1. 中国科学院东北地理与农业生态研究所,吉林 长春 130102 2. 中国科学院大学,北京 100049 3. Lancaster Environment Centre, Lancaster University, Lancaster LA1 4YQ, UK
Modeling and Predicting of MODIS Leaf Area Index Time Series Based on a Hybrid SARIMA and BP Neural Network Method
JIANG Chun-lei1,2, ZHANG Shu-qing1*, ZHANG Ce3, LI Hua-peng1, DING Xiao-hui1,2
1. Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, Changchun 130102, China 2. University of Chinese Academy of Sciences, Beijing 100049, China 3. Lancaster Environment Centre, Lancaster University, Lancaster LA1 4YQ, UK
Abstract:The modeling and predicting of vegetation Leaf area index (LAI) is an important component of land surface model and assimilation of remote sensing data. The MODIS LAI product (i.e. MOD15A2) is one of the most widely used LAI data sources. However, the time series of MODIS LAI contains some data of low quality. For example, because of the influence of the cloud, aerosol, etc., the MODIS LAI presents the characteristics of the discontinuous in time and space. In fact, the time series of MODIS LAI include both linear and nonlinear components, which cannot be accurately modeled and predicted by either linear method or nonlinear method alone. In this paper, the original LAI time series data were first smoothed with Savitzky-Golay (SG) filtration and linear interpolation; SARIMA, BP neural network and a hybrid method of SARIMA-BP neural network were then used for modeling and predicting MODIS LAI time series. The SARIMA-BP neural network combined both SARIMA and BP neural network, which could model the linear and the nonlinear component of MODIS LAI time series respectively. That is, the final result of SARIMA-BP neural network was the sum of results of the two methods. Experiments showed that the time series of MODIS LAI that were smoothed with the SG filtration and linear interpolation were more smooth than original time series, with a determination coefficient up to 0.981, closer to 1 than that of SARIMA (0.941) and BP neural network (0.884); the correlation coefficient between SARIMA-BP neural network and the observation is 0.991, higher than that of between SARIMA (0.971) or BP neural network (0.942) SARIMA and the observation. Thus, it can be concluded that, the proposed SARIMA-BP neural network method can better adapt to the LAI time series, and it outperforms the SARIMA and BP neural network methods.
Key words:SARIMA;BP neural network;MODIS LAI;SARIMA-BP neural network method;LAI time series modeling and predicting
姜春雷1,2,张树清1*,张 策3,李华朋1,丁小辉1,2 . 基于SARIMA-BP神经网络组合方法的MODIS叶面积指数时间序列建模与预测 [J]. 光谱学与光谱分析, 2017, 37(01): 189-193.
JIANG Chun-lei1,2, ZHANG Shu-qing1*, ZHANG Ce3, LI Hua-peng1, DING Xiao-hui1,2 . Modeling and Predicting of MODIS Leaf Area Index Time Series Based on a Hybrid SARIMA and BP Neural Network Method . SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(01): 189-193.
[1] Xiao Z Q, Liang S L, Wang J D, et al. Remote Sensing of Environment, 2011, 115(1): 97. [2] Jin H A, Wang J D, Xiao Z Q, et al. Geoscience and Remote Sensing Symposium (IGARSS), 2010 IEEE International. IEEE, 2010. [3] LI Xi-jia, XIAO Zhi-qiang, WANG Jin-di, et al(李喜佳,肖志强,王锦地,等). Journal of Remote Sensing(遥感学报), 2013,18(1): 27. [4] Savoy P, Mackay D S. Agricultural and Forest Meteorology, 2015, 200: 46. [5] Dickinson R E, Tian Y H, Liu Q, et al. Journal of Geophysical Research: Atmospheres (1984—2012), 2008, 113(D16). [6] Jiang B, Liang S L, Wang J D, et al. Remote Sensing of Environment, 2010, 114(7): 1432. [7] Gao F, Morisette J T, Wolfe R E, et al. IEEE Geoscience and Remote Sensing Letters, 2008, 5(1): 60. [8] Zhang G P. Neurocomputing, 2003, 50: 159. [9] CUI Ri-xian, LIU Ya-dong, FU Jin-dong(崔日鲜, 刘亚东, 付金东). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2015,35(9): 46. [10] ZHOU Chun-yan, HUA Deng-xin, LE Jing, et al(周春艳,华灯鑫,乐 静). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2015, 35(9): 53. [11] Box G E, Jenkins G M, Reinsel G C. Time Series Analysis: Forecasting and Control. John Wiley & Sons, 2011. [12] Cheng C, Cheng X S, Dai N, et al. Computers in Biology and Medicine, 2015, 66: 103. [13] Liu Y K, Xie F, Xie C L, et al. Annals of Nuclear Energy, 2015, 85: 566. [14] Fu L M. Neural Networks in Computer Intelligence. Tata: McGraw-Hill Education, 2003. [15] Khashei M, Bijari M. Applied Soft Computing, 2011, 11(2): 2664. [16] Faruk D . Engineering Applications of Artificial Intelligence, 2010, 23(4): 586.