Spatio-temporal analysis of phenology in Yangtze River Delta based on MODIS NDVI time series from 2001 to 2015

doi:10.1007/s11707-018-0713-0

Frontiers of Earth Science

2019, Vol. 13

Issue (1): 92-110 https://doi.org/10.1007/s11707-018-0713-0

本期目录

Spatio-temporal analysis of phenology in Yangtze River Delta based on MODIS NDVI time series from 2001 to 2015

Yongfeng WANG¹, Zhaohui XUE²(

), Jun CHEN¹, Guangzhou CHEN¹

¹. School of Environment and Engineering, Anhui Jianzhu University, Hefei 230022, China
². School of Earth Sciences and Engineering, Hohai University, Nanjing 211100, China

全文: PDF(12882 KB) HTML

Abstract：

Phenology has become a good indicator for illustrating the long-term changes in the natural resources of the Yangtze River Delta. However, two issues can be observed from previous studies. On the one hand, existing time-series classification methods mainly using a single classifier, the discrimination power, can become deteriorated due to fluctuations characterizing the time series. On the other hand, previous work on the Yangtze River Delta was limited in the spatial domain (usually to 16 cities) and in the temporal domain (usually 2000–2010). To address these issues, this study attempts to analyze the spatio-temporal variation in phenology in the Yangtze River Delta (with 26 cities, enlarged by the state council in June 2016), facilitated by classifying the land cover types and extracting the phenological metrics based on Moderate Resolution Imaging Spectrometer (MODIS) Normalized Difference Vegetation Index (NDVI) time series collected from 2001 to 2015. First, ensemble learning (EL)-based classifiers are used for land cover classification, where the training samples (a total of 201,597) derived from visual interpretation based on GlobelLand30 are further screened using vertex component analysis (VCA), resulting in 600 samples for training and the remainder for validating. Then, eleven phenological metrics are extracted by TIMESAT (a package name) based on the time series, where a seasonal-trend decomposition procedure based on loess (STL-decomposition) is used to remove spikes and a Savitzky-Golay filter is used for filtering. Finally, the spatio-temporal phenology variation is analyzed by considering the classification maps and the phenological metrics. The experimental results indicate that: 1) random forest (RF) obtains the most accurate classification map (with an overall accuracy higher than 96%); 2) different land cover types illustrate the various seasonalities; 3) the Yangtze River Delta has two obvious regions, i.e., the north and the south parts, resulting from different rainfall, temperature, and ecosystem conditions; 4) the phenology variation over time is not significant in the study area; 5) the correlation between gross spring greenness (GSG) and gross primary productivity (GPP) is very high, indicating the potential use of GSG for assessing the carbon flux.

Key words： Yangtze River Delta MODIS NDVI ensemble learning land cover classification spatio-temporal phenology

收稿日期: 2016-12-16 出版日期: 2019-01-25

Corresponding Author(s): Zhaohui XUE

引用本文:

. [J]. Frontiers of Earth Science, 2019, 13(1): 92-110.
Yongfeng WANG, Zhaohui XUE, Jun CHEN, Guangzhou CHEN. Spatio-temporal analysis of phenology in Yangtze River Delta based on MODIS NDVI time series from 2001 to 2015. Front. Earth Sci., 2019, 13(1): 92-110.

链接本文:

https://academic.hep.com.cn/fesci/CN/10.1007/s11707-018-0713-0
https://academic.hep.com.cn/fesci/CN/Y2019/V13/I1/92

