Detection and Management of Plant Disease Using Artificial Intelligence and Machine Learning Applications: A Review

Abstract

The detection and management of plant disease using Artificial intelligence and machine learning applications. Artificial intelligence (AI) and machine learning (ML) have emerged as transformative technologies in plant disease detection and management, offering highly accurate, scalable, and real-time diagnostic solutions. Traditional disease detection methods, reliant on manual scouting and laboratory-based assays, are time-intensive, prone to human error, and often fail to detect early-stage infections. AI-driven approaches, particularly deep learning models such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and vision transformers, have significantly improved disease classification accuracy, surpassing 95% in multiple studies. The integration of AI with the Internet of Things (IoT) enables real-time disease monitoring through smart sensors, drone-based imaging, and cloud computing, enhancing large-scale agricultural surveillance. Big data analytics play a crucial role in AI-driven disease management, utilizing satellite imagery, hyperspectral data, and field-based mobile applications to detect infections before symptoms become visible. Predictive analytics models, powered by AI, analyse environmental and pathogen-related data to forecast disease outbreaks, supporting proactive decision-making in precision agriculture. Despite significant advancements, challenges such as limited access to large, annotated datasets, computational resource constraints, and model generalization issues across diverse crops and climatic conditions persist. Ethical concerns related to data privacy and the adoption of AI technologies among farmers further hinder widespread implementation. Blockchain technology has been proposed for secure and transparent disease data sharing, while edge computing solutions aim to reduce latency in AI-driven disease detection systems. Autonomous AI-powered agricultural robots equipped with deep learning models and multispectral sensors are being developed for real-time disease monitoring and targeted treatment. Future research must focus on optimizing AI algorithms for large-scale agricultural deployment, integrating AI-driven genomic selection for disease-resistant crop breeding, and leveraging emerging technologies such as quantum computing and synthetic biology to enhance plant disease management and global food security. The quantum computing and artificial intelligence combinedly offers ground breaking capabilities in real-time data processing, predictive analytics, and optimization, enabling high-precision agricultural strategies that can transform crop management, climate adaptation, and global food distribution.

Plant phenotyping relevance

植物病害の画像・センサー観測とAIによる症状・感染状態の推定を扱う方法論レビューであり、植物フェノタイピング手法が中心です。

Code and data availability

公開論文であることは確認できましたが、現在の公式API・許可済み取得経路では本文を自動取得できませんでした。

No evidence-backed public reproduction asset is currently recorded.