Enhanced paddy leaf disease detection using novel dual me…

Scientific Reports – Enhanced paddy leaf disease detection using novel dual metaheuristic loss functions in generative adversarial networks with identity block preservation for thermal image…

This paper presents a novel dual metaheuristic loss function framework integrated within Generative Adversarial Networks (GANs) for enhanced thermal image augmentation, specifically designed to improve paddy leaf disease detection through intelligent data quality enhancement and diversity generation. The proposed methodology revolutionizes traditional GAN training by replacing conventional loss functions with two bio-inspired metaheuristic algorithms: the Chaoborus algorithm, which serves as an innovative generator loss function implementing intelligent missing pixel imputation through phantom midge larvae hunting behavior simulation, and the Australian Crayfish algorithm, which functions as an advanced discriminator loss function optimizing adaptive 8-pixel connectivity through foraging and territorial behavior modeling.

The framework incorporates strategically positioned identity blocks to preserve critical thermal signatures during adversarial training, ensuring disease-specific thermal patterns remain intact throughout the image enhancement process while maintaining diagnostic integrity. The proposed dual metaheuristic GAN achieves superior image generation quality with 31.47 ± 0.52 dB Peak Signal-to-Noise Ratio (PSNR) and 0.923 ± 0.008 Structural Similarity Index Measure (SSIM), representing significant improvements over state-of-the-art methods including StyleGAN2 (26.89 dB PSNR), Progressive GAN (27.34 dB PSNR), and BigGAN (28.12 dB PSNR).

Disease classification performance evaluation across four distinct neural network architectures (ResNet-50, EfficientNet-B7, Vision Transformer, and DenseNet-201) reveals substantial accuracy improvements, with the Vision Transformer achieving 97.89 ± 0.63% accuracy using the proposed augmentation compared to 83.45 ± 1.76% on original datasets and 87.23 ± 1.54% with standard augmentation techniques.

Statistical significance analysis confirms the robustness of improvements with p-values less than 0.001 for all comparative metrics and Cohen’s d effect sizes exceeding 1.2, indicating large practical significance. Rigorous tenfold cross-validation yields consistent performance with 96.85% mean accuracy and low standard deviation (0.674%), while Leave-One-Out Cross-Validation demonstrates minimal bias (< 0.0012) and low variance (< 0.0055).

Generalization studies across five different datasets show robust transferability with direct transfer accuracies ranging from 84.12% to 91.45%, improving to 89.67–95.89% with minimal fine-tuning. Environmental robustness evaluation reveals excellent stability under varying temperature (15–35 °C), humidity (40–80%), and temporal conditions, with performance drops limited to 6.07% under extreme conditions.

Comprehensive ablation studies validate the synergistic contribution of each framework component, with individual algorithms providing 5.68 dB and 3.76 dB PSNR improvements respectively, while their combination with identity blocks achieves the full 31.47 dB performance. Computational efficiency analysis demonstrates practical viability with 45.2 ± 2.8 ms inference time for image generation and 1.41 × speedup over baseline methods while maintaining 9.8 GB memory efficiency.

Real-world field deployment across four geographic locations in India (Punjab, Tamil Nadu, West Bengal, and Odisha) over 2.75 months processing 44,860 images achieves 94.65% average accuracy with 3.12% false positive and 2.24% false negative rates. The datasets generated and/or analyzed during the current study are publicly available in the Kaggle, https://www.kaggle.com/datasets/sujaradha/thermal-images-diseased-healthy-leaves-paddy and https://www.kaggle.com/datasets/vbookshelf/rice-leaf-diseases.

Maheswaran, S. et al. Detection and Classification of Paddy Leaf Diseases Using Deep Learning (CNN). In Computer, Communication, and Signal Processing. ICCCSP 2022. IFIP Advances in Information and Communication Technology Vol. 651 (eds Neuhold, E. J. et al.) (Springer, 2022). https://doi.org/10.1007/978-3-031-11633-9_6. Kaur, A., Guleria, K. & Trivedi, N. K. A deep learning-based model for biotic rice leaf disease detection.

