|
|
|
|
|
|
Research on Prediction Model of Soil Nitrogen Content Based on
Encoder-CNN |
JI Rong-hua1, 2, ZHAO Ying-ying2, LI Min-zan2, ZHENG Li-hua2* |
1. Yantai Research Institute of China Agricultural University, Yantai 264670, China
2. Key Laboratory of Modern Precision Agriculture System Integration Research, Ministry of Education, China Agricultural University, Beijing 100083, China
|
|
|
Abstract Poor generalization ability of soil nitrogen content prediction models based on spectroscopy is the bottleneck of its actual application in agriculture production. However, the deep learning model shows strong potential for generalization because of its automatic feature extraction and excellent nonlinear expression. In this paper, a spectral prediction model of soil nitrogen content combining the auto-encoder and convolutional neural network (Encoder-CNN) was proposed, the influence of model structure and parameters on model performance was explored, and its generalization ability was investigated. After researching the previous references and analyzing the correlation between wavelengths and soil nitrogen content, 180 wavelengths with the highest correlation were selected and taken as the input of the Encoder-CNN model. The output of the Encoder-CNN model was the soil nitrogen content. The Encoder-CNN model first used the auto-encoder to reduce the dimension of 180 wavelengths and then predicted the soil nitrogen content by its convolutional neural network. Two network structures were designed. Each network structure had two different parameter settings. Therefore, four models were used to explore the effects of structure and parameters of the Encoder-CNN soil nitrogen content spectral prediction model on modeling performance. Encoder CNN models were trained by the LUCAS data set. According to the 3σ principle, 20 791 data were obtained from LUCAS and then divided into a training set (18 711) and test set (2 080). The results were analyzed and discussed, and several conclusions were achieved in this research. The reproduction effect of the automatic encoder reached the best when the number of neurons in the last hidden layer was set to 30 with the same number of hidden layers as the others; the more hidden layers, the better the reproduction effect. As for the prediction part based on CNN, increasing the number of convolution kernels, especially 1×1 convolution kernels, could improve the prediction performance and reliability. By adding pooling layer in CNN, the model’s prediction accuracy was improved to more than 0.90. The model’s performance could also be improved by increasing the number of neurons in the full junction layer. The Encoder-CNN model built by the LUCAS data set was migrated to the Heilongjiang data set, and the generalization ability of the model was observed and evaluated. The prediction accuracy of the model, which was trained 100 times by the Heilongjiang data set, could reach more than 0.90. When the number of iterations was set to 900, the model’s prediction accuracy could be as high as 0.98. The results showed that the proposed Encoder-CNN spectral prediction model of soil nitrogen content had good generalization ability, and it could be used to detect soil nitrogen content after the model migration process.
|
Received: 2021-04-05
Accepted: 2021-06-10
|
|
Corresponding Authors:
ZHENG Li-hua
E-mail: zhenglh@cau.edu.cn
|
|
[1] Ji W, Li S, Chen S, et al. Soil and Tillage Research, 2016, 155:492.
[2] Nie Pengcheng, Dong Tao, He Yong, et al. Sensors, 2017, 17(5):1102.
[3] ZHAO Yan-dong, PI Ting-ting(赵燕东,皮婷婷). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2016, 47(3):144.
[4] ZHOU Peng, YANG Wei, LI Min-zan, et al(周 鹏,杨 玮,李民赞,等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2017, 48(S1):271.
[5] Marcelo de Souza, André Filgueiras P, Coelho, et al. Journal of Near Infrared Spectroscopy, 2016, 24(3):293.
[6] Li X Y, Fan P P, Liu Y, et al. Journal of Applied Spectroscopy, 2019, 86(4):765.
[7] Xu Y, Wang X, Bai J, et al. Ecological Indicators, 2020, 111:106002.
[8] Fang K, Shen C, Kifer D, et al. Geophysical Research Letters, 2017, 44(21):11030.
[9] Zhang X, Lin T, Xu J, et al. Analytica Chimica Acta, 2019, 1058:48.
[10] Ng W, Minasny B, Mendes W D S, et al. Soil, 2020, 6(2):565.
[11] Tsakiridis N L, Keramaris K D, Theocharis J B, et al. Geoderma, 2020, 367:114208.
