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

Research Articles

Early Access

Early detection of rice blast disease using hyperspectral remote sensing

DOI
https://doi.org/10.14719/pst.11111
Submitted
5 August 2025
Published
07-01-2026

Abstract

We presented an integrative hyperspectral approach for the rapid and non-invasive detection of rice blast (Magnaporthe oryzae) that moves beyond traditional index-based methods. Leaf and canopy-level reflectance data (350 nm- 2500 nm) were smoothed using Savitzky - Golay polynomials, standardised with Standard Normal Variate (SNV) and Multiplicative Scatter Correction (MSC) and then differentiated to highlight subtle infection signals. Dimensionality reduction methods including Principal Component Analysis (PCA), t-Distributed Stochastic Neighbour Embedding (t-SNE) and Uniform Manifold Approximation and Projection (UMAP) revealed clear separations between healthy and diseased spectra, while cosine similarity and the Spectral Angle Mapper (SAM) measured illumination-invariant spectral differences. A Random Forest impurity analysis identified the ten most informative wavelengths, enabling the evaluation of over one million band combinations. From this, we developed the Rice Blast Index (RBI = (R1068 - R1560) / (R1068 + R1560)), which outperformed Normalized Difference Vegetation Index (NDVI) and Photochemical Reflectance Index (PRI), achieving an F1-score of 0.95 and Cohen’s κ of 0.93 across independent growing seasons. New structural diagnostics, including lagged correlation, spectral autocorrelation and feature persistence, were introduced to quantify redundancy and identify stable biochemical absorption zones, notably a 38 nm region around 680 nm and a 1470 nm region linked with chlorophyll - protein features. Outlier spectra were removed with an Isolation Forest algorithm, improving robustness by 4.7 %. The average processing time was 18 ms per spectrum, enabling real-time scouting. Together, these elements deliver a unified, end-to-end framework that combines advanced pre-processing, dimensionality reduction, anomaly rejection, machine-learning-based band selection and new structural metrics. This framework improves early rice blast surveillance and offers a transferable template for hyperspectral phenotyping of diverse crop stresses, effectively bridging fine-scale sensitivity with field-scale applicability in precision agriculture.

