Science; Cybersecurity; Data Structures and Information Theory; Deep learning; Effectiveness; Embedded systems; Food security; Hyperspectral imaging; Internet of Things; Machine learning; Multimedia Information Systems; Plant diseases; Population density; Real time; Special Purpose and Application-Based Systems; Sustainable agriculture; Smart agriculture; Plant disease detection; Embedded systems; Sustainable agriculture; Cloud platforms; Food security; Internet of things (IoT); Machine learning (ML); Deep learning (DL)
• ISSN: 1573-7721; 1380-7501; 1573-7721
• DOI: 10.1007/s11042-024-18392-9

Plant diseases pose a significant threat to the sustainability of the environment and global food security. With an increasing population density and the growing demand for plant-based food, the need to address the ongoing plant disease pandemic has become urgent. These issues may be resolved and a more precise and effective approach for early disease detection in smart agriculture can be provided through the use of the embedded systems, Internet of Things (IoT), cloud platforms, machine learning (ML), and deep learning (DL). This paper presents a summary of current work in this field, as well as novel ideas put forth to increase the precision and effectiveness of plant disease detection. In this survey paper, we present (a) a survey on various plant diseases, (b) a method to detect plant diseases using IoT, embedded systems, and cloud platforms that receive and process data in real-time, (c) a ML pipeline for disease identification, and (d) a method to detect plant diseases using deep learning. Framework, dataset, and hyperspectral imaging with DL models for plant disease identification (e). The analysis, challenges of plant disease and pest detection using DL, ML, embedded systems,and the IoT are described in this paper. These databases: ScienceDirect, Springer, IEEE Xplore, MDPI, Hindawi, Frontiers, and others were used in this comprehensive search. Researchers, policymakers, and other stakeholders interested in smart agriculture, plant disease detection, and sustainable food security may find this resource from this study useful.