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Tab.1

Fig.7

Tab.2

Tab.3

Fig.8

Tab.4

Fig.9

Fig.10

Fig.11

Fig.12

Fig.13

1	S PAbercrombie, M AFriedl (2016). Improving the consistency of multitemporal land cover maps using a hidden Markov model. IEEE Trans Geosci Remote Sens, 54(2): 703–713 https://doi.org/10.1109/TGRS.2015.2463689
2	M CAnderson, C A Zolin, P C Sentelhas, C R Hain, K Semmens, MTugrul Yilmaz, FGao, J AOtkin, RTetrault (2016). The evaporative stress index as an indicator of agricultural drought in Brazil: an assessment based on crop yield impacts. Remote Sens Environ, 174: 82–99 https://doi.org/10.1016/j.rse.2015.11.034
3	LBreiman (1996). Bagging predictors. Mach Learn, 24(2):123–140
4	LBreiman (2001) Random forests. Mach Learn, 45(1): 5–32 https://doi.org/10.1023/A:1010933404324
5	JChen, J Chen, A PLiao, XCao, L J Chen, X H Chen, S Peng, GHan, H WZhang, C YHe, HWu, M Lu (2014). Concepts and key techniques for 30 m global land cover mapping. Acta Geodaetica et Cartographica Sinica, 43(6): 551–557
6	JChen, P Jonsson, MTamura, Z HGu, BMatsushita, LEklundh (2004). A simple method for reconstructing a high-quality NDVI time-series data set based on the Savitzky-Golay filter. Remote Sens Environ, 91(3‒4): 332–344 https://doi.org/10.1016/j.rse.2004.03.014
7	JChen, Y H Rao, M G Shen, C Wang, YZhou, LMa, Y H Tang, X Yang (2016). A simple method for detecting phenological change from time series of vegetation index. IEEE Trans Geosci Remote Sens, 54(6): 3436–3449 https://doi.org/10.1109/TGRS.2016.2518167
8	KClauss, H M Yan, C Kuenzer (2016). Mapping paddy rice in China in 2002, 2005, 2010 and 2014 with MODIS time series. Remote Sens, 8(5): 434 https://doi.org/10.3390/rs8050434
9	CCortes, V Vapnik (1995). Support-vector networks. Mach Learn, 20(3): 273–297 https://doi.org/10.1007/BF00994018
10	T MCover, P E Hart (1967). Nearest neighbor pattern classification. IEEE Trans Inf Theory, 13(1): 21–27 https://doi.org/10.1109/TIT.1967.1053964
11	BDemir, F Bovolo, LBruzzone (2013). Updating land-cover maps by classification of image time series: a novel change-detection-driven transfer learning approach. IEEE Trans Geosci Remote Sens, 51(1): 300–312 https://doi.org/10.1109/TGRS.2012.2195727
12	P JDu, J S Xia, W Zhang, KTan, YLiu, S C Liu (2012). Multiple classifier system for remote sensing image classification: a review. Sensors (Basel), 12(4): 4764–4792 https://doi.org/10.3390/s120404764
13	LEklundh, P Jönsson (2015). Timesat 3.2 software mannual. Lund and Malmö University, Sweden
14	RFensholt, SR Proud (2012). Evaluation of earth observation based global long term vegetation trends- Comparing GIMMS and MODIS global NDVI time series. Remote Sens Environ, 119: 131–147 https://doi.org/10.1016/j.rse.2011.12.015
15	MFernandez-Delgado, ECernadas, SBarro, DAmorim (2014). Do we need hundreds of classifiers to solve real world classification problems? J Mach Learn Res, 15: 3133–3181
16	G MFoody (2004). Thematic map comparison: evaluating the statistical significance of differences in classification accuracy. Photogramm Eng Remote Sensing, 70(5): 627–633 https://doi.org/10.14358/PERS.70.5.627
17	SGhosh, D R Mishra, A A Gitelson (2016). Long-term monitoring of biophysical characteristics of tidal wetlands in the northern Gulf of Mexico−A methodological approach using MODIS. Remote Sens Environ, 173: 39–58 doi:10.1016/j.rse.2015.11.015
18	CGómez, J C White, M A Wulder (2016). Optical remotely sensed time series data for land cover classification: a review. ISPRS J Photogramm Remote Sens, 116: 55–72 https://doi.org/10.1016/j.isprsjprs.2016.03.008
19	X DGuan, C Huang, G HLiu, X LMeng, Q SLiu (2016). Mapping rice cropping systems in Vietnam using an NDVI-based time-series similarity measurement based on DTW distance. Remote Sens, 8(1): 19 https://doi.org/10.3390/rs8010019
20	G FHan, J H Xu (2013). Land surface phenology and land surface temperature changes along an urban-rural gradient in Yangtze River Delta, China. Environ Manage, 52(1): 234–249 https://doi.org/10.1007/s00267-013-0097-6
