|
|
|
|
|
|
| Research on Fractional-Order Hyperspectral Diagnosis of Rubber Tree Leaf Powdery Mildew Based on TabPFN Model |
| HU Wen-feng1, CHEN Zhou-yang1, LI Chuang1, LUO Xiao-chuan1, ZHAO Yong-chen1, HE Yong2, TANG Rong-nian1* |
1. School of Mechanical and Electrical Engineering, Hainan University, Haikou 570228, China
2. School of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, China
|
|
|
|
|
Abstract Powdery mildew (PM) is a common foliar disease that negatively impacts the health of rubber trees and the yield of natural rubber. Rapid and accurate disease diagnosis is essential for implementing precise control measures and ensuring optimal rubber production. This study employed hyperspectral imaging technology to analyze infected leaves in Hainan rubber plantations. Samples of rubber leaves at various infection levels were collected, and hyperspectral reflectance data ranging from 965.4 to 1 668.0 nm were obtained using hyperspectral imaging equipment. The hyperspectral data contained noise and redundant information. Three traditional models, namely Support Vector Machine (SVM), Random Forest (RF), and Multi-Layer Perceptron (MLP), as well as the Tabular Prior Data Fitting Network (TabPFN), which incorporates automatic feature weighting, were used to model and analyze both the raw spectral data and the full-band data preprocessed by Savitzky-Golay smoothing, Standard Normal Variate (SNV), and Fractional Order Differentiation (FOD). A multi-model evaluation identified the optimal spectral preprocessing method. To assess the feature weighting capability of TabPFN, Principal Component Analysis (PCA), ReliefF, Maximum Relevance Minimum Redundancy (mRMR), and HSICLasso algorithms were employed for feature selection, extracting sensitive bands associated with powdery mildew grading. The performance of the whole band and feature subsets was compared across different classifiers to determine the optimal model architecture. Finally, Shapley Additive Explanationswas used to analyze the key features and their influence on disease grading. The results showed that TabPFN outperformed all other models, demonstrating superior robustness and effective feature weighting selection. FOD preprocessing effectively reduced spectral noise and enhanced the extraction of essential detail features, resulting in the highest data quality improvement. The full-band TabPFN model with FOD preprocessing achieved a classification accuracy of 95.27%, surpassing traditional methods by 3.24%～13.24%. After applying HSICLasso to select 20 critical features, the accuracy remained at 94.31%, while reducing model complexity by nearly 90% and only decreasing accuracy by 1.01%. SHAP analysis identified the 1 160 nm and 1400 nm regions as key discriminatory bands, linked to C—H and O—H chemical bond vibrations. These bands correspond to the leaf's carbohydrate, lignin, and water content, indicating the model's ability to capture spectral responses related to physicochemical changes caused by powdery mildew. This study validates the integration of FOD and TabPFN for PM detection, providing an accurate model for assessing disease severity, which can aid in precise pesticide application and promote the health of rubber trees, ultimately improving rubber production.
|
|
Received: 2025-05-05
Accepted: 2025-09-17
|
|
|
|
Corresponding Authors:
TANG Rong-nian
E-mail: rn.tang@hainanu.edu.cn
|
|
[1] SUN Yong-shuai, TIAN Wei-min, ZHAI De-li, et al(孙永帅, 田维敏, 翟德利, 等). Bulletin of Chinese Academy of Sciences(中国科学院院刊), 2024, 39(1): 191.
[2] LI Bo-xun, LIU Xian-bao, CHEN Li-qiong, et al(李博勋, 刘先宝, 陈丽琼, 等). Scientia Sinica Vitae(中国科学: 生命科学), 2024, 54(10): 1798.
[3] Zeng T, Li C, Zhang B, et al. Frontiers in Plant Science, 2022, 13: 829479.
[4] Bao D, Zhou J, Bhuiyan S A, et al. Journal of Agriculture and Food Research, 2024, 18: 101369.
