Advertisement

Frontiers of Earth Science

, Volume 13, Issue 1, pp 92–110 | Cite as

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

  • Yongfeng Wang
  • Zhaohui XueEmail author
  • Jun Chen
  • Guangzhou Chen
Research Article
  • 28 Downloads

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 spatiotemporal 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.

Keywords

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

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Notes

Acknowledgements

This work was partially supported by the National Natural Science Foundation of China (Grant No. 41601347), the Natural Science Foundation of Jiangsu Province (BK20160860), the Fundamental Research Funds for the Central Universities (2018B17814), the Open Research Found of State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University (17R04), the Fundamental Research Funds for the Central Universities, and the Open Research Fund in 2018 of Jiangsu Key Laboratory of Spectral Imaging & Intelligent Sense (3091801410406). The authors would like to thank USGS LP DAAC for sharing the MODIS product data.

References

  1. Abercrombie S P, Friedl M A (2016). Improving the consistency of multitemporal land cover maps using a hidden Markov model. IEEE Trans Geosci Remote Sens, 54(2): 703–713Google Scholar
  2. Anderson M C, Zolin C A, Sentelhas P C, Hain C R, Semmens K, Tugrul Yilmaz M, Gao F, Otkin J A, Tetrault R (2016). The evaporative stress index as an indicator of agricultural drought in Brazil: an assessment based on crop yield impacts. Remote Sens Environ, 174: 82–99Google Scholar
  3. Breiman L (1996). Bagging predictors. Mach Learn, 24(2):123–140Google Scholar
  4. Breiman L (2001) Random forests. Mach Learn, 45(1): 5–32Google Scholar
  5. Chen J, Chen J, Liao A P, Cao X, Chen L J, Chen X H, Peng S, Han G, Zhang H W, He C Y, Wu H, Lu M (2014). Concepts and key techniques for 30 m global land cover mapping. Acta Geodaetica et Cartographica Sinica, 43(6): 551–557Google Scholar
  6. Chen J, Jonsson P, Tamura M, Gu Z H, Matsushita B, Eklundh L (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): 332–344Google Scholar
  7. Chen J, Rao Y H, Shen M G, Wang C, Zhou Y, Ma L, Tang Y H, Yang X (2016). A simple method for detecting phenological change from time series of vegetation index. IEEE Trans Geosci Remote Sens, 54 (6): 3436–3449Google Scholar
  8. Clauss K, Yan H M, Kuenzer C (2016). Mapping paddy rice in China in 2002, 2005, 2010 and 2014 with MODIS time series. Remote Sens, 8 (5): 434Google Scholar
  9. Cortes C, Vapnik V (1995). Support-vector networks. Mach Learn, 20 (3): 273–297Google Scholar
  10. Cover T M, Hart P E (1967). Nearest neighbor pattern classification. IEEE Trans Inf Theory, 13(1): 21–27Google Scholar
  11. Demir B, Bovolo F, Bruzzone L (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): 300–312Google Scholar
  12. Du P J, Xia J S, Zhang W, Tan K, Liu Y, Liu S C (2012). Multiple classifier system for remote sensing image classification: a review. Sensors (Basel), 12(4): 4764–4792Google Scholar
  13. Eklundh L, Jönsson P (2015). Timesat 3.2 software mannual. Lund and Malmö University, SwedenGoogle Scholar
  14. Fensholt R, Proud SR (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 doi:10.1016/j.rse.2011.12.015Google Scholar
  15. Fernandez-Delgado M, Cernadas E, Barro S, Amorim D (2014). Do we need hundreds of classifiers to solve real world classification problems? J Mach Learn Res, 15: 3133–3181Google Scholar
  16. Foody G M (2004). Thematic map comparison: evaluating the statistical significance of differences in classification accuracy. Photogramm Eng Remote Sensing, 70(5): 627–633Google Scholar
