Advertisement

Journal of the Indian Society of Remote Sensing

, Volume 46, Issue 12, pp 2045–2055 | Cite as

Evaluating the Performance of Multi-Class and Single-Class Classification Approaches for Mountain Agriculture Extraction Using Time-Series NDVI

  • Saptarshi Mondal
  • Chockalingam Jeganathan
Research Article
  • 50 Downloads

Abstract

Supervised multi-class classification (MCC) approach is widely being used for regional-level land use–land cover (LULC) mapping and monitoring. However, it becomes inefficient if the end user wants to map only one particular class. Therefore, an improved single-class classification (SCC) approach is required for quick and reliable map production purpose. In this regard, the current study attempts to evaluate the performance of MCC and SCC approaches for extracting mountain agriculture area using time-series normalized differential vegetation index (NDVI). At first, samples of eight LULC classes were acquired using Google Earth image, and corresponding temporal signatures (TS) were extracted from time-series NDVI to perform classification using minimum distance to mean (MDM) and spectral angle mapper (i.e., multi-class SAM—MCSAM) under MCC approach. Secondly, under SCC approach, the TS of three agriculture classes (i.e., agriculture, mixed agriculture and plantation) were utilized as a reference to extract agriculture extent using Euclidean distance (ED) and SAM (i.e., single-class SAM—SCSAM) algorithms. The area of all four maps (i.e., MDM—19.77% of total geographical area (TGA), MCSAM—21.07% of TGA, ED—15.23% of TGA, SCSAM—13.85% of TGA) was compared with reference agriculture area (14.54% of TGA) of global land cover product, and SCC-based maps were found to have close agreement. Also, the class-wise detection accuracy was evaluated using random sample point-based error matrix which reveals the better performance of ED-based map than rest three maps in terms of overall accuracy and kappa coefficient.

Keywords

Euclidean distance Spectral angle mapper MODIS NDVI Time series Mountain agriculture 

Notes

Acknowledgements

We would like to acknowledge NASA MODIS team and National Geomatics Center of China for making MODIS NDVI product and GLC-30 m data freely available.

