Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

RareAgriDetectAI a generative deep learning framework using RareSimGAN for early detection and simulation of rare

G Ramadevi¹, Resham Raj Shivwanshi², Rajkumar Kalimuthu²

¹School of Technology, Woxsen University, Hyderabad, India. ramadv21@gmail.com.

Scientific Reports

|July 13, 2026

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

A hybrid AI method for lung cancer classification using explainable AI techniques.

Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)·2025

Same author

Quantum-enhanced hybrid feature engineering in thoracic CT image analysis for state-of-the-art nodule classification: an advanced lung cancer assessment.

Biomedical physics & engineering express·2024

Same author

Hyperparameter optimization and development of an advanced CNN-based technique for lung nodule assessment.

Physics in medicine and biology·2023

Same author

Analysis of coal ash samples from thermal power plants of India for their gallium content using NAA and EDXRF techniques.

Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine·2022

Same author

Single electroconvulsive shock and dopamine autoreceptors.

Indian journal of psychiatry·2011

Same author

Prostaglandins can modify gamma-radiation and chemical induced cytotoxicity and genetic damage in vitro and in vivo.

Prostaglandins·1989

RareAgriDetectAI enhances crop disease identification using synthetic data generation for rare diseases, significantly improving detection accuracy and enabling earlier intervention in precision agriculture.

Area of Science:

Agricultural Science
Computer Science
Artificial Intelligence

Background:

Timely crop disease identification is crucial for sustainable agriculture.
Deep learning models struggle with rare plant diseases due to data imbalance.
Existing generative methods lack focus on early disease stages or progression control.

Purpose of the Study:

To develop a generative deep learning framework, RareAgriDetectAI, for synthesizing rare crop disease images.
To improve the classification performance of rare plant diseases in precision agriculture.
To enable visualization of disease progression and early detection.

Main Methods:

Proposed RareSimGAN, a generative framework for synthesizing rare disease images.
Implemented a latent traversal mechanism to visualize disease progression.

Keywords:

Generative deep learning Plant disease classification Precision agriculture Rare disease detection Synthetic data augmentation

Related Experiment Videos

Augmented a ResNet50 classification pipeline with synthetic rare disease samples.

Utilized SSIM, Inception Score, and FID for generative quality validation.

Main Results:

Achieved a recall increase from 0.42 to 0.81 for the rare ToLCNDV class.
Maintained stable performance on common disease classes.
Demonstrated improved feature diversity for earlier disease recognition.
Identified an optimal augmentation threshold through ablation studies.

Conclusions:

RareAgriDetectAI offers a data-efficient solution for rare plant disease detection.
The framework improves classification robustness and enables proactive crop health monitoring.
RareAgriDetectAI supports reliable and interpretable deep learning applications in agriculture.