  17. Ghosh S, Mishra D R, Gitelson A A (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: 39–58Google Scholar
  18. Gómez C, White J C, Wulder M A (2016). Optical remotely sensed time series data for land cover classification: a review. ISPRS J Photogramm Remote Sens, 116: 55–72Google Scholar
  19. Guan X D, Huang C, Liu G H, Meng X L, Liu Q S (2016). Mapping rice cropping systems in Vietnam using an NDVI-based time-series similarity measurement based on DTW distance. Remote Sens, 8(1): 19Google Scholar
  20. Han G F, Xu J H (2013). Land surface phenology and land surface temperature changes along an urban-rural gradient in Yangtze River Delta, China. Environ Manage, 52(1): 234–249Google Scholar
  21. Heremans S, Suykens J A K, Van Orshoven J (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: 226–238Google Scholar
  22. Hmimina G, Dufrêne E, Pontailler J Y, Delpierre N, Aubinet M, Caquet B, de Grandcourt A, Burban B, Flechard C, Granier A, Gross P, Heinesch B, Longdoz B, Moureaux C, Ourcival JM, Rambal S, Saint André L, Soudani K (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: 145–158Google Scholar
  23. Ho T K (1998). The random subspace method for constructing decision forests. IEEE Trans Pattern Anal Mach Intell, 20(8): 832–844Google Scholar
  24. Huete A, Didan K, Miura T, Rodriguez E P, Gao X, Ferreira L G (2002). Overview of the radiometric and biophysical performance of the MODIS vegetation indices. Remote Sens Environ, 83(1–2): 195–213Google Scholar
  25. Jönsson P, Eklundh L (2002). Seasonality extraction by function fitting to time-series of satellite sensor data. IEEE Trans Geosci Remote Sens, 40(8): 1824–1832Google Scholar
  26. Karalas K, Tsagkatakis G, Zervakis M, Tsakalides P (2016). Land classification using remotely sensed data: going multilabel. IEEE Trans Geosci Remote Sens, 54(6): 3548–3563Google Scholar
  27. Li J, Bioucas-Dias J M, Plaza A (2011). Hyperspectral image segmentation using a new Bayesian approach with active learning. IEEE Trans Geosci Remote Sens, 49(10): 3947–3960Google Scholar
  28. Li M M, Mao Z C, Song Y, Liu M X, Huang X (2015). Impacts of the decadal urbanization on thermally induced circulations in eastern China. J Appl Meteorol Climatol, 54(2): 259–282Google Scholar
  29. Marston C G, Giraudoux P, Armitage R P, Danson F M, Reynolds S C, Wang Q, Qiu J M, Craig P S (2016). Vegetation phenology and habitat discrimination: impacts for E. multilocularis transmission host modelling. Remote Sens Environ, 176: 320–327Google Scholar
  30. Nascimento J MP, Dias JM B (2005). Vertex component analysis: a fast algorithm to unmix hyperspectral data. IEEE Trans Geosci Remote Sens, 43(4): 898–910Google Scholar
  31. Qader S H, Dash J, Atkinson P M, Rodriguez-Galiano V (2016). Classification of vegetation type in Iraq using satellite-based phenological parameters. IEEE J Sel Top Appl Earth Obs Remote Sens, 9(1): 414–424Google Scholar
  32. Qiu B W, Feng M, Tang Z H (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: 91–101Google Scholar
  33. Rodriguez J J, Kuncheva L I, Alonso C J (2006). Rotation forest: a new classifier ensemble method. IEEE Trans Pattern Anal Mach Intell, 28 (10): 1619–1630Google Scholar
  34. Shao Y, Lunetta R S, Wheeler B, Iiames J S, Campbell J B (2016). An evaluation of time-series smoothing algorithms for land-cover classifications using MODIS-NDVI multi-temporal data. Remote Sens Environ, 174: 258–265Google Scholar
  35. Shi J J, Huang J F (2015). Monitoring spatio-temporal distribution of rice planting area in the Yangtze River Delta region using MODIS images. Remote Sens, 7(7): 8883–8905Google Scholar
  36. Verbesselt J, Hyndman R, Newnham G, Culvenor D (2010). Detecting trend and seasonal changes in satellite image time series. Remote Sens Environ, 114(1): 106–115Google Scholar
