Hyperspectral Inversion of Soil Organic Matter Content Using a Discrete Wavelet Coupling Algorithm
LI Xiao-fang1, WANG Jin-gao1, HUO Jian-hong1, LI Zi-tong1, HAO Hong-chun1, HAN Rui-xin1, GU Xiao-he2*, ZHU Yu-chen4, WANG Yan-cang2, 3
1. Langfang Normal University, Langfang 065000, China
2. Information Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, China
3. North China Institute of Aerospace Engineering，Langfang 065000, China
4. Institute of Hydrogeology and Environmental Geology, Chinese Academy of Geosciences, Shijizhuang 050061, China
Abstract：Soil organic matter content in the plow layer is a key indicator for evaluating soil quality. It not only provides crops with abundant nutrients but also improves the soil environment in the plow layer, making it an essential component of the plow layer. This study proposes a spectral data mining algorithm to enhance the sensitivity of spectral data to soil organic matter content and improve its estimation capability. The study first employed discrete wavelet algorithms to sequentially perform separation, correlation analysis, and model construction on soil spectral data, thereby establishing a model for estimating soil organic matter content. Subsequently, coupled algorithms were used to sequentially perform data mining, correlation analysis, and model construction on soil spectral data, with evaluation metrics used to assess the accuracy of the resulting model. Finally, the sensitivity and estimation capability of spectral data toward soil organic matter content were compared before and after coupling. The research results indicate: (1) The spectral information mining algorithm proposed in this study can integrate the advantages of various wavelet bases, significantly enhancing the sensitivity of the spectra to soil organic matter content, with the correlation coefficient increasing by an average of 15.33%. (2) A comparison of model accuracy before and after coupling indicates that the spectral information mining algorithm proposed in this study can significantly enhance the estimation capability of spectra for soil organic matter content and reduce estimation errors. The conclusions of this study can support the mining and analysis of spectral data across different locations and serve as a reference for the development of related algorithms.
李笑芳，王金杲，霍建鸿，李子桐，郝红春，韩瑞鑫，顾晓鹤，朱玉晨，王延仓. 利用离散小波耦合算法的土壤有机质含量高光谱反演[J]. 光谱学与光谱分析, 2025, 45(12): 3488-3497.
LI Xiao-fang, WANG Jin-gao, HUO Jian-hong, LI Zi-tong, HAO Hong-chun, HAN Rui-xin, GU Xiao-he, ZHU Yu-chen, WANG Yan-cang. Hyperspectral Inversion of Soil Organic Matter Content Using a Discrete Wavelet Coupling Algorithm. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(12): 3488-3497.
[1] YANG Shi-qi, ZHANG Ai-ping, YANG Shu-jing, et al(杨世琦, 张爱平, 杨淑静, 等). Chinese Journal of Eco-Agriculture(中国生态农业学报), 2009, 17(6): 1124.
[2] Yadav V, Malanson G. Progress in Physical Geography, 2007, 31(2): 131.
[3] Meng X T, Bao Y L, Zhang X L, et al. Geoderma，2022，411: 115696.
[4] Seely B, Welham C, Blanco J A. Ecological Indicators, 2010, 10(5): 999.
[5] Meng X, Bao Y, Liu J，et al. Int. J. Appl. Earth Obs. Geoinformatio, 2020, 89: 102111.
[6] Moura-Bueno J M, Dalmolin R S D, Caten A ten, et al. Geoderma, 2019, 337: 565.
[7] Terra F S, Demattê J A M, Viscarra Rossel R A. Geoderma, 2015: 255: 81.
[8] Clark R N, King T V V, Klejwa M. Journal of Geophysical Research, 1990, 95(B8): 12653.
[9] Bao Y, Ustin S, Meng X, et al. Geoderma, 2021, 403: 115263.
[10] Guo L, Sun X, Fu P, et al. Geoderma, 2021, 398: 115118.
[11] WANG Yan-cang, YANG Xiu-feng, ZHAO Qi-chao, et al(王延仓, 杨秀峰, 赵起超, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2019, 39(9): 2855.
[12] LIU Tan, WANG Wen-qi, LI Zi-mo, et al(刘 潭，王雯琦，李子默，等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报)，2024，55(12): 306.
[13] Wu Z, Liu Y, Han Y, et al. Science of Total Environment, 2021, 754(2): 142120.
[14] Zhou T, Geng Y, Ji C, et al. Science of Total Environment, 2021, 755(2): 142661.
[15] Sun W C, Liu S, Zhang X, et al. Geoderma, 2022, 409(3): 115653.
[16] JING Xia, LÜ Xiao-yan, ZHANG Chao, et al(竞 霞, 吕小艳, 张 超, 等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2020, 51(6): 191.
[17] YANG Ling, YANG Hui-xia, WANG Yun-yun, et al(杨 玲, 杨慧霞, 王云云, 等). Journal of Lake Sciences(湖泊科学), 2025, 37(2): 508.
[18] YE Miao, ZHU Lin, LIU Xu-dong, et al(叶 淼, 朱 琳, 刘旭东, 等). Environmental Science(环境科学), 2024, 45(4): 2280.
[19] ZHAO Hai-long, GAN Shu, YUAN Xi-ping, et al(赵海龙, 甘 淑, 袁希平, 等). Acta Optica Sinica(光学学报), 2022, 42(22): 2230002.
[20] GUO Yan-ping，WANG Xue-mei, ZHAO Feng, et al(郭艳萍, 王雪梅, 赵 枫, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2025, 41(3): 83.
