Skip to main navigation menu Skip to main content Skip to site footer
Plant Science Today (PST)

Research Articles

Vol. 13 No. sp9 (2026): Recent Advances in Agriculture

Evaluation of deep learning models for optimised accuracy-emission trade-offs in the early detection of grain discolouration disease in rice

DOI
https://doi.org/10.14719/pst.13143
Submitted
10 December 2025
Published
30-10-2026

Abstract

Rice (Oryza sativa L.) constitutes a primary food source for a significant proportion of the global population and its grain quality directly influences market value and consumer acceptance. Grain discolouration (GD), largely attributable to seed-borne pathogens and occasionally to insect infestation, poses a critical challenge by compromising visual quality and reducing commercial grade. This study evaluated the performance of advanced deep learning models for automated detection and classification of discoloured rice grains, incorporating criteria related to predictive accuracy, computational requirements and environmental sustainability. Among the assessed architectures, DenseNet121 exhibited the highest accuracy (98 %), followed by MobileNet (96 %) and MobileNetV2 (92 %), each demonstrating strong precision, recall and F1 scores. In contrast, VGG19 recorded comparatively lower accuracy (84 %). Computational and energy analysis revealed that DenseNet121, MobileNet and Xception required shorter training durations and lower computational resources, whereas MobileNetV2 and InceptionV3 were comparatively resource-intensive. Notably, MobileNet demonstrated superior energy efficiency, consuming 19.03 watts and generating 0.00952 kg carbon dioxide (CO₂), whereas InceptionV3 consumed 377.27 watts and emitted 0.18864 kg CO₂. To facilitate comprehensive model prioritisation, the technique for order of preference by similarity to ideal solution (TOPSIS) was employed, identifying MobileNet as the optimal model when considering performance, efficiency and environmental impact. The findings highlight the potential applicability of lightweight deep learning architectures, particularly MobileNet and DenseNet121, in real-time rice grading and sorting systems, supporting sustainable post-harvest management, improving grain quality assurance and mitigating seed-borne pathogen dissemination.

