Artificial Intelligence in Pathogen Based Plant Disease Detection: Advances, Trends, and Challenges

Abstract

Plant disease outbreaks caused by fungi, bacteria,
and viruses continue to threaten crop yields, food security, and
the long-term health of agricultural systems across the globe.
Detecting these diseases early, accurately, and at scale remains a
difficult task, especially as climate patterns shift and food supply
chains stretch across continents. Conventional diagnostic methods
such as visual inspection, lab-based tests, and molecular assays
have long been the standard, yet they are often slow, expensive,
and tied to controlled laboratory settings. In recent years,
advances in artificial intelligence (AI) have begun to transform
this landscape. Modern approaches powered by convolutional
neural networks (CNNs), transformers, and multimodal AI now
take on the challenge of interpreting complex agricultural data,
whether from images, sensors, or text. This review explores the
current ecosystem of AI-driven techniques for detecting plant
diseases caused by pathogens, comparing how different methods
perform and where each one fits best. Special focus is given
to the shift from traditional image-based deep learning toward
newer frontiers such as explainable AI (XAI), graph neural
networks (GNNs), few-shot and foundation models, and fully
multimodal systems. We structure our comparison not around
accuracy rankings alone, but around what each paradigm can
and cannot do: the conditions under which it was tested, what it
requires to operate, what it reports about its own decisions, and
how close it has come to real agricultural deployment. Along the
way, the review identifies persistent challenges including dataset
over-reliance on controlled benchmarks, poor domain transfer to
real-world conditions, constraints in real-time deployment, and
the absence of standardised explainability evaluation. Drawing
from the latest research, it outlines the major gaps that still
remain and offers practical directions for future work.