HFA-Net: Explainable Multi-Scale Deep Learning Framework for Illumination-Invariant Plant Disease Diagnosis in Precision Agriculture
Sensors · 2026
DOI: 10.3390/s26072067 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2026. Verfasst von Muhammad Hassaan Ashraf und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, COMSATS University, Islamabad 45550, Pakistan. Hauptthemen laut MEDLINE: Deep Learning, Agriculture, Plant Diseases. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: MSIT and the National Research Foundation (NRF) of South Korea, MSIT https://ror.org/01wpjm123, National Research Foundation (NRF) of South Korea.
Abstract (Originalsprache)
Robust plant disease detection in real-world agricultural environments remains challenging due to dynamic environmental conditions. Accurate and reliable disease identification is essential for precision agriculture and effective crop management. Although computer vision and Artificial Intelligence (AI) have shown promising results in controlled settings, their performance often drops under lesion scale variability, inter- and intra-class similarity among diseases, class imbalance, and illumination fluctuations. To overcome these challenges, we propose a Heterogeneous Feature Aggregation Network (HFA-Net) that brings together architectural improvements, illumination-aware preprocessing, and training-level enhancements into a single cohesive framework. To extract richer and more discriminative features from the early layers of the network, HFA-Net introduces a multi-scale, multi-level feature aggregation stem. The Reduction-Expansion (RE) mechanism helps preserve important lesion details while adapting to variations in scale. Considering real agricultural environments, an Illumination-Adaptive Contrast Enhancement (IACE) preprocessing pipeline is designed to address illumination variability in real agricultural environments. Experimental results show that HFA-Net achieves 96.03% accuracy under normal conditions and maintains strong performance under challenging lighting scenarios, achieving 92.95% and 93.07% accuracy in extremely dark and bright environments, respectively. Furthermore, quantitative explainability analysis using perturbation-based metrics demonstrates that the model’s predictions are not only accurate but also faithful to disease-relevant regions. Finally, Grad-CAM-based visual explanations confirm that the model’s predictions are driven by disease-specific regions, enhancing interpretability and practical reliability.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Science, COMSATS University, Islamabad 45550, Pakistan.
- Department of Computer Science, Faculty of Arts and Sciences, Edge Hill University, Ormskirk L39 4QP, UK.
- Department of Optical Engineering, Sejong University, Seoul 05006, Republic of Korea.
ORCID-Profile: Muhammad Hassaan Ashraf
Förderung
- MSIT and the National Research Foundation (NRF) of South Korea
- MSIT https://ror.org/01wpjm123
- National Research Foundation (NRF) of South Korea
Zitieren
APA
Ashraf, M. H., Jabeen, F., Waqar, M., & Kim, A. (2026). HFA-Net: Explainable Multi-Scale Deep Learning Framework for Illumination-Invariant Plant Disease Diagnosis in Precision Agriculture. Sensors. https://doi.org/10.3390/s26072067
Vancouver
Ashraf MH, Jabeen F, Waqar M, Kim A. HFA-Net: Explainable Multi-Scale Deep Learning Framework for Illumination-Invariant Plant Disease Diagnosis in Precision Agriculture. Sensors. 2026. doi:10.3390/s26072067
BibTeX
@article{Ashraf2026,
author = {Ashraf, Muhammad Hassaan and Jabeen, Farhana and Waqar, Muhammad and Kim, Ajung},
title = {HFA-Net: Explainable Multi-Scale Deep Learning Framework for Illumination-Invariant Plant Disease Diagnosis in Precision Agriculture},
journal = {Sensors},
year = {2026},
doi = {10.3390/s26072067}
}
EUVIMED