Multi-scale monitoring for hazard level classification of brown planthopper damage in rice using hyperspectral technique

Juan Liao, Wanyan Tao, Yexiong Liang, Xinying He, Hui Wang, Haoqiu Zeng, Zaiman Wang, Xiwen Luo, Jun Sun, Pei Wang, Ying Zang

Abstract


The primary aim of this study was to classify the hazard level of brown Planthopper (BPH) damage in rice. Three datasets, including spectral reflectance corresponding to the sensitive wavelengths from rice canopy spectral wavelengths, rice stem spectral wavelengths, and fusion information of rice canopy and stem spectral wavelengths were used for BPH hazard level classification by using different algorithms. Datasets and algorithms were optimized by the BPH hazard level classification effects (which was evaluated by indices of accuracy, precision, recall, F1, k-value, etc.). The optimized algorithms combination was used to build hazard level classification model for spectral reflectance corresponding to the sensitive wavelength from the rice canopy spectral images. Results showed that: (1) The spectral reflectance corresponding to the sensitive wavelengths of fusion information dataset performed best in BPH hazard level classification, with the highest accuracy (99.08%), precision (99.31%), recall (98.83%), F1 (0.99), and k-value (0.99). (2) The optimum algorithms combination was Savitzky-Golay (S-G) smoothing, principal component analysis (PCA) for sensitive wavelength selection, and broad-learning system (BLS) for modeling. (3) The spectral reflectance corresponding to the sensitive wavelengths dataset of rice canopy spectral images achieved the accuracy (80.63%), precision (80.28%), recall (77.03%), F1 (0.79), and k-value (0.74) in classifying BPH hazard level by using the optimum algorithms combination.
Keywords: brown planthopper (BPH), hazard level classification, hyperspectral technique, rice canopy, rice stem, fusion information
DOI: 10.25165/j.ijabe.20241706.9199

Citation: Liao J, Tao W Y, Liang1 Y X, He X Y, Wang H, Zeng H Q, et al. Multi-scale monitoring for hazard level classification of brown planthopper damage in rice using hyperspectral technique. Int J Agric & Biol Eng, 2024; 17(6): 202-211 .

Keywords


brown planthopper (BPH), hazard level classification, hyperspectral technique, rice canopy, rice stem, fusion information

Full Text:

PDF

References


Kang K, Yue L, Xia X, Liu K, Zhang W Q. Regulatory function of the trehalose‐6‐phosphate synthase gene TPS3 on chitin metabolism in brown planthopper, Nilaparvata lugens. Insect Molecular Biology, 2022; 31(2): 241-250. DOI: 10.1111/imb.12754

Min S, Lee S W, Choi B R, Lee S H, Kwon D H. Insecticide resistance monitoring and correlation analysis to select appropriate insecticides against Nilaparvata lugens (Stl), a migratory pest in Korea. Journal of Asia-Pacific Entomology, 2014; 17(4): 711-716. DOI: 10.1016/j.aspen.2014.07.005

Gomez-Chova L, Calpe J, Camps-Valls G, Martín J D, Soria E, Vila J, et al. Feature selection of hyperspectral data through local correlation and SFFS for crop classification. IEEE International Geoscience & Remote Sensing Symposium. IEEE, 2003; pp.555-557.

Liang K, Ren Z Z, Song J P, Yuan R, Zhang Q. Wheat FHB resistance assessment using hyperspectral feature bandimage fusion and deep learning. Int J Agric & Biol Eng, 2024; 17(2): 240–249. DOI: 10.25165/j.ijabe.20241702.8269

Carter G A, Miller R L. Early detection of plant stress by digital imaging within narrow stress-sensitive wavebands. Remote Sensing of Environment, 1994; 50: 295-302.