Multimed. Tools Appl. 83, 83583–83609. https://doi.org/10.1007/s11042-024-18730-x (2024). Ramadan, S. T. Y. et al. Image-based rice leaf disease detection using CNN and generative adversarial network. Neural Comput. Applic. 37, 439–456. https://doi.org/10.1007/s00521-024-10572-w (2025). Rajpoot, V., Tiwari, A. & Jalal, A. S. Automatic early detection of rice leaf diseases using hybrid deep learning and machine learning methods.

Multimed. Tools Appl. 82, 36091–36117. https://doi.org/10.1007/s11042-023-14969-y (2023). Manoranjitham, T. An artificial intelligence ensemble model for paddy leaf disease diagnosis utilizing deep transfer learning. Multimed. Tools Appl. 83, 79533–79558. https://doi.org/10.1007/s11042-024-19987-y (2024). Trinh, D. C. et al. Alpha-EIOU-YOLOv8: An improved algorithm for rice leaf disease detection.

AgriEngineering 6(1), 302–317. https://doi.org/10.3390/agriengineering6010018 (2024). Li, R. et al. Predicting rice diseases using advanced technologies at different scales: Present status and future perspectives. aBIOTECH 4(4), 289–314 (2023). Seelwal, P. et al. A systematic review of deep learning applications for rice disease diagnosis: Current trends and future directions. Front. Comput. Sci.

6, 1452961 (2024). Simhadri, C. G. & Kondaveeti, H. K. Advanced diagnosis of common rice leaf diseases using KERTL-BME ensemble approach. J. Real-Time Image Proc. 21, 144. https://doi.org/10.1007/s11554-024-01522-9 (2024). Chen, X., Zhang, Y., Wang, L. & Li, M. Convolutional neural network in rice disease recognition: Accuracy, speed and lightweight. Front. Plant Sci. 14, 1269371 (2023). Singh, A., Kumar, P.

& Sharma, R. Application of generative adversarial networks in image, face reconstruction and medical imaging: Challenges and the current progress. Comput. Methods Biomech. Biomed. Eng. Imaging Visual. 12(4), 512–535 (2024). Khan, A. H., Li, S. & Wang, X. Nature-inspired metaheuristic optimization algorithms 2024. Biomimetics 9(7), 425 (2024). Mohamed, A., Khalil, H. & Ibrahim, M. Flood algorithm: A novel metaheuristic algorithm for optimization problems.

PeerJ Comput. Sci. 10, e2278 (2024). Khalifa, N. E. M., Taha, M. H. N., Khalil, H. M. & Malik, M. H. ONDL: An optimized Neutrosophic Deep Learning model for classifying waste for sustainability. PLoS ONE 19(11), e0313327. https://doi.org/10.1371/journal.pone.0313327 (2024). Jia, H., Rao, H., Wen, C. & Mirjalili, S. Crayfish optimization algorithm. Artif. Intell. Rev. 56(2), 1919–1979 (2023). Wu, D.

et al. Modified crayfish optimization algorithm for solving multiple engineering application problems. Artif. Intell. Rev. 57(5), 112 (2024). Zhang, L., Li, X., Wang, Y., Chen, M. & Liu, S. Adaptive dynamic crayfish algorithm with multi-enhanced strategy for global high-dimensional optimization and real-engineering problems. Sci. Rep. 15(1), 457 (2025). Chen, Y., Wu, X., Li, H., Zhang, P. & Wang, J.

An improved multi-strategy crayfish optimization algorithm for solving numerical optimization problems. BMC Bioinform. 25, 201 (2024). Patel, R., Kumar, S. & Singh, V. Applications of hybrid metaheuristic algorithms for image processing. Stud. Computat. Intell. 890, 1–25 (2020). Goodfellow, I. et al. Generative adversarial nets. Adv. Neural. Inf. Process. Syst. 27, 2672–2680 (2014). Radford, A., Metz, L., & Chintala, S.

Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv:1511.06434 (2015). Arjovsky, M., Chintala, S., & Bottou, L. Wasserstein generative adversarial networks. International Conference on Machine Learning 214–223 (2017). Mao, X., Li, Q., Xie, H., Lau, R. Y., Wang, Z., & Paul Smolley, S. Least squares generative adversarial networks. In: Proc. IEEE International Conference on Computer Vision 2794–2802 (2017).

Karras, T., Aila, T., Laine, S., & Lehtinen, J. Progressive growing of GANs for improved quality, stability, and variation. arXiv:1710.10196 (2017). Karras, T., Laine, S., & Aila, T. A style-based generator architecture for generative adversarial networks. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition 4401–4410 (2019). Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., & Aila, T.

Analyzing and improving the image quality of StyleGAN. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition 8110–8119 (2020). Brock, A., Donahue, J., & Simonyan, K. Large scale GAN training for high fidelity natural image synthesis. arXiv:1809.11096 (2018). Zhu, J. Y., Park, T., Isola, P., & Efros, A. A. Unpaired image-to-image translation using cycle-consistent adversarial networks.

In: Proc. IEEE International Conference on Computer Vision 2223–2232 (2017). Isola, P., Zhu, J. Y., Zhou, T., & Efros, A. A. Image-to-image translation with conditional adversarial networks. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition 1125–1134 (2017). Mirza, M., & Osindero, S. Conditional generative adversarial nets. arXiv:1411.1784 (2014). Mahmoud, G. M. et al. A novel 8-connected pixel identity GAN with neutrosophic (ECP-IGANN) for missing imputation.

Sci. Rep. 14, 23936. https://doi.org/10.1038/s41598-024-73976-7 (2024). Mahmoud, G. M. et al. Novel GSIP: GAN-based sperm-inspired pixel imputation for robust energy image reconstruction. Sci. Rep. 15, 1102. https://doi.org/10.1038/s41598-024-82242-9 (2025). Marie, H. S. & Elbaz, M. MCI-GAN: A novel GAN with identity blocks inspired by menstrual cycle behavior for missing pixel imputation. Neural Comput.

Applic. 37, 9669–9703. https://doi.org/10.1007/s00521-025-11059-y (2025). Elbaz, M. et al. A dual GAN with identity blocks and pancreas-inspired loss for renewable energy optimization. Sci. Rep. 15, 16635. https://doi.org/10.1038/s41598-025-00600-7 (2025). Mahmoud, G. M. et al. Menstrual cycle inspired latent diffusion model for image augmentation in energy production. Sci. Rep. 15, 16749. https://doi.org/10.1038/s41598-025-99088-4 (2025).

Marie, H. S. et al. Novel dual gland GAN architecture improves human protein localization classification using salivary and pituitary gland inspired loss functions. Sci. Rep. 15, 28055. https://doi.org/10.1038/s41598-025-11254-w (2025). Marie, H. S. et al. DentoMorph-LDMs: diffusion models based on novel adaptive 8-connected gum tissue and deciduous teeth loss for dental image augmentation. Sci. Rep.

15, 27268. https://doi.org/10.1038/s41598-025-11955-2 (2025). Open access funding provided by The Science, Technology & Innovation Funding Authority (STDF) in cooperation with The Egyptian Knowledge Bank (EKB). H. M. Khalil conceptualized the methodology, designed the dual metaheuristic loss functions, and conducted experiments. A. A. Elsonbaty performed data preprocessing and thermal image analysis.

A. Elrefaiy developed the GAN architecture with identity block preservation. M. Elbaz supervised the research, validated results, and revised the manuscript. All authors reviewed and approved the final version. Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.

The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.

To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. Khalil, H.M., Elrefaiy, A., Elbaz, M. et al. Enhanced paddy leaf disease detection using novel dual metaheuristic loss functions in generative adversarial networks with identity block preservation for thermal image augmentation. Sci Rep (2026). https://doi.org/10.1038/s41598-026-36477-3

Summary

This report covers the latest developments in artificial intelligence. The information presented highlights key changes and updates that are relevant to those following this topic.

---