Abstract：The soil pH is the key factor affecting the transformation of soil nutrients and the soil fertility. The detection of pH value of soil by near-infrared spectroscopy can provide an important basis for the development and utilization of soil resources. As a typical algorithm of deep learning in artificial intelligence, the convolutional neural network can not only extract the characteristics of complex spectral data but also reduce the training parameters of the network and improve the efficiency of network operation, because its structure has the ability of “local perception, weight sharing”. In this paper, the convolution neural network is applied to the modeling and analysis of the near-infrared spectrum, and a soil pH prediction method based on convolution neural network and the near-infrared spectrum is proposed. The network is built by Python calling Tensor Flow toolkit, and its structure is composed of the input layer, convolution layer, pooling layer and full connection layer. The spectral sample dataset of mineral soils, collected from the Statistical Survey of Land Use and Coverage conducted by the European Statistical Office in 2008—2012, was employed as an object of study. In order to eliminate the baseline drift in the spectrum and improve the signal-to-noise ratio, the first derivative and Savitzky-Golay smoothing of the original visible near-infrared spectrum (400~2 500 nm) were carried out. In the model training process, 15 000 samples are randomly selected as the training set, and the remaining 2 272 samples are selected as the test set. The effects of the number of convolution layers and training iterations on the model performance are discussed. The ReLU activation function and Adam optimizer are used to prevent the gradient disappearance of the model and improve the stability of the model. Then, the goodness of fit of the model is analyzed and calculated, and finally, the network model is compared with the traditional BP and PLSR models. The experimental results show that when the number of iterations of the model is 2 500, and the number of convolution layers is 4, the model reaches the best performance, and the mean square error of the training set is reduced from 1.898 to 0.097; the goodness of fit of the test set is 0.909, which is 0.117 and 0.218 higher than BP and PLSR models respectively. The results indicate that convolution neural network can extract the internal characteristic information of soil near-infrared spectrum, so as to realize efficient and accurate prediction of soil pH on a large scale. CNNR model can provide guidance for crop planting and precision fertilization to achieve the goal of soil structure stability and sustainable development. The convolution neural network-based NIRS regression method can also be applied to other soil information research.
Key words：Soil pH; Convolution neural network; LUCAS soil sample; Near infrared spectrum; CNNR Model
[1] Ferreira E C, Neto J G, Milori D M, et al. Spectrochimica Acta Part B: Atomic Spectroscopy, 2015，110: 96.
[2] Patil S, Ghadi H, Ramgir N, et al. Sensors and Actuators B: Chemical, 2019，286: 583.
[3] SHEN Zhang-quan, WANG Ke（沈掌泉，王 珂）. Journal of Infrared and Millimeter Waves（红外与毫米波学报），2010，29(1): 32.
[4] SHENG Meng-ge, WANG Kai, WANG Yu-jie, et al（盛梦鸽，王 凯，王玉洁，等）. Journal of Anhui Agricultural University（安徽农业大学学报），2018，45(4): 580.
[5] WANG Kai-long, XIONG Hei-gang, ZHANG Fang（王凯龙，熊黑钢，张 芳）. Arid Zone Research（干旱区研究），2014，31(6): 1005.
[6] GAO Xiao-hong, YANG Yang, ZHANG Wei, et al(高小红，杨 扬，张 威，等). Remote Sensing Technology and Application(遥感技术与应用)，2015，30(5)：849.
[7] FANG Xiang, WANG Wen-cai, JIN Xiu, et al(方 向，王文才，金 秀，等). Jiangsu Journal of Agricultural Sciences(江苏农业学报)，2019，35(5)：1112.
[8] LeCun Y, Kavukcuoglu K, Farabet C. Convolutional Network and Application in Vision. Proceedings of 2010 IEEE International Symposium on Circuits and Systems, 2010: 253.
[9] Sarikaya R, Hinton G E, Deoras A. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014，22(4): 778.
[10] Abdel-Hamid O, Mohamed A R, Jiang H, et al. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014，22(10): 1533.
[11] Panagos P, Meusburger K, Ballabio C, et al. Science of the Total Environment, 2014，479: 189.
[12] Rossel R V, Behrens T. Geoderma, 2010，158(1-2): 46.
[13] Yang M, Xu D, Chen S, et al. Sensors, 2019, 19(2): 263.
[14] Padarian J, Minasny B, McBratney A B. Geoderma Regional, 2019，16: e00198.