Delalieux S, Somers B, Verstraeten W W, Van Aardt J A N, Keulemans W, Coppin P. Hyperspectral indices to diagnose leaf biotic stress of apple plants, considering leaf phenology. International Journal of Remote Sensing, 2009; 30(8): 1887-1912. DOI: 10.1080/01431160802541556

Prasannakumar N R, Chander S, Sahoo R N, Gupta V K. Assessment of Brown Planthopper, (Nilaparvata lugens) [Stl], damage in rice using hyperspectral remote sensing. Pans Pest Articles & News Summaries, 2013; 59(3): 180-188. DOI: 10.1080/09670874.2013.808780

Prasannakumar N R, Chander S, Sahoo R N. Characterization of brown planthopper damage on rice crops through hyperspectral remote sensing under field conditions. Phytoparasitica, 2014; 42(3): 387-395. DOI: 10.1007/s12600-013-0375-0

Huang J R, Sun J Y, Liao H J, Liu X D. Detection of brown planthopper infestation based on SPAD and spectral data from rice under different rates of nitrogen fertilizer. Precision Agriculture, 2015; 16(2): 148-163. DOI: 10.1007/s11119-014-9367-4

Tan Y, Sun J Y, Zhang B, Chen M, Liu Y, Liu X D. Sensitivity of a ratio vegetation index derived from hyperspectral remote sensing to the brown planthopper stress on rice plants. Sensors, 2019; 19(375). DOI: 10.3390/s19020375

Sōgawa K. The rice brown planthopper: Feeding physiology and host plant interactions. Annual Review of Entomology, 1982; 27: 49-73. DOI: 10.1146/annurev.en.27.010182.000405

Nault B A, Taylor A G, Urwiler M, Rabaey T, Hutchison W D. Neonicotinoid seed treatments for managing potato leafhopper infestations in snap bean. Crop Protection, 2004; 23(2): 147–154. DOI: 10.1016/j.cropro.2003.08.002

Liu Y, Liu S, Xu J, Kong X, Xie L, Chen Y, et al. Forest pest identification based on a new dataset and convolutional neural network model with enhancement strategy. Computers and Electronics in Agriculture, 2002; 192: 1-14. DOI: 10.1016/j.compag.2021.106625

Wang K, Chen K, Du H, Liu S, Xu J, Zhao J, Chen H, Liu Y. New image dataset and new negative sample judgment method for crop pest recognition based on deep learning models. Ecological informatics: an International Journal on Ecoinformatics and Computational Ecology, 2002; 69. DOI:10.1016/j.ecoinf.2022.101620

Erfani S M, Rajasegarar S, Karunasekera S, Leckie C. High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning. Pattern Recognition, 2016; 58(C): 121-134. Doi: 10.1016/j.patcog.2016.03.0

Guo W J, Feng S, Feng Q, Li X Z, Gao X Z. Cotton leaf disease detection method based on improved SSD. Int J Agric & Biol Eng, 2024; 17(2): 211-220. DOI: 10.25165/j.ijabe.20241702.8574

Chen C L P, Liu Z. Broad learning system: An effective and efficient incremental learning system without the need for deep architecture. IEEE Transactions on Neural Networks & Learning Systems, 2018; 29(99): 10-24. DOI: 10.1109/TNNLS.2017.2716952

Yasuda T, Bateni M H, Chen L, Fahrbach M, Fu G, Mirrokni V. Sequential attention for feature selection. arXiv e-prints. ICLR, Kigali Rwanda, 2023. DOI: 10.48550/arXiv.2209.14881

Borzov S M, Potaturkin O I. Increasing the classification efficiency of hyperspectral images due to multi-scale spatial processing. Computer Optics, 2020; 44(6): 937-943. DOI: 10.18287/2412-6179-co-779

Sun J, Yang W, Zhang M, Feng M, Ding G. Estimation of water content in corn leaves using hyperspectral data based on fractional order Savitzky-Golay derivation coupled with wavelength selection. Computers and Electronics in Agriculture, 2021; 182(1). DOI: 10.1016/j.compag.2021.105989

Zimmermann B, Kohler A. Optimizing Savitzky-Golay parameters for improving spectral resolution and quantification in infrared spectroscopy. Appl Spectrosc, 2013; 67(8): 892-902. DOI: 10.1366/12-06723

Wold S, Esbensen K, Geladi P. Principal component analysis, Chemometr. Intell. Lab. Syst, 1987; 2(1987): 37–52.