References

  1. 1. Bin Rahman AR, Zhang J. Trends in rice research: 2030 and beyond. Food Energy Secur. 2023;12(2):e390. https://doi.org/10.1002/fes3.390
  2. 2. Deng SW, Abdellah YAY, Chen HY, Gao PL, Abdallah MM, Rana MS, et al. Optimizing agricultural management practices to promote ratoon rice yield during ratoon crop: A global meta-analysis. Field Crops Res. 2025;328:109943. https://doi.org/10.1016/j.fcr.2025.109943
  3. 3. Agarwal VK, Singh OV. Relative percentage incidence of seed-borne fungi associated with different varieties of rice seeds. Seed Res. 1974;2:23–5.
  4. 4. Gopalakrishnan KG, Valluvaparidasan V. Survey of seed-borne fungi associated with rice seeds in Tamil Nadu, India. Libyan Agric Res Cent J Int. 2010;1:307–9.
  5. 5. Islam MS, Rahman H, Pervez Z, Mahmud MR, Alam A. Studies on seed-borne fungi in rice cultivars grown in tidal zones of Patuakhali and their effect on germination. J Bangladesh Res Publ. 2012;6:286–90.
  6. 6. Nandakumar R, Rush MC, Correa F. Association of Burkholderia glumae and Burkholderia gladioli with panicle blight in Panama. Plant Dis. 2007;91(6):767. https://doi.org/10.1094/PDIS-91-6-0767C
  7. 7. Trung HM, Van NV, Vien NV, Lam DT, Lien M. Occurrence of rice grain rot disease in Vietnam. Int Rice Res Notes. 1993;18:30.
  8. 8. Baite MS, Raghu S, Prabhukarthikeyan SR, Keerthana U, Jambhulkar NN, Rath PC. Disease incidence and yield loss in rice due to grain discolouration. J Plant Dis Prot. 2020;127:9–13. https://doi.org/10.1007/s41348-019-00268-y
  9. 9. Ashfaq M, Mubashar U, Haider MS, Ali M, Ali A, Sajjad M. Grain discoloration: An emerging threat to rice crop in Pakistan. J Anim Plant Sci. 2017;27(3).
  10. 10. Munir R, Rahmayanti HD, Murniati R, Rahman DY, Utami FD, Viridi S, et al. Experiment and modeling of rice winnowing: Granular segregation method. Granul Matter. 2020;22:1–14. https://doi.org/10.1007/s10035-019-0991-6
  11. 11. Ferentinos KP. Deep learning models for plant disease detection and diagnosis. Comput Electron Agric. 2018;145:311–18. https://doi.org/10.1016/j.compag.2018.01.009
  12. 12. Too EC, Yujian L, Njuki S, Yingchun L. Fine-tuning deep learning models for plant disease identification: A comparative study. Comput Electron Agric. 2019;161:272–9. https://doi.org/10.1016/j.compag.2018.03.032
  13. 13. Mohanty SP, Hughes DP, Salathé M. Using deep learning for image-based plant disease detection. Front Plant Sci. 2016;7:1419. https://doi.org/10.3389/fpls.2016.01419
  14. 14. Jiang F, Lu Y, Chen Y, Cai D, Li G. Image recognition of four rice leaf diseases based on deep learning and SVM. Comput Electron Agric. 2020;179:105824. https://doi.org/10.1016/j.compag.2020.105824
  15. 15. Malathy S, Karthiga RR, Swetha K, Preethi G. Disease detection in fruits using image processing. In: 2021 6th Int Conf Inventive Comput Technol (ICICT). IEEE; 2021. p. 747–52. https://doi.org/10.1109/ICICT50816.2021.9358541
  16. 16. Shoaib M, Hussain T, Shah B, Ullah I, Shah SM, Ali F, et al. Deep learning-based segmentation and classification for tomato leaf disease detection. Front Plant Sci. 2022;13:1031748. https://doi.org/10.3389/fpls.2022.1031748
  17. 17. Panchal AV, Patel SC, Bagyalakshmi K, Kumar P, Khan IR, Soni M. Image-based plant disease detection using deep learning. Mater Today Proc. 2023;80:3500–6. https://doi.org/10.1016/j.matpr.2021.07.281
  18. 18. Bhola A, Kumar P. Deep feature-support vector machine-based hybrid model for multi-crop leaf disease identification in corn, rice, and wheat. Multimed Tools Appl. 2024;84:4751–71. https://doi.org/10.1007/s11042-024-18733-8
  19. 19. Wongchai A, Jenjeti DR, Priyadarsini AI, Deb N, Bhardwaj A, Tomar P. Farm monitoring and disease prediction using deep learning in sustainable agriculture. Ecol Model. 2022;474:110167. https://doi.org/10.1016/j.ecolmodel.2022.110167
  20. 20. Sharma R. Machine learning approach to fungal disease management in rice. In: 2024 Int Conf Commun Comput Sci Eng (IC3SE). IEEE; 2024. p. 798–805. https://doi.org/10.1109/IC3SE62002.2024.10593103