[5] BAI Da-yu, SHI Qing-hua, WANG Jian-quan, et al(白大昱, 史庆华, 王建全, 等). Journal of Chinese Agricultural Mechanization(中国农机化学报), 2024, 45(11): 172.
[6] BAO Hao, HUANG Li, ZHANG Yan, et al(鲍 浩, 黄 莉, 张 艳, 等). Progress in Biochemistry and Biophysics(生物化学与生物物理进展), 2025, 52(2): 513.
[7] Xuan G, Li Q, Shao Y, et al. Computers and Electronics in Agriculture, 2022, 197: 106921.
[8] Cheng X, Feng Y, Guo A, et al. Remote Sensing, 2024, 16(1): 105.
[9] Cheng X, Huang M, Guo A, et al. Remote Sensing, 2024, 16(9): 1634.
[10] MAMAT Sawut, LI Wu-yao, CUI Jin-tao, et al(买买提·沙吾提, 李武耀, 崔锦涛, 等). Cotton Science(棉花学报), 2024, 36(4): 296.
[11] ZHANG Yun, MAO Hong, FANG Hao-fan, et al(张 运, 茆 红, 方浩帆, 等). Remote Sensing Information(遥感信息), 2024, 39(5): 20.
[12] Chen K, Li C, Tang R. Industrial Crops and Products, 2017, 108: 831.
[13] Zhang J, Jing X, Song X, et al. Computers and Electronics in Agriculture, 2023, 206: 107671.
[14] Rogers M, Blanc-Talon J, Urschler M, et al. Journal of Food Measurement and Characterization, 2023, 17(6): 6039.
[15] WU Meng-hong, DOU Sen, LIN Nan, et al(吴梦红, 窦 森, 林 楠, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2025, 45(1): 204.
[16] Nguyen D H D, Tan A J H, Lee R, et al. Pest Management Science, 2025, 81(1): 149.
[17] Su J, Liu C, Coombes M, et al. Computers and electronics in agriculture, 2018, 155: 157.
[18] Swaraj S, Aparna S. Infrared Physics and Technology, 2024, 142: 105522.
[19] Hollmann N, Müller S, Purucker L, et al. Nature, 2025, 637(8045): 319.
[20] Verma B, Prasad R, Srivastava P K, et al. Computers and Electronics in Agriculture, 2022, 192: 106581.
[21] Lundberg S M, Lee S I. Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017, 4768.
[22] Zhao Z, Anand R, Wang M. Maximum Relevance and Minimum Redundancy Feature Selection Methods for a Marketing Machine Learning Platform, 2019 IEEE International Conference on Data Science and Advanced Analytics (DSAA). IEEE, 2019: 442.
[23] CHENG Feng-wei, WANG Wen-jian, ZHANG Zhen-zhen(程凤伟, 王文剑, 张珍珍). Journal of Nanjing University (Natural Sciences)[南京大学学报(自然科学版)], 2023, 59(6): 928.
[24] Yamada M, Jitkrittum W, Sigal L, et al. Neural computation, 2014, 26(1): 185.
[25] Curran P J. Remote Sensing of Environment, 1989, 30(3): 271.
[26] HU Peng-fei, TANG Rong-nian, HU Wen-feng, et al(胡鹏飞, 唐荣年, 胡文锋, 等). Jiangsu Agricultural Sciences(江苏农业科学), 2024, 52(18): 222.