21	SHeremans, J A K Suykens, J Van Orshoven (2016). The effect of imposing ‘fractional abundance constraints’ onto the multilayer perceptron for sub-pixel land cover classification. Int J Appl Earth Obs Geoinf, 44: 226–238 https://doi.org/10.1016/j.jag.2015.09.007
22	GHmimina, E Dufrêne, J YPontailler, NDelpierre, MAubinet, BCaquet, Ade Grandcourt, BBurban, CFlechard, AGranier, PGross, BHeinesch, BLongdoz, CMoureaux, J MOurcival, SRambal, LSaint André, KSoudani (2013). Evaluation of the potential of MODIS satellite data to predict vegetation phenology in different biomes: an investigation using ground-based NDVI measurements. Remote Sens Environ, 132: 145–158 https://doi.org/10.1016/j.rse.2013.01.010
23	T KHo (1998). The random subspace method for constructing decision forests. IEEE Trans Pattern Anal Mach Intell, 20(8): 832–844 https://doi.org/10.1109/34.709601
24	AHuete, K Didan, TMiura, E PRodriguez, XGao, L G Ferreira (2002). Overview of the radiometric and biophysical performance of the MODIS vegetation indices. Remote Sens Environ, 83(1‒2): 195–213 https://doi.org/10.1016/S0034-4257(02)00096-2
25	PJönsson, L Eklundh (2002). Seasonality extraction by function fitting to time-series of satellite sensor data. IEEE Trans Geosci Remote Sens, 40(8): 1824–1832 https://doi.org/10.1109/TGRS.2002.802519
26	KKaralas, G Tsagkatakis, MZervakis, PTsakalides (2016). Land classification using remotely sensed data: going multilabel. IEEE Trans Geosci Remote Sens, 54(6): 3548–3563 https://doi.org/10.1109/TGRS.2016.2520203
27	JLi, J M Bioucas-Dias, A Plaza (2011). Hyperspectral image segmentation using a new Bayesian approach with active learning. IEEE Trans Geosci Remote Sens, 49(10): 3947–3960 https://doi.org/10.1109/TGRS.2011.2128330
28	M MLi, Z C Mao, Y Song, M XLiu, XHuang (2015). Impacts of the decadal urbanization on thermally induced circulations in eastern China. J Appl Meteorol Climatol, 54(2): 259–282 https://doi.org/10.1175/JAMC-D-14-0176.1
29	C GMarston, P Giraudoux, R PArmitage, F MDanson, S CReynolds, QWang, J M Qiu, P S Craig (2016). Vegetation phenology and habitat discrimination: impacts for E. multilocularis transmission host modelling. Remote Sens Environ, 176: 320–327 https://doi.org/10.1016/j.rse.2016.02.015
30	J M PNascimento, J M BDias (2005). Vertex component analysis: a fast algorithm to unmix hyperspectral data. IEEE Trans Geosci Remote Sens, 43(4): 898–910 https://doi.org/10.1109/TGRS.2005.844293
31	S HQader, J Dash, P MAtkinson, VRodriguez-Galiano (2016). Classification of vegetation type in Iraq using satellite-based phenological parameters. IEEE J Sel Top Appl Earth Obs Remote Sens, 9(1): 414–424 https://doi.org/10.1109/JSTARS.2015.2508639
32	B WQiu, M Feng, Z HTang (2016). A simple smoother based on continuous wavelet transform: comparative evaluation based on the fidelity, smoothness and efficiency in phenological estimation. Int J Appl Earth Obs Geoinf, 47: 91–101 https://doi.org/10.1016/j.jag.2015.11.009
33	J JRodriguez, L IKuncheva, C JAlonso (2006). Rotation forest: a new classifier ensemble method. IEEE Trans Pattern Anal Mach Intell, 28(10): 1619–1630 https://doi.org/10.1109/TPAMI.2006.211
34	YShao, R S Lunetta, B Wheeler, J SIiames, J BCampbell (2016). An evaluation of time-series smoothing algorithms for land-cover classifications using MODIS-NDVI multi-temporal data. Remote Sens Environ, 174: 258–265 https://doi.org/10.1016/j.rse.2015.12.023
35	J JShi, J F Huang (2015). Monitoring spatio-temporal distribution of rice planting area in the Yangtze River Delta region using MODIS images. Remote Sens, 7(7): 8883–8905 https://doi.org/10.3390/rs70708883
36	JVerbesselt, R Hyndman, GNewnham, DCulvenor (2010). Detecting trend and seasonal changes in satellite image time series. Remote Sens Environ, 114(1): 106–115 https://doi.org/10.1016/j.rse.2009.08.014