Hervé A, Williams L J. Principal component analysis. Wiley Interdisciplinary Reviews Computational Statistics, 2010; 2(4): 433-459.

Beattie J R, Esmonde-White F W L. Exploration of principal component analysis: deriving principal component analysis visually using spectra. Applied Spectroscopy, 2021; 75(4): 361-375. DOI: 10.1177/0003702820987847

Rodionova O, Kucheryavskiy S, Pomerantsev A. Efficient tools for principal component analysis of complex data—A tutorial. Chemometrics and Intelligent Laboratory Systems, 2021; 213: 1-11. DOI: 10.1016/j.chemolab.2021.104304

Saloni K, Deepika K, Mamta M. An ensemble approach for classification and prediction of diabetes mellitus using soft voting classifier - ScienceDirect. International Journal of Cognitive Computing in Engineering, 2021; 2: 40-46. DOI: 10.1016/j.ijcce.2021.01.001

Machart P, Ralaivola L. Confusion matrix stability bounds for multiclass classification. Computer Science, 2012; 1-11. DOI：10.48550/arXiv.1202.6221

Simon D, Simon D L. Analytic confusion matrix bounds for fault detection and isolation using a sum-of-squared-residuals approach. IEEE Transactions on Reliability, 2021; 59(2): 287-296. DOI: 10.1109/TR.2010.2046772

Paulino J L C, Almirol L C A, Favila J M C, Aquino K A G L, Cruz A H D L, Roxas R. Multilingual sentiment analysis on short text document using semi-supervised machine learning. 5th International Conference on E-Society, E-Education and E-Technology, 2021. DOI: 10.1145/3485768.3485775

Hasnain M, Pasha M F, Ghani I, Imran M, Alzahrani M Y, Budiarto R. Evaluating trust prediction and confusion matrix measures for web services ranking. IEEE Access, 2020; 8: 90847-90861. DOI: 10.1109/ACCESS.2020.2994222

Lydia A, Meena K, Sekar R R, Swaminathan J N. Parkinson's disease prediction through machine learning techniques. In: Chen J I Z, Wang H, Du K L, Suma V (eds.) Machine Learning and Autonomous Systems. Smart Innovation, Systems and Technologies, 269. Springer, Singapore, 2022.

Caelen O. A Bayesian interpretation of the confusion matrix. Ann. Math. Artif. Intell, 2017; 81(3-4): 429-450. DOI: 10.1007/s10472-017-9564-8

Rajalakshmi R, Aravindan C. A Naive Bayes approach for URL classification with supervised feature selection and rejection framework. Computational Intelligence, 2018; 34(1): 363-396. DOI: 10.1111/coin.12158

Popescu S A, Marilena J N. First-order differential equations. in: advanced mathematics for engineers and physicists. Springer, Cham, 2022.

Cotter S F, Adler R, Kreutz-Delgado K. Forward sequential algorithms for best basis selection. Vision Image & Signal Processing IEE Proceedings, 1999.

Ramirez S, Lizarazo I. Decision tree classification model for detecting and tracking precipitating objects from series of meteorological images. Semantic Scholar, 2016. DOI: 10.3990/2.384

Bruzzone L, Chi M, Marconcini M. A novel transductive SVM for semisupervised classification of remote-sensing images. IEEE Transactions on Geoscience & Remote Sensing, 2006; 44: 3363-3373. DOI: 10.1109/TGRS.2006.877950




Copyright (c) 2024 International Journal of Agricultural and Biological Engineering

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

2023-2026 Copyright IJABE Editing and Publishing Office