Estimating Nitrogen Concentration of Rubber Leaves Based on a Hybrid Learning Framework and Near-Infrared Spectroscopy
HU Wen-feng1, 2, TANG Wei-hao1, LI Chuang1, WU Jing-jin1, MA Qing-fen1, LUO Xiao-chuan1, WANG Chao2, TANG Rong-nian1*
1. School of Mechanical and Electrical Engineering, Hainan University, Haikou 570228, China
2. School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China
Abstract：Leaf nitrogen Concentration(LNC) is an important criterion for determining the nutritional status of rubber trees. Rapid and accurate detection of rubber trees’ leaf nitrogen content is necessary to ensure the growth of rubber trees. In this paper, the leaf nitrogen content of 119 rubber leaves was quantitatively analyzed by near-infrared spectroscopy, a high-precision prediction model was established, and the rapid and accurate detection of nitrogen content in rubber leaves was realized. The experimental objects of rubber leaf crops in Hainan were collected. First, the GaiaField-F-N17E spectrometer was used to measure rubber leaves’ near-infrared spectral reflectance data, with a wavelength range of 942nm to 1680nm. Then, abnormal samples in the measured spectral data were eliminated, and three different preprocessing methods were used to transform the data and compare their effects on improving model accuracy. Due to the massive redundant information and highly collinear spectral feature bands in the near-infrared spectral data of rubber leaves, a hybrid variable selection algorithm consisting of machine learning and evolutionary algorithms was proposed. it can effectively eliminate the redundancy and collinearity of spectral features and use the proposed method to extract the 28 bands from all 224 spectral bands effectively. Finally, using partial least squares regression (PLSR) and the selected spectral bands were used to establish the LNC estimation model of the rubber leaves. The results show that the spectral curve after multivariate anti-scattering effect (MSC) processing and the estimation model established by the CARS-NNS algorithm performed on the prediction set as follows: the RMSEp reaches 0.116, and the coefficient of determination is 0.116. R2p was 0.951. Both evaluation metrics were better than other models. In conclusion, the prediction model based on NIR spectroscopy and the hybrid learning IMF framework can well reveal the relationship between the spectral data and the nitrogen content of rubber leaves, providing a necessary technology for the nutrient diagnosis of rubber forests. Ensure the good growth of rubber trees to improve the yield and quality of natural rubber.
Key words：Near-infrared spectroscopy; Machine learning; Evolutionary algorithm; Spectral features selection; Leaf nitrogen concentration; Rubber trees
胡文锋，唐玮豪，李 创，吴京锦，马庆芬，罗小川，王 超，唐荣年. 基于近红外光谱技术和混合学习框架的橡胶树叶片氮含量估算[J]. 光谱学与光谱分析, 2023, 43(07): 2050-2058.
HU Wen-feng, TANG Wei-hao, LI Chuang, WU Jing-jin, MA Qing-fen, LUO Xiao-chuan, WANG Chao, TANG Rong-nian. Estimating Nitrogen Concentration of Rubber Leaves Based on a Hybrid Learning Framework and Near-Infrared Spectroscopy. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(07): 2050-2058.
[1] Chlingaryan A, Sukkarieh S, Whelan B. Computers and Electronics in Agriculture, 2018, 151: 61.
[2] Guo P T, Li M F, Luo W, et al. Infrared Physics & Technology, 2019, 102: 103021.
[3] Chen K, Li C, Tang R N. Industrial Crops and Products, 2017, 108: 831.
[4] ZENG Qing-song, LIU Yang-jun, WANG Ju-xiang, et al(曾庆松，刘洋君，王菊香，等). Ordnance Industry Automation(兵工自动化), 2021, 40(12): 81.
[5] LIU Tan, XU Tong-yu, YU Feng-hua, et al(刘 潭，许童羽，于丰华，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2021, 41(8): 2556.
[6] Li J B, Zhang H L, Zhan B S, et al. Infrared Physics & Technology, 2020, 104: 103154.
[7] Liu Y, Liu Y L, Chen Y Y, et al. Remote Sensing, 2019, 11(4): 450.
[8] Ding Z G, Fei M R. IFAC Proceedings Volumes, 2013, 46(20): 12.
[9] Wang Y J, Li T H, Jin G, et al. Journal of the Science of Food and Agriculture, 2020, 100(1): 161.
[10] Ritvanen T, Pastell H, Welling A, et al. Agricultural and Food Science, 2020, 29(1): 1.
[11] Yuan L M, Mao F, Huang G Z, et al. Postharvest Biology and Technology, 2020, 169: 111308.
[12] James B, Brent K, Chris E, et al. Computational Science & Discovery, 2015, 8(1): 014008.
[13] LIU Jin-xiang, BAN Wei, CHEN Yu, et al(刘金香，班 伟，陈 宇，等). Chinese Journal of Lasers(中国激光), 2021, 48(16): 159.