37	AVerger, I Filella, FBaret, JPenuelas (2016). Vegetation baseline phenology from kilometric global LAI satellite products. Remote Sens Environ, 178: 1–14 https://doi.org/10.1016/j.rse.2016.02.057
38	B DWardlow, S L Egbert, J H Kastens (2007). Analysis of time-series MODIS 250 m vegetation index data for crop classification in the US Central Great Plains. Remote Sens Environ, 108(3): 290–310 https://doi.org/10.1016/j.rse.2006.11.021
39	H YWei, P Heilman, J GQi, M ANearing, Z HGu, Y GZhang (2012). Assessing phenological change in China from 1982 to 2006 using AVHRR imagery. Front Earth Sci, 6(3): 227–236 https://doi.org/10.1007/s11707-012-0321-3
40	CWohlfart, G H Liu, C Huang, CKuenzer (2016). A river basin over the course of time: multi-temporal analyses of land surface dynamics in the Yellow River Basin (China) based on medium resolution remote sensing data. Remote Sens, 8(3): 186 https://doi.org/10.3390/rs8030186
41	JWright, A Y Yang, A Ganesh, S SSastry, YMa (2009). Robust face recognition via sparse representation. IEEE Trans Pattern Anal Mach Intell, 31(2): 210–227 https://doi.org/10.1109/TPAMI.2008.79
42	J SXia, M Dalla Mura, JChanussot, P JDu, X YHe (2015). Random subspace ensembles for hyperspectral image classification with extended morphological attribute profiles. IEEE Trans Geosci Remote Sens, 53(9): 4768–4786 https://doi.org/10.1109/TGRS.2015.2409195
43	J SXia, P J Du, X Y He, J Chanussot (2014). Hyperspectral remote sensing image classification based on rotation forest. IEEE Geosci Remote Sens Lett, 11(1): 239–243 https://doi.org/10.1109/LGRS.2013.2254108
44	Z HXue, P J Du, L Feng (2014a). Phenology-driven land cover classification and trend analysis based on long-term remote sensing image series. IEEE J Sel Top Appl Earth Obs Remote Sens, 7(4): 1142–1156 https://doi.org/10.1109/JSTARS.2013.2294956
45	Z HXue, P J Du, H J Su (2014b). Harmonic analysis for hyperspectral image classification integrated with PSO optimized SVM. IEEE J Sel Top Appl Earth Obs Remote Sens, 7(6): 2131–2146 https://doi.org/10.1109/JSTARS.2014.2307091
46	Z HXue, J Li, LCheng, P JDu (2015). Spectral-spatial classification of hyperspectral data via morphological component analysis-based image separation. IEEE Trans Geosci Remote Sens, 53(1): 70–84 https://doi.org/10.1109/TGRS.2014.2318332
47	L LZeng, B D Wardlow, R Wang, JShan, TTadesse, M JHayes, D RLi (2016). A hybrid approach for detecting corn and soybean phenology with time-series MODIS data. Remote Sens Environ, 181: 237–250 https://doi.org/10.1016/j.rse.2016.03.039
48	B HZhang, L Zhang, DXie, X LYin, C JLiu, GLiu (2016). Application of synthetic NDVI time series blended from Landsat and MODIS data for grassland biomass estimation. Remote Sensing, 8: 10
49	CZhang, Y Ma (2012). Ensemble Machine Learning. Springer Verlag New York
50	X YZhang, Q Y Zhang (2016). Monitoring interannual variation in global crop yield using long-term AVHRR and MODIS observations. ISPRS J Photogramm Remote Sens, 114: 191–205 https://doi.org/10.1016/j.isprsjprs.2016.02.010
51	BZhao, Y Yan, H QGuo, M MHe, Y JGu, BLi (2009). Monitoring rapid vegetation succession in estuarine wetland using time series MODIS-based indicators: an application in the Yangtze River Delta area. Ecol Indic, 9(2): 346–356 https://doi.org/10.1016/j.ecolind.2008.05.009
52	J JZhao, Y Y Wang, Z X Zhang, H Y Zhang, X Y Guo, S Yu, W LDu, FHuang (2016). The variations of land surface phenology in northeast China and its responses to climate change from 1982 to 2013. Remote Sens, 8(5): 400 https://doi.org/10.3390/rs8050400
53	D CZhou, S Q Zhao, L X Zhang, S G Liu (2016). Remotely sensed assessment of urbanization effects on vegetation phenology in China’s 32 major cities. Remote Sens Environ, 176: 272–281 https://doi.org/10.1016/j.rse.2016.02.010
54	C MZhu, D S Lu, D Victoria, L VDutra (2016). Mapping fractional cropland distribution in Mato Grosso, Brazil using time series MODIS enhanced vegetation index and Landsat thematic mapper data. Remote Sens, 8: 22

Viewed

Full text

Abstract

Cited

Shared

Discussed