利用CARS-CNN模型的土壤有机质含量高光谱预测

doi:10.3964/j.issn.1000-0593(2024)08-2303-07

Abstract
References
Related Citation (15)

Download: PDF (5058 KB)
Export: BibTeX | EndNote (RIS)

Abstract Convolutional Neural Network (CNN) has a great advantage in data feature extraction, as it can fully acquire data features and has better generalization than traditional models. This study used a hyperspectral prediction method and modeling of Soil Organic Matter (SOM) content based on CNN. Using 320 soil samples from Shangzhuang Experimental Station, Changping District, Beijing, 807 spectral bands within 350~1 700 nm in the visible-near-infrared (VIS-NIR) were extracted, and the spectral data were denoised and transformed by the multivariate scattering correction (MSC) and the first-order differential transform. Successive projection algorithm (SPA) and competitive adaptive reweighted Sampling (CARS) were used to screen the sensitive wavelengths to realize the dimensionality reduction of the spectral data, respectively. To solve the problems of poor generalization of traditional means as well as the complexity and overload of deep CNN networks, based on the CARS and SPA algorithms, a shallow CNN model prediction based on 6 convolutional layers is proposed, and 1D-CNN1 and 1D-CNN2 with different convolutional sizes and number of convolutions are compared to find the optimal network parameters. By comparing the performance of VGG16, Support Vector Regression (SVR), Partial Least Squares Regression (PLSR), and Random Forests (RF) to build a prediction model in the feature wavelength and the full waveform. The optimal model was determined. The results show that compared with the full-spectrum band and SPA filtering algorithms, the model based on CARS filtering feature wavelength modeling performs better, and the number of bands is compressed to 8% of the full-wavelength band, which effectively realizes the dimensionality reduction of the spectral data. Comparing the full-band data, 1D-CNN1 and 1D-CNN2 based on CARS screening wavelengths performed better, with the model predicted R² improved by 0.028 and 0.018, respectively, and the RMSE reduced by 0.150 and 0.107 g·kg^-1, respectively. Overall, the 1D-CNN1 model based on CARS performs the best, with the predicted R²=0.846 and the RMSE decreased by 0.150 g·kg^-1, respectively 0.846, and RMSE=3.145 g·kg^-1, which reduces the network load while improving the model accuracy, and also proves that small-size convolution outperforms a larger number of large-size convolutions for better acquisition of data features. The SOM content prediction model is established by CARS screening feature wavelengths combined with shallow CNN, which provides a method and reference for establishing a high-precision SOM content prediction model.

Key words：Soil organic matter; Convolutional neural network; Hyperspectral; Precision agriculture

Received: 2023-03-10 Accepted: 2023-12-07

ZTFLH:	TP183
	S153.621

Corresponding Authors: YANG Wei E-mail: cauyw@cau.edu.cn

Cite this article:

LI Hao,YU Hao,CAO Yong-yan, et al. Hyperspectral Prediction of Soil Organic Matter Content Using CARS-CNN Modelling[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(08): 2303-2309.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2024)08-2303-07 OR https://www.gpxygpfx.com/EN/Y2024/V44/I08/2303

[1] Angelopoulou T, Balafoutis A, Zalidis G, et al. Sustainability, 2020, 12(2): 443.
[2] GAO Zhen, ZHAO Chun-jiang, YANG Gui-yan, et al(高振，赵春江，杨桂燕，等). Smart Agriculture(智慧农业)，2022，4(2): 121.
[3] Wang C, Qiao X, Liang Z, et al. Fresenius Environmental Bulletin, 2021，30(7): 7979.
[4] Angelopoulou T, Balafoutis A, Zalidis G, et al. Sustainability, 2020, 12 (2): 443.
[5] LIU Tian-lin, ZHU Xi-cun, BAI Xue-yuan, et al(刘恬琳，朱西存，白雪源，等). Smart Agriculture(智慧农业), 2020, 2(3): 129.
[6] Odebiri O, Odindi J, Mutanga O. International Journal of Applied Earth Observation and Geoinformation, 2021，102: 102389.
[7] Liu H Z, Shi T Z, Chen Y Y, et al. Remote Sensing, 2017，9(1): 29.
[8] Zhao M S, Gao Y F, Lu Y Y, et al. Sustainability，2022，14(14): 8455.
[9] Guindo M L, Kabir M H, Chen R, et al. Sensors, 2021, 21(14): 4882.
[10] ZHANG Tao, YU Lei, YI Jun, et al(章涛，于雷，易军，等). Spectroscopy and Spectral Analysis(光谱学与光谱学分析), 2019, 39(10): 3217.
[11] MENG Shan, LI Xin-guo, JIAO Li(孟珊，李新国，焦黎). Environmental Science & Technology(环境科学与技术), 2022, 45(8): 218.
[12] Liu J, Xie J, Meng T, et al. Agronomy Journal, 2022, 114(4): 1944.
[13] 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): 2380.
[14] ZHONG Liang, GUO Xi, GUO Jia-xin, et al(钟亮, 郭熙, 国佳欣, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2021, 37(1): 203.
[15] Liu J B, Dong Z Y, Xia J S, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2021, 258: 119823.
[16] CUI Yu-lu, YANG Wei, WANG Wei-chao, et al(崔玉露，杨玮，王炜超，等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2021, 52(S1): 323.