Research on the Inversion of Moisture Content in Rapeseed Silique Peel Based on Hyperspectral Fusion Imaging
WEI Wei1, WANG Dan2, WANG Bo-tao3, TAN Zuo-jun1, LIU Quan1, XIE Jing1*
1. College of Engineering, Huazhong Agricultural University, Wuhan 430070, China
2. College of Informatics, Huazhong Agricultural University, Wuhan 430070, China
3. College of Resources & Environment, Huazhong Agricultural University, Wuhan 430070, China
Abstract：To explore the potential of indirectly estimating the moisture content in silique peel based on hyperspectral data, this study took the rapeseed experimental field as the research object. From March to May 2023, the rapeseed spectra and moisture content of rapeseed silique peel were collected from the experimental field. After two spectral preprocessing methods, three feature wavelength selection methods, and their combinations, hyperspectral image spatial texture information was introduced. Partial Least Squares Regression (PLSR), Lasso regression, Support Vector Regression (SVR), and Extreme Learning Machine (ELM) were used to establish a regression model for the moisture content of rapeseed silique peel, and the accuracy of the model results was evaluated. The research results indicate that: (1) Spectral preprocessing techniques can highlight some hidden information in the spectrum, and mathematical transformations such as Multiple Scatter Correction (MSC) and First Derivative (FD) are more conducive to extracting spectral sensitive information; (2) After performing preprocessing, a feature selecting method combining Competitive Adaptive Reweighted Sampling (CARS) and Iterative Retention Informative Variables (IRIV) was used. The Lasso model demonstrated the best prediction performance, with an R2 of 0.772 0 for test set 3.In response to the complex structure, small volume, and geometric influence of moisture content distribution in rapeseed silique peel, spatial texture information is introduced based on pure spectral information. Spatial texture quantifies the spatial variation and structural details (such as wrinkles and bumps) related to moisture content on the surface of silique, compensates for the variation caused by the shape and orientation of silique in a single pixel spectrum, improves the regression accuracy and prediction ability of the model, enhances the robustness of the model to noise and outliers, and provides a new effective way to solve the precise inversion of physiological parameters of complex small-scale crop objects.
Key words：Hyperspectral; Rape field; Rapeseed silique peel; Moisture content; Spectral data processing; Spatial texture information
魏 薇，王 丹，王博韬，谭佐军，刘 泉，谢 静. 融合高光谱图谱特征的油菜角果含水率反演研究[J]. 光谱学与光谱分析, 2025, 45(10): 2863-2874.
WEI Wei, WANG Dan, WANG Bo-tao, TAN Zuo-jun, LIU Quan, XIE Jing. Research on the Inversion of Moisture Content in Rapeseed Silique Peel Based on Hyperspectral Fusion Imaging. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(10): 2863-2874.
[1] ZHANG Rui-jie, LI Li-li, LI Li, et al(张瑞杰, 李俐俐, 李 礼, 等). Journal of Geomatics(测绘地理信息), 2021, 46(S1): 227.
[2] Singh K D, Duddu H S N, Vail S, et al. Canadian Journal of Remote Sensing, 2021, 47(1): 33.
[3] WANG Ke-xiao, ZHOU Rui, LI Bo, et al(王克晓, 周 蕊, 李 波, 等). Remote Sensing Information(遥感信息), 2022, 37(4): 16.
[4] GAO Kai-xiu, GAO Wen-han, MING Jin, et al(高开秀，高雯晗，明 金，等). Chinese Journal of Oil Crop Sciences(中国油料作物学报)，2019，41(2)：232.
[5] YANG Shu-ting, LI Ji, WANG Rong, et al(杨淑婷, 李 季, 王 蓉, 等). Ningxia Journal of Agriculture and Forestry Science Technology(宁夏农林科技), 2022, 63(3): 53.
[6] Xie C, Yang C. Computers and Electronics in Agriculture, 2020, 178: 105731.
[7] ZHOU Min-gu, SHAO Guo-min, ZHANG Li-yuan, et al(周敏姑, 邵国敏, 张立元, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2020, 36(20): 125.
[8] WEI Qing, ZHANG Bao-zhong, WEI Zheng, et al(魏 青, 张宝忠, 魏 征, 等). Journal of Triticeae Crops(麦类作物学报), 2020, 40(3): 365.
[9] Aasen H, Bolten A. Remote Sensing of Environment, 2018, 205: 374.
[10] ZHU Zhi-cheng, WU Yong-feng, MA Jun-cheng, et al(朱志成, 武永峰, 马浚诚, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2023, 43 (11): 3524.
[11] ZHANG Xian-zheng(张宪政). Methods in Crop Physiology(作物生理研究法). Beijing: Agricultural Press(北京: 农业出版社), 1992.
[12] TANG Xue-hai, YAN Li-peng, FU Gen-shen, et al(唐雪海，燕李鹏，傅根深，等). Chinese Journal of Oil Crops Sciences(中国油料作物学报)，2025，47(2): 488.
[13] HOU Yan-jun, DONG Lin-lin(侯艳军，董琳琳). Laser & Optoelectronics Progress(激光与光电子学进展), 2021, 58(3): 0330005.
[14] CHEN Ming-jie, HE Hao, KE Hao-nan, et al(陈铭杰，何 昊，柯浩楠，等). Journal of Agro-Environment Science(农林环境科学学报)，2025，44(5)：1148.
[15] SHI Zhou(史 舟). Principles and Methods of Hyperspectral Remote Sensing for Ground and Soil(土壤地面高光谱遥感原理与方法). Beijing: Science Press(北京：科学出版社)，2014.
[16] QIN Yi, WANG Teng, MAO Yong-fang(秦 毅, 王 腾, 毛永芳). Journal of Vibration and Shock(振动与冲击), 2013, 32(23): 186.
[17] Allen D M. Technometrics, 1974, 16(1): 125.
[18] SUN Jun, MO Yun-nan, DAI Chun-xia, et al(孙 俊，莫云南，戴春霞，等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2018, 34(14): 188.
[19] Yun Y H, Wang W T, Tan M L, et al. Analytica Chimica Acta, 2014, 807: 36.
[20] Wang C, Wang S, He X, et al. Meat Science, 2020, 169: 108194.
[21] Wold S, Sjostrom M, Eriksson L. Chemometrics and Intelligent Laboratory Systems, 2001, 58(1): 109.
[22] Tibshirani R. Journal of the Royal Statistical Society: Series B: Statistical Methodology, 1996, 58(1): 267.
[23] Huang G B, Zhu Q Y, Siew C K. Neurocomputing, 2006, 70(1-3): 489.
[24] Haralic R M, Shanmugam K, Dinstein I. IEEE Transactions on Systems, Man, and Cybernetics, 1973, SMC-3(6): 610.
[25] Breiman L. Machine Learning, 2001, 45(1): 5.
[26] YIN Ya-jun, ZHANG Xiang-yu, ZHANG Yu(尹亚军，张翔宇，张 喻). Science and Technology of Food Industry(食品工业科技), 2015, 36(5): 339.
