Convolutional Neural Network Application in Prediction of Soil Moisture Content
WANG Can1, WU Xin-hui1, LI Lian-qing2, WANG Yu-shun1, LI Zhi-wei1*
1. College of Engineering,Shanxi Agricultural University,Taigu 030801,China
2. College of Resources and Environmental Sciences, Nanjing Agricultural University, Nanjing 210095, China
Abstract:The technology of near infrared spectroscopy that has unique advantage in the prediction of soil moisture content is a convenient and effective method. Convolutional neural network (CNN) is a deep learning model with high performance. Using CNN, effective features data can be extracted from complex spectral data and the inner structure of feature data can be learned. Compared with traditional surface learning models, convolutional neural network has more powerful modeling capability. In this research, the CNN was used to predict the soil moisture content by near infrared spectroscopy. An efficient modeling method of CNN for spectral regression was proposed. The pretreatment process of spectral data was simplified and the accuracy of spectral prediction was improved by this modeling method. In this paper, firstly, the simple pretreatment was used to treat the spectral reflectance data of soil samples under different moisture contents. Principal component analysis was used to reduce the amount of spectral data and the correlation of the features. The processed spectral data was transformed into 2-dimensional spectral information matrixes to meet the special learning structure of CNN. Secondly, the convolutional neural network was used to build the regression model for the prediction of soil moisture content. The first four stages of this CNN model were composed of two types of layers: convolutional layers and pooling layers. Inner features of the input spectral data were obtained by composing convolutional layers and pooling layers, each transforms the representation at one level into a representation at a higher, slightly more Abstract level. With the composition of enough such transformations, very effective inner features of spectral data can be extracted. There were two key ideas behind the CNN model that can reduce the number of parameters of the network: local connections and shared weights. In addition, these ideas can also improve the generalization performance of the CNN model. The model structure and parameters were optimized by carrying out experiments. Finally, the CNN model with improved regression structure of soil spectral data was built for the prediction of soil moisture content. The CNN model was compared with the BP, PLSR and LSSVM models, and these three traditional models were commonly used in the prediction of soil moisture content. The results showed that when the number of training samples reached to some degree, the prediction accuracy and regression fitting degree of the CNN model were higher than those of the traditional models. The performance of the CNN model were much higher than the BP neural network which had the same network training method with the CNN model, but slightly lower than the PLSR and LSSVM models when a small number of training samples were used in the modeling. The prediction accuracy of the CNN model greatly increased with the number of training samples growing. So did the regression fitting degree of the CNN model. In the end, the performance of the CNN model was significantly better than the traditional models. Therefore, the CNN method could be used to effectively predict the soil moisture content by the near infrared spectral data, and better results are obtained when more training samples are involved in modeling.
Key words:Convolutional neural network;Near infrared spectroscopy;Soil moisture content;Prediction model
王 璨,武新慧,李恋卿,王玉顺,李志伟. 卷积神经网络用于近红外光谱预测土壤含水率[J]. 光谱学与光谱分析, 2018, 38(01): 36-41.
WANG Can, WU Xin-hui, LI Lian-qing, WANG Yu-shun, LI Zhi-wei. Convolutional Neural Network Application in Prediction of Soil Moisture Content. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(01): 36-41.
[1] Ge Y F,Morgan C L S,Ackerson J P. Geoderma,2014,(221-222):61.
[2] Susha Lekshmi S U,Singh D N,Baghini M S. Measurement,2014,54:92.
[3] Soriano-Disla J M,Janik L J,Viscarra Rossel R A,et al. Applied Spectroscopy Reviews,2014,49(2):139.
[4] LIU Yan-de,XIONG Song-sheng,LIU De-li(刘燕德,熊松盛,刘德力). Spectroscopy and Spectral Analysis(光谱学与光谱分析),2014,34(10): 2639.
[5] Qiu Y,Fu B,Wang J,et al. Journal of Arid Environments,2010,74(2):208.
[6] Ahmad S,Kalra A,Stephen H. Advances in Water Resources,2010,33(1):69.
[7] Shi T,Cui L,Wang J,et al. Plant and Soil,2013,366(1-2):363.
[8] Mouazen A M,Kuang B,De Baerdemaeker J, et al. Geoderma,2010,158(1):23.
[9] WANG Hai-jiang,ZHANG Hua-ling,REN Shao-ting,et al(王海江,张花玲,任少亭,等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报),2014,45(7):133.
[10] YU Lei,ZHU Ya-xing,HONG Yong-sheng,et al(于 雷,朱亚星,洪永胜,等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报),2016,32(22):138.
[11] Morellos A,Pantazi X E,Moshou D,et al. Biosystems Engineering,2016,152:104.
[12] Krizhevsky A,Sutskever I,Hinton G E. ImageNet Classification with Deep Convolutional Neural Networks, Neural Information Processing Systems (NIPS 2012), 2012. 1097.
[13] LeCun Y, Bengio Y, Hinton G E. Nature,2015,521(7553):436.
[14] Szegedy C,Liu W,Jia Y,et al. Going Deeper with Convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2015. 1.
[15] Sun Y,Wang X G,Tang X O. Deep Convolutional Network Cascade for Facial Point Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2013. 3476.