References

  1. 1. Ou SH. Rice diseases. Kew: Commonwealth Mycol Inst; 1985.
  2. 2. Mahlein AK. Plant disease detection by imaging sensors parallels and specific demands for precision agriculture and plant phenotyping. Plant Dis. 2016;100(2):241–251. https://doi.org/10.1094/PDIS-03-15-0318-FE
  3. 3. Zhang G, Xu T, Tian Y, Feng S, Zhao D, Guo Z. Classification of rice leaf blast severity using hyperspectral imaging. Sci Rep. 2022;12(1):19757. https://doi.org/10.1038/s41598-022-22074-7
  4. 4. Zheng Q, Chen Y, Xia Q, Zhang Y, Li D, Jiang H, et al. New hyperspectral geometry ratio index for monitoring rice blast disease from leaf scale to canopy scale. Remote Sens. 2024;16(24):4681. https://doi.org/10.3390/rs16244681
  5. 5. Mandal N, Adak S, Das DK, Sahoo RN, Mukherjee J, Kumar A, et al. Spectral characterization and severity assessment of rice blast disease using univariate and multivariate models. Front Plant Sci. 2023;14:1067189. https://doi.org/10.3389/fpls.2023.1067189
  6. 6. Maina AW, Oerke EC. Hyperspectral imaging for quantifying Magnaporthe oryzae sporulation on rice genotypes. Plant Methods. 2024;20(1):87. https://doi.org/10.1186/s13007-024-01215-1
  7. 7. Ma B, Cao G, Hu C, Chen C. Monitoring the rice panicle blast control period based on UAV multispectral remote sensing and machine learning. Land. 2023;12(2):469. https://doi.org/10.3390/land12020469
  8. 8. Bauriegel E, Herppich WB. Hyperspectral and chlorophyll fluorescence imaging for early detection of plant diseases. Agriculture. 2014;4(1):32–57. https://doi.org/10.3390/agriculture4010032
  9. 9. Healy J, McInnes L. Uniform manifold approximation and projection. Nat Rev Methods Primers. 2024;4(1):82.https://doi.org/10.1038/s43586-024-00363-x
  10. 10. Kruse FA, Lefkoff AB, Boardman JW, Heidebrecht KB, Shapiro AT, Barloon PJ, Goetz AF. The spectral image processing system (SIPS). Remote Sens Environ. 1993;44(2–3):145–163. https://doi.org/10.1016/0034-4257(93)90013-N
  11. 11. Savitzky A, Golay MJ. Smoothing and differentiation of data by simplified least squares procedures. Anal Chem. 1964;36(8):1627–1639. https://doi.org/10.1021/ac60214a047
  12. 12. Liu FT, Ting KM, Zhou ZH. Isolation forest. In: Proc IEEE Int Conf Data Mining; 2008. p. 413–422. https://doi.org/10.1109/ICDM.2008.17
  13. 13. Kuswidiyanto LW, Noh HH, Han X. Plant disease diagnosis using deep learning based on aerial hyperspectral images: a review. Remote Sens. 2022;14(23):6031. https://doi.org/10.3390/rs14236031
  14. 14. Khan K, Aleem A. Lung disease detection using CNNs and transfer learning. In: Proc Int Conf Commun Secur Artif Intell; 2025. p. 1196–1203. https://doi.org/10.1109/ICCSAI64074.2025.11063806
  15. 15. Shi G, Shen X, Ren H, Rao Y, Weng S, Tang X. Kernel principal component analysis of pesticide residues. Front Plant Sci. 2022;13:956778. https://doi.org/10.3389/fpls.2022.956778
  16. 16. Shaodan L, Yue Y, Jiayi L, Xiaobin L, Jie M, Haiyong W, et al. UAV-based imaging and deep learning in rice blast resistance assessment. Rice Sci. 2023;30(6):652–660. https://doi.org/10.1016/j.rsci.2023.06.005
  17. 17. Barnes RJ, Dhanoa MS, Lister SJ. Standard normal variate transformation of NIR spectra. Appl Spectrosc. 1989;43(5):772–777. https://doi.org/10.1366/0003702894202201
  18. 18. Martens H, Næs T. Multivariate calibration. Chichester: Wiley; 1992.
  19. 19. Jolliffe IT, Cadima J. Principal component analysis: a review. Philos Trans R Soc A. 2016;374(2065):20150202. https://doi.org/10.1098/rsta.2015.0202
  20. 20. van der Maaten L, Hinton G. Visualizing data using t-SNE. J Mach Learn Res. 2008;9:2579–2605.
  21. 21. Breiman L. Random forests. Mach Learn. 2001;45(1):5–32. https://doi.org/10.1023/A:1010933404324
  22. 22. Wu D, Zhao X, Liang S, Zhou T, Huang K, Tang B, Zhao W. Time-lag effects of vegetation responses to climate change. Glob Change Biol. 2015;21(9):3520–3531. https://doi.org/10.1111/gcb.12945
  23. 23. Feng ZH, Wang LY, Yang ZQ, Zhang YY, Li X, Song L, et al. Hyperspectral monitoring of powdery mildew severity in wheat. Front Plant Sci. 2022;13:828454. https://doi.org/10.3389/fpls.2022.828454
  24. 24. Krishnamoorthi S, Urano D. Hyperspectral reflectance imaging protocols. STAR Protoc. 2025;6(2):103854. https://doi.org/10.1016/j.xpro.2025.103854
  25. 25. Sarić R, Nguyen VD, Burge T, Berkowitz O, Trtílek M, Whelan J, et al. Applications of hyperspectral imaging in plant phenotyping. Trends Plant Sci. 2022;27(3):301–315. https://doi.org/10.1016/j.tplants.2021.10.008
  26. 26. Moghimi A, Yang C, Anderson JA. Aerial hyperspectral imagery and deep neural networks for high-throughput yield phenotyping in wheat. Computers and Electronics in Agriculture. 2020;172:105299. https://doi.org/10.1016/j.compag.2020.105299
  27. 27. Nagasubramanian K, Jones S, Singh AK, Singh A, Ganapathysubramanian B, Sarkar S. Explaining hyperspectral imaging based plant disease identification: 3D CNN and saliency maps. arXiv preprint. https://doi.org/10.48550/arXiv.1804.08831
  28. 28. Ram BG, Mettler J, Howatt K, Ostlie M, Sun X. WeedCube: Proximal hyperspectral image dataset of crops and weeds for machine learning applications. Data in Brief. 2024;56:110837. https://doi.org/10.1016/j.dib.2024.110837
  29. 29. Turkoglu MO, Ledain S, Aasen H. Model-agnostic, temperature-informed sampling enhances cross-year crop mapping with deep learning. arXiv preprint. https://doi.org/10.48550/arXiv.2506.12885
  30. 30. Chanchí Golondrino GE, Ospina Alarcón MA, Saba M. Vegetation identification in hyperspectral images using distance/correlation metrics. Atmosphere. 2023;14(7):1148. https://doi.org/10.3390/atmos14071148
  31. 31. Badola A, Panda SK, Roberts DA, Waigl CF, Bhatt US, Smith CW, Jandt RR. Hyperspectral data simulation (Sentinel-2 to AVIRIS-NG) for improved wildfire fuel mapping, boreal Alaska. Remote Sensing. 2021;13(9):1693. https://doi.org/10.3390/rs13091693
  32. 32. Li J, Li Q, Wang F, Liu F. Hyperspectral redundancy detection and modeling with local Hurst exponent. Physica A. 2022;592:126830. https://doi.org/10.1016/j.physa.2021.126830
  33. 33. Wójtowicz A, Piekarczyk J, Czernecki B, Ratajkiewicz H. A random forest model for the classification of wheat and rye leaf rust symptoms based on pure spectra at leaf scale. Journal of Photochemistry and Photobiology B. 2021;223:112278. https://doi.org/10.1016/j.jphotobiol.2021.112278
  34. 34. Tian L, Xue B, Wang Z, Li D, Yao X, Cao Q, Cheng T, et al. Spectroscopic detection of rice leaf blast infection from asymptomatic to mild stages with integrated machine learning and feature selection. Remote Sensing of Environment. 2021;257:112350. https://doi.org/10.1016/j.rse.2021.112350
  35. 35. Zhao D, Cao Y, Li J, Cao Q, Li J, Guo F, Xu T, et al. Early detection of rice leaf blast disease using unmanned aerial vehicle remote sensing: a novel approach integrating a new spectral vegetation index and machine learning. Agronomy. 2024;14(3):602. https://doi.org/10.3390/agronomy14030602
  36. 36. Guo Y, Mokany K, Ong C, Moghadam P, Ferrier S, Levick SR. Plant species richness prediction from DESIS hyperspectral data: a comparison study on feature extraction procedures and regression models. ISPRS Journal of Photogrammetry and Remote Sensing. 2023;196:120-133. https://doi.org/10.1016/j.isprsjprs.2022.12.028
  37. 37. Girouard G, Bannari A, El Harti A, Desrochers A. Validated spectral angle mapper algorithm for geological mapping: comparative study between QuickBird and Landsat-TM. In: XXth ISPRS Congress, Geo-imagery Bridging Continents; 2004;12:23.

Downloads

Download data is not yet available.