  37. Verger A, Filella I, Baret F, Penuelas J (2016). Vegetation baseline phenology from kilometric global LAI satellite products. Remote Sens Environ, 178: 1–14Google Scholar
  38. Wardlow B D, Egbert S L, Kastens J H (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): 290–310Google Scholar
  39. Wei H Y, Heilman P, Qi J G, Nearing M A, Gu Z H, Zhang Y G (2012). Assessing phenological change in China from 1982 to 2006 using AVHRR imagery. Front Earth Sci, 6(3): 227–236Google Scholar
  40. Wohlfart C, Liu G H, Huang C, Kuenzer C (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): 186Google Scholar
  41. Wright J, Yang A Y, Ganesh A, Sastry S S, Ma Y (2009). Robust face recognition via sparse representation. IEEE Trans Pattern Anal Mach Intell, 31(2): 210–227Google Scholar
  42. Xia J S, Dalla Mura M, Chanussot J, Du P J, He X Y (2015). Random subspace ensembles for hyperspectral image classification with extended morphological attribute profiles. IEEE Trans Geosci Remote Sens, 53(9): 4768–4786Google Scholar
  43. Xia J S, Du P J, He X Y, Chanussot J (2014). Hyperspectral remote sensing image classification based on rotation forest. IEEE Geosci Remote Sens Lett, 11(1): 239–243Google Scholar
  44. Xue Z H, Du P J, Feng L (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): 1142–1156Google Scholar
  45. Xue Z H, Du P J, Su H J (2014b). Harmonic analysis for hyperspectral image classification integrated with PSO optimized SVM. IEEE J Sel Top Appl Earth Obs Remote Sens, 7(6): 2131–2146Google Scholar
  46. Xue Z H, Li J, Cheng L, Du P J (2015). Spectral-spatial classification of hyperspectral data via morphological component analysis-based image separation. IEEE Trans Geosci Remote Sens, 53(1): 70–84Google Scholar
  47. Zeng L L, Wardlow B D, Wang R, Shan J, Tadesse T, Hayes M J, Li D R (2016). A hybrid approach for detecting corn and soybean phenology with time-series MODIS data. Remote Sens Environ, 181: 237–250Google Scholar
  48. Zhang B H, Zhang L, Xie D, Yin X L, Liu C J, Liu G (2016). Application of synthetic NDVI time series blended from Landsat and MODIS data for grassland biomass estimation. Remote Sensing, 8: 10Google Scholar
  49. Zhang C, Ma Y (2012). Ensemble Machine Learning. Springer Verlag New YorkGoogle Scholar
  50. Zhang X Y, Zhang Q Y (2016). Monitoring interannual variation in global crop yield using long-term AVHRR and MODIS observations. ISPRS J Photogramm Remote Sens, 114: 191–205Google Scholar
  51. Zhao B, Yan Y, Guo H Q, He M M, Gu Y J, Li B (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): 346–356Google Scholar
  52. Zhao J J, Wang Y Y, Zhang Z X, Zhang H Y, Guo X Y, Yu S, Du W L, Huang F (2016). The variations of land surface phenology in northeast China and its responses to climate change from 1982 to 2013. Remote Sens, 8(5): 400Google Scholar
  53. Zhou D C, Zhao S Q, Zhang L X, Liu S G (2016). Remotely sensed assessment of urbanization effects on vegetation phenology in China’s 32 major cities. Remote Sens Environ, 176: 272–281Google Scholar
  54. Zhu C M, Lu D S, Victoria D, Dutra L V (2016). Mapping fractional cropland distribution in Mato Grosso, Brazil using time series MODIS enhanced vegetation index and Landsat thematic mapper data. Remote Sens, 8: 22Google Scholar

Copyright information

© Higher Education Press and Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  • Yongfeng Wang
    • 1
  • Zhaohui Xue
    • 2
    Email author
  • Jun Chen
    • 1
  • Guangzhou Chen
    • 1
  1. 1.School of Environment and EngineeringAnhui Jianzhu UniversityHefeiChina
  2. 2.School of Earth Sciences and EngineeringHohai UniversityNanjingChina

Personalised recommendations