發(fā)布時間：2018-02-28 22:11

  本文關(guān)鍵詞： SARIMA BP神經(jīng)網(wǎng)絡(luò) LAI SARIMA-BP神經(jīng)網(wǎng)絡(luò)組合方法 LAI時間序列建模與預(yù)測　出處：《光譜學(xué)與光譜分析》2017年01期 　論文類型：期刊論文

【摘要】：植被葉面積指數(shù)(LAI)時間序列的建模及預(yù)測是陸面過程模型和遙感數(shù)據(jù)同化方法的重要組成部分。MODIS數(shù)據(jù)產(chǎn)品MOD15A2是目前應(yīng)用最為廣泛的LAI數(shù)據(jù)源之一,然而MODIS LAI時間序列產(chǎn)品包含了一些低質(zhì)量的數(shù)據(jù),例如由于云層、氣溶膠等的影響,該產(chǎn)品在時間和空間上缺乏連續(xù)性。MODIS LAI時間序列包含線性部分和外在干擾產(chǎn)生的非線性部分,單一的線性方法或非線性方法都不能對其精確建模和預(yù)測。首先利用Savitzky-Golay(SG)濾波和線性插值平滑受到干擾的LAI時間序列,然后采用季節(jié)自回歸積分滑動平均(SARIMA)方法、BP神經(jīng)網(wǎng)絡(luò)方法及二者的組合方法(SARIMA-BP)對MODIS LAI時間序列進行建模及預(yù)測。在SARIMA-BP神經(jīng)網(wǎng)絡(luò)組合方法中,各自在線性與非線性建模的優(yōu)勢得以充分發(fā)揮,其中SARIMA方法用于建模及預(yù)測LAI時間序列中的線性部分,BP神經(jīng)網(wǎng)絡(luò)方法用于對非線性殘差部分進行建模及預(yù)測。實驗結(jié)果顯示:SG濾波和線性插值后的LAI時間序列比原LAI時間序列更平滑;SARIMA-BP神經(jīng)網(wǎng)絡(luò)組合方法的決定系數(shù)為0.981,比SARIMA和BP神經(jīng)網(wǎng)絡(luò)的0.941和0.884更接近于1;SARIMA-BP神經(jīng)網(wǎng)絡(luò)組合方法的預(yù)測值同觀測值之間的相關(guān)系數(shù)為0.991,高于SARIMA(0.971)和BP神經(jīng)網(wǎng)絡(luò)(0.942)的相關(guān)系數(shù)。由此得出結(jié)論:SARIMA-BP神經(jīng)網(wǎng)絡(luò)組合方法對MODIS LAI時間序列具有更好的適應(yīng)性,其建模和預(yù)測準(zhǔn)確性高于SARIMA方法或BP神經(jīng)網(wǎng)絡(luò)方法。
[Abstract]:Modeling and prediction of vegetation leaf area index (Lai) time series is an important part of land surface process model and remote sensing data assimilation method. MODIS data product MOD15A2 is one of the most widely used LAI data sources at present. However, MODIS LAI time series products contain some low-quality data, such as clouds, aerosols, etc. The product lacks continuity in time and space. The MODIS LAI time series consists of linear parts and nonlinear parts produced by external disturbances. Neither a single linear method nor a nonlinear method can accurately model and predict it. Firstly, Savitzky-Golayn filtering and linear interpolation are used to smooth the disturbed LAI time series. Then the MODIS LAI time series is modeled and predicted by using the seasonal autoregressive integral moving average (SARIMA) method and the combined method of BP neural network and SARIMA-BP. in the SARIMA-BP neural network combination method, the BP neural network method is used to model and predict the MODIS LAI time series. Their respective advantages in linear and nonlinear modeling have been brought into full play, The SARIMA method is used to model and predict the linear part of the LAI time series and the BP neural network method is used to model and predict the nonlinear residual part. The experimental results show that the LAI time series ratio after being filtered by the w / SG filter and the linear interpolation is obtained. The determination coefficient of the original LAI time series smoother SARIMA-BP neural network combination method is 0.981, which is closer to the correlation coefficient between the predicted value and the observed value of the SARIMA and BP neural network combination method and the SARIMA-BP neural network combination method, which is higher than that of SARIMA0.971. It is concluded that the combined method of the 1: SARIMA-BP neural network has better adaptability to the MODIS LAI time series. The accuracy of modeling and prediction is higher than that of SARIMA or BP neural network.
【作者單位】： 中國科學(xué)院東北地理與農(nóng)業(yè)生態(tài)研究所;中國科學(xué)院大學(xué);Lancaster
【基金】：國家自然科學(xué)基金項目(41271196) 中國科學(xué)院重點部署項目(KZZD-EW-07-02)資助
【分類號】：Q948;TP79

【相似文獻】

相關(guān)期刊論文 前8條

1 張欽禮;程健;陳秋松;胡威;周碧輝;;GA-SVM和神經(jīng)網(wǎng)絡(luò)組合模型預(yù)測充填鉆孔壽命[J];科技導(dǎo)報;2013年34期

2 裘國華;申屠南瑛;施正倫;;基于GM-RBF神經(jīng)網(wǎng)絡(luò)組合模型的水泥強度預(yù)測方法[J];科技導(dǎo)報;2014年03期

3 段海妮;沈冰;莫淑紅;;灰色GM(1,N)自記憶神經(jīng)網(wǎng)絡(luò)組合預(yù)測模型研究[J];水資源與水工程學(xué)報;2010年05期

4 熊維莉;謝祥俊;陶莉;屈懷林;;GM(1.1)與BP神經(jīng)網(wǎng)絡(luò)組合模型在原油產(chǎn)量預(yù)測中的應(yīng)用[J];石油化工自動化;2007年06期

5 羅黨;時亞楠;;基于灰色BP神經(jīng)網(wǎng)絡(luò)組合模型的鄭州市商品住宅價格預(yù)測[J];華北水利水電學(xué)院學(xué)報;2010年03期

6 荀新新;張德生;王雁;杜方欣;;基于T-S模糊神經(jīng)網(wǎng)絡(luò)組合模型的CPI預(yù)測[J];陜西科技大學(xué)學(xué)報(自然科學(xué)版);2014年03期

7 盛建龍;熊綿國;;基于灰色—BP神經(jīng)網(wǎng)絡(luò)組合模型的邊坡穩(wěn)定性預(yù)報方法[J];有色金屬(礦山部分);2012年04期

8 ;[J];;年期

，

本文編號：1549174