References

  1. Adhikari, P., & de Beurs, K. M. (2016). An evaluation of multiple land-cover data sets to estimate cropland area in West Africa. International Journal of Remote Sensing, 37(22), 5344–5364.CrossRefGoogle Scholar
  2. Atkinson, P. M., Jeganathan, C., Dash, J., & Atzberger, C. (2012). Inter-comparison of four models for smoothing satellite sensor time-series data to estimate vegetation phenology. Remote Sensing of Environment, 123, 400–417.CrossRefGoogle Scholar
  3. Basannagari, B., & Kala, C. P. (2013). Climate change and apple farming in the Indian Himalayas: A study of local perceptions and responses. PLoS ONE, 8(10), e77976.CrossRefGoogle Scholar
  4. Chen, J., Chen, J., Liao, A., Cao, X., Chen, L., Chen, X., et al. (2015). Global land cover mapping at 30 m resolution: A POK-based operational approach. ISPRS Journal of Photogrammetry and Remote Sensing, 103, 7–27.CrossRefGoogle Scholar
  5. Clark, M. L., Aide, T. M., Grau, H. R., & Riner, G. (2010). A scalable approach to mapping annual land cover at 250 m using MODIS time series data: A case study in the Dry Chaco ecoregion of South America. Remote Sensing of Environment, 114(11), 2816–2832.CrossRefGoogle Scholar
  6. Delrue, J., Bydekerke, L., Eerens, H., Gilliams, S., Piccard, I., & Swinnen, E. (2013). Crop mapping in countries with small-scale farming: A case study for West Shewa, Ethiopia. International Journal of Remote Sensing, 34(7), 2566–2582.CrossRefGoogle Scholar
  7. DES. (2015). Statistical abstract of Himachal Pradesh 2014–2015 (pp. 1–189). Shimla: Department of Economics and Statistics, The Government of Himachal Pradesh.Google Scholar
  8. Erasmi, S., Bothe, M., & Petta, R. A. (2006). Enhanced filtering of MODIS time series data for the analysis of desertification process in northeast Brazil. In Proceedings of the ISPRS/ITC-midterm symposium—remote sensing: From pixels to processes, Enschede, The Netherlands (Vol. 34, No. 30, pp. 8–11).Google Scholar
  9. Estel, S., Kuemmerle, T., Alcántara, C., Levers, C., Prishchepov, A., & Hostert, P. (2015). Mapping farmland abandonment and recultivation across Europe using MODIS NDVI time series. Remote Sensing of Environment, 163, 312–325.CrossRefGoogle Scholar
  10. Foody, G. M. (2010). Assessing the accuracy of remotely sensed data: Principles and practices. The Photogrammetric Record, 25(130), 204–205.CrossRefGoogle Scholar
  11. Frazier, A. E. & Wang, L. (2011). Optimal Ranges to evaluate sub-pixel classifications for landscape metrics. In ASPRS 2011 annual conference, Milwaukee, Wisconsin (pp. 1–12).Google Scholar
  12. Hamandawana, H., Eckardt, F., & Chanda, R. (2005). Linking archival and remotely sensed data for long-term environmental monitoring. International Journal of Applied Earth Observation and Geoinformation, 7(4), 284–298.CrossRefGoogle Scholar
  13. Husak, G. J., Marshall, M. T., Michaelsen, J., Pedreros, D., Funk, C., & Galu, G. (2008). Crop area estimation using high and medium resolution satellite imagery in areas with complex topography. Journal of Geophysical Research: Atmospheres, 113(D14112), 1–8.Google Scholar
  14. Jakubauskas, M. E., Legates, D. R., & Kastens, J. H. (2001). Harmonic analysis of time-series AVHRR NDVI data. Photogrammetric Engineering and Remote Sensing, 67(4), 461–470.Google Scholar
  15. Jeganathan, C., Dash, J., & Atkinson, P. M. (2010). Mapping the phenology of natural vegetation in India using a remote sensing-derived chlorophyll index. International Journal of Remote Sensing, 31(22), 5777–5796.CrossRefGoogle Scholar
  16. Jiménez-Valverde, A. (2012). Insights into the area under the receiver operating characteristic curve (AUC) as a discrimination measure in species distribution modelling. Global Ecology and Biogeography, 21(4), 498–507.CrossRefGoogle Scholar
  17. Justice, C., & Becker-Reshef, I. (2007). Developing a strategy for global agricultural monitoring in the framework of the Group on Earth Observations (GEO) Workshop Report (p. 67). Rome: Group on Earth Observations.Google Scholar
  18. Kaivanto, K. (2008). Maximization of the sum of sensitivity and specificity as a diagnostic cutpoint criterion. Journal of Clinical Epidemiology, 61(5), 517.CrossRefGoogle Scholar
  19. Kruse, F., Lefkoff, A., Boardman, J., Heidebrecht, K., Shapiro, A., Barloon, P., et al. (1993). The spectral image processing system (SIPS)—Interactive visualization and analysis of imaging spectrometer data. Remote Sensing of Environment, 44, 145–163.CrossRefGoogle Scholar
  20. Lambin, E. F., & Strahlers, A. H. (1994). Change-vector analysis in multitemporal space: A tool to detect and categorize land-cover change processes using high temporal-resolution satellite data. Remote Sensing of Environment, 48(2), 231–244.CrossRefGoogle Scholar
  21. Lhermitte, S., Verbesselt, J., Verstraeten, W. W., & Coppin, P. (2011). A comparison of time series similarity measures for classification and change detection of ecosystem dynamics. Remote Sensing of Environment, 115(12), 3129–3152.CrossRefGoogle Scholar
  22. Lobo, J. M., Jiménez-Valverde, A., & Real, R. (2008). AUC: A misleading measure of the performance of predictive distribution models. Global Ecology and Biogeography, 17(2), 145–151.CrossRefGoogle Scholar
  23. Lu, D., & Weng, Q. (2007). A survey of image classification methods and techniques for improving classification performance. International Journal of Remote Sensing, 28(5), 823–870.CrossRefGoogle Scