ArticleScientific reports2025
Attention guided convolutional neural network with explainable AI for papaya leaf disease detection in edge and drone agricultural systems.
Article in Scientific reports, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 1 paper.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
1 citing paper in PubMed.
- Agrimind intelligent deep learning framework for accurate soil fertility prediction.Scientific reports · 2026Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
9 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Existing disease discovery in papaya leaves is most significant in achieving yield and profitability stability in the tropics but has proven difficult in the presence of deficiencies in manual exploration and tailored crop models in crop-AI systems. Therefore, this study introduces PapayaNet, a lightweight attention-guided convolutional network specifically structured for the automated classification of six papaya leaf states, including major diseases and healthy leaves. For real-world deployment in scarce-resource farming contexts, PapayaNet adopts batch norm and hierarchical attention steps in five convolution stages and accelerates both computational celerity and discriminability. Trained on 6618 manually annotated orchard images sourced from orchards in Bangladesh at a very high resolution, it has a 98.79% classification accuracy, all of which was realized using 483,926 parameters and an average infer time of 0.01 s, which is significantly better when evaluated using EfficientNetB6, DenseNet121, and VGG16. XAI methods, including Grad-CAM and LIME, showed model decisions towards the biologically informative parts of the leaf, thus boosting interpretability and user confidence. Systematic ablation analysis also confirmed the importance of distributed attention in ensuring robust generalization towards visually similar disease classes. An in-browser diagnostic portal deployed using Gradio provides intra-browser predictive deployment and interpretability overlay in real time, thus inviting field practicability. Given its low-latency inference and minimal computational footprint, PapayaNet is well-suited for integration into edge devices and drone platforms, offering a scalable solution for real-time in-situ crop health monitoring. This study advances the field of precision agriculture by delivering a crop-specialized, explainable, and deployable AI system for sustainable management of papaya diseases.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.