|
| [1] |
CHEN Shao-yang, DAI Xue-jing*, LI Yun-peng, TANG Cheng-qing. Bloodstain Recognition Based on Residual Network Integrating SENet Channel Attention Mechanism and Hyperspectral Imaging[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(12): 3431-3440. |
| [2] |
CHEN Nan1, 2*, ZOU Zhao-hua1, LUO Zi-xun1, SHEN Xin-jian1, LIU Yan-de1, 2. Fast Classification of Black Mass by Handheld LIBS Based on
Machine Learning[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(12): 3342-3348. |
| [3] |
WU Yi-jian1, 4, XU Wei-ming1, 2, 4*, XU Xue-sen1, 4*, LI Lu-ning2, 4, LÜ Wen-hao1, 4, YAN Peng-peng2, SHU Rong1, 2, 3, 4. Laser Pyrolysis Spectroscopic Detection and Qualitative-Quantitative
Analysis of Organic Compounds in Space Dust[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(12): 3403-3414. |
| [4] |
JIANG Lin-yi, DAI Xue-jing*, LI Yun-peng, TANG Cheng-qing. Identification of Homochromy Inks Based on Improved Convolutional Neural Network and Hyperspectral Imaging Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(12): 3422-3430. |
| [5] |
ZHANG Ying1, 2, ZHANG Chi1, 2, SHI Jian-bo1, 2, LIU Si-si3*. Advances in the Application of Machine Learning to the Spectrum
Detection of Gases[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(11): 3001-3010. |
| [6] |
HUANG Lian-fei1, WU Sha1, HUANG Ren-shuai1, 2*. Research on Non-Destructive Prediction Method of Tomato Quality
Indicators Using Hyperspectral Imaging and Extreme Learning
Machine[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(11): 3090-3097. |
| [7] |
LI Chang-sheng, GAO Shu-hui*, LI Kai-kai. Feature Analysis and Classification of the Line-Crossing Sequences
Between Stamp Inks and Laser Printing Toner Based on
Hyperspectral Techniques[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(10): 2804-2815. |
| [8] |
WU Qiang1, YANG Mo-han1, DUAN Feng-hui1, WANG Zan-pu2, KANG Jia-kun1, YANG Hao3, YANG Gui-jun3, ZHANG Zhi-yong1, MA Xin-ming1, CHENG Jin-peng1*. Accurate Estimation of Maize Above-Ground Biomass Using Integrated Multispectral and LiDAR Data[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(10): 2906-2914. |
| [9] |
LIU En-qin1, 2, HUANG Wei3, XU Yong3, YANG Man2, GAO Bing2, MO Ding-ru4. Hyperspectral Camouflaged Identification Driven by Spatial-Spectral
Characteristics[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(10): 2942-2949. |
| [10] |
SHENG Shu-li1, ZOU Ming-min1, 2*, LIU Tian-qi1, CHENG Yong-ping1, CHEN Zi-zheng1, WANG Xu-wen1. Research on Satellite Greenhouse Gas Remote Sensing Retrieval Methods Based on Machine Learning[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(10): 2983-2991. |
| [11] |
WEN Zhu1, GUO Song1, SHU Tian1, ZHAO Long-cai2, 3. Hyperspectral Estimation of Selenium Content in Selenium-Rich Tea Based on Feature Selection and Machine Learning[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(09): 2590-2596. |
| [12] |
HU Wei-cheng, LI Yun-peng*, WANG Hong-wei, DAI Xue-jing, WANG Hua-peng. Hyperspectral Image Visualization and Recognition of Bloodstains and Their Analogues Based on Attention Mechanism[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(09): 2625-2631. |
| [13] |
LI Yun-peng, WANG Hong-wei, DAI Xue-jing, WU Lian-quan, HU Wei-cheng, ZHANG Yan-chun. Fast Visual Identification Method of Pyrotechnic Composition Based on Hyperspectral Imaging[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(08): 2183-2189. |
| [14] |
KONG Ling-yuan1, 2, HUANG Qing-feng1, 2, NI Chen1, 2, XU Jia-jia1, 2, TANG Xue-hai1, 2*. Estimation of Nitrogen Content of Carya illinoinensis Leaves Based on Canopy Hyperspectral and Wavelet Transform at Different Flight Heights[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(08): 2200-2209. |
| [15] |
LI Shan1, 2, 3, LIN Peng1, 2, 3, XU Zhen-hao1, 2, 3*, XIANG Hang1, 2, 3, LI Qian-ji1, 2, 3. Intelligent Lithology Identification Based on Transfer Learning of Rock Hyperspectral Images[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(08): 2289-2301. |
|
|
|
|