  21. 21. Goodfellow I, Bengio Y, Courville A. Deep Learning. Cambridge: MIT Press; 2016.
  22. 22. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv. 2014;arXiv:1409.1556.
  23. 23. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, et al. Going deeper with convolutions. In: Proc IEEE Conf Comput Vis Pattern Recogn. 2015. p. 1–9. https://doi.org/10.1109/CVPR.2015.7298594
  24. 24. Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Yu T, et al. MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv. 2017;arXiv:1704.04861.
  25. 25. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proc IEEE Conf Comput Vis Pattern Recogn. 2016. p. 770–8. https://doi.org/10.1109/CVPR.2016.90
  26. 26. Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC. MobileNetV2: Inverted residuals and linear bottlenecks. In: Proc IEEE Conf Comput Vis Pattern Recogn. 2018. p. 4510–25. https://doi.org/10.1109/CVPR.2018.00474
  27. 27. Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. In: Proc IEEE Conf Comput Vis Pattern Recogn. 2017. p. 4700–8. https://doi.org/10.1109/CVPR.2017.243
  28. 28. Chollet F. The limitations of deep learning. In: Deep Learning with Python. Berkeley (CA): Apress; 2017. p. 1–5. https://doi.org/10.1007/978-1-4842-2766-4_1
  29. 29. Erickson BJ, Kitamura F. Magician's corner: Performance metrics for machine learning models. Radiol Artif Intell. 2021;3(3):e200126. https://doi.org/10.1148/ryai.2021200126
  30. 30. Environmental Protection Agency. GHG emission factors hub. 2025.
  31. https://www.epa.gov/climateleadership/ghg-emission-factors-hub
  32. 31. Chetlur S, Woolley C, Vandermersch P, Cohen J, Tran J, Catanzaro B, et al. cuDNN: Efficient primitives for deep learning. arXiv. 2014;arXiv:1410.0759.
  33. 32. Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. In: Proc IEEE Conf Comput Vis Pattern Recogn. 2016. p. 2818–26. https://doi.org/10.1109/CVPR.2016.308
  34. 33. Joshua SR, Junghyun Y, Park S, Kwon K. Integrating deep learning and energy management standards for solar-hydrogen systems: MobileNetV2 and InceptionV3. Hydrogen. 2024;5(4):819–50. https://doi.org/10.3390/hydrogen5040043
  35. 34. Bhuyan P, Singh PK, Das SK, Kalla A. SE-SPNet: Rice leaf disease prediction using stacked parallel convolutional neural network with squeeze-and-excitation. Expert Syst. 2023;40:e13304. https://doi.org/10.1111/exsy.13304
  36. 35. Gulzar Y. Fruit image classification model based on MobileNetV2 with deep transfer learning technique. Sustainability. 2023;15(3):1906. https://doi.org/10.3390/su15031906
  37. 36. Prathima S, Praveena NG, Sivachandar K, Nath SS, Sarala B. Generic paddy plant disease detector (GP2D2) using deep-CNN. Int J Electr Comput Eng Syst. 2023;14:647–56. https://doi.org/10.32985/ijeces.14.6.4
  38. 37. Kalupahana D, Kahatapitiya NS, Silva BN, Kim J, Jeon M, Wijenayake U, et al. Dense CNN pipeline for circular leaf spot disease pre-identification using optical coherence tomography. Sensors. 2024;24(16):5398. https://doi.org/10.3390/s24165398
  39. 38. Krishnamoorthy N, Prasad LN, Kumar CP, Subedi B, Abraha HB, Sathishkumar VE. Rice leaf disease prediction using deep neural networks with transfer learning. Environ Res. 2021;198:111275. https://doi.org/10.1016/j.envres.2021.111275
  40. 39. Orchi H, Sadik M, Khaldoun M, Sabir E. Automation of crop disease detection through ML and deep transfer learning. Agriculture. 2023;13(2):352. https://doi.org/10.3390/agriculture13020352
  41. 40. Gaurav A, Pan VSH, Arya V, Raman R, Gupta BB, Chui KT. AI-driven lightweight CNN model for sustainable vegetable classification in smart food systems. Green Technol Sustain. 2026;4(1):100257. https://doi.org/10.1016/j.grets.2025.100257
  42. 41. Thakur PS, Chaturvedi S, Seal A, Khanna P, Sheorey T, Ojha A. An ultra-lightweight interpretable convolution-vision transformer fusion model for plant disease identification: ConViTX. IEEE Trans Comput Biol Bioinform. 2025;22(1):310–21. https://doi.org/10.1109/TCBBIO.2024.3515149

Downloads

Download data is not yet available.