[12] Wang Y, Li M, Ji R, et al. Sensors (Basel, Switzerland), 2020, 20(24):7078.
|
[1] |
PAN Hong-wei, TONG Wen-bin, LEI Hong-jun*, YANG Guang, SHI Li-li. Spectral Analysis of the Effect of Organic Fertilizer Application on the
Evolution of Organic Matter and Nitrogen in Farmaland[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 3116-3123. |
[2] |
HU Guo-tian1, 2, 3, SHANG Hui-wei1, 2, 3, TAN Rui-hong1, XU Xiang-hu1, PAN Wei-dong1. Research on Model Transfer Method of Organic Matter Content
Estimation of Different Soils Using VNIR Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 3148-3154. |
[3] |
FAN Yi-guang1, 3, 5, FENG Hai-kuan1, 2, 3*, LIU Yang1, 3, 4, BIAN Ming-bo1, 3, ZHAO Yu1, 3, YANG Gui-jun1, 3, QIAN Jian-guo5. Estimation of Potato Plant Nitrogen Content Using UAV Multi-Source Sensor Information[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 3217-3225. |
[4] |
KUANG En-jun1, 2, 3, CHI Feng-qin1, ZHANG Jiu-ming1, XU Ming-gang2*, Gilles Colinet3, SU Qing-rui1, HAO Xiao-yu1, ZHU Bao-guo4. Analysis of DOC Component Structure of Black Soil Profile With Straw Deeply Bried and Based on Fluorescence Spectrum[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 3243-3248. |
[5] |
YANG Xin1, 2, YUAN Zi-ran1, 2, YE Yin1, 2*, WANG Dao-zhong1, 2, HUA Ke-ke1, 2, GUO Zhi-bin1, 2. Winter Wheat Total Nitrogen Content Estimation Based on UAV
Hyperspectral Remote Sensing[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 3269-3274. |
[6] |
ZHANG Yang1, 2, YUE Jun1*, JIA Shi-xiang1, LI Zhen-bo2, SHENG Guo-rui1. Recognition of Shellfish Based on Visible Spectrum and Convolutional Neural Network[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 3298-3306. |
[7] |
BAI Zi-jin1, PENG Jie1*, LUO De-fang1, CAI Hai-hui1, JI Wen-jun2, SHI Zhou3, LIU Wei-yang1, YIN Cai-yun1. A Mid-Infrared Spectral Inversion Model for Total Nitrogen Content of Farmland Soil in Southern Xinjiang[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(09): 2768-2773. |
[8] |
XU Lu1, CHEN Yi-yun1, 2, 3*, HONG Yong-sheng1, WEI Yu1, GUO Long4, Marc Linderman5. Estimation of Soil Organic Carbon Content by Imaging Spectroscopy With Soil Roughness[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(09): 2788-2794. |
[9] |
DAI Qiu-fang1, 2, 3, LIAO Chen-long1, 2, LI Zhen1, 2, 3*,SONG Shu-ran1, 2, 3,XUE Xiu-yun1, 2, 3,XIONG Shi-lu1, 2. Hyperspectral Visualization of Citrus Leaf Moisture Content Based on CARS-CNN[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(09): 2848-2854. |
[10] |
ZHONG Xiang-jun1,2, YANG Li1,2*, ZHANG Dong-xing1,2, CUI Tao1,2, HE Xian-tao1,2, DU Zhao-hui1,2. Prediction of Organic Matter Content in Sandy Fluvo-Aquic Soil by
Visible-Near Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(09): 2924-2930. |
[11] |
ZHANG Yuan-zhe1, LIU Yu-hao1, LU Yu-jie1, MA Chao-qun1, 2*, CHEN Guo-qing1, 2, WU Hui1, 2. Study on the Spectral Prediction of Phosphor-Coated White LED Based on Partial Least Squares Regression[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(08): 2347-2352. |
[12] |
FAN Chun-hui1, 2, XIN Yi-bei1, YUAN Wen-jing1. Spectral Characteristics of Dissolved Organic Matter (DOM) in Leachate Released From Agricultural Soil Irrigated With Reclaimed Water[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(08): 2432-2436. |
[13] |
ZHONG Xiang-jun1, 2, YANG Li1, 2*, ZHANG Dong-xing1, 2, CUI Tao1, 2, HE Xian-tao1, 2, DU Zhao-hui1, 2. Effect of Different Particle Sizes on the Prediction of Soil Organic Matter Content by Visible-Near Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(08): 2542-2550. |
[14] |
ZHANG Peng-peng1, 2, XU Jin-li1, 2*, HU Meng-ying1, 2, ZHANG Ling-huo1, 2, BAI Jin-feng1, 2, ZHANG Qin1, 2*. Determinations of Zr, Hf and Nb Contents in Soil Samples by
Laser-Induced Breakdown Spectroscopy (LIBS)[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(07): 2163-2168. |
[15] |
GUO Jin-ke, LU Ji-long, SI Jun-shi, ZHAO Wei, LIU Yang, WANG Tian-xin, LAI Ya-wen*. Study on Heavy Metal in Soil by Portable X-Ray Fluorescence
Spectrometry Based on Matrix Effect Correction and
Correspondence Analysis[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(07): 2309-2314. |
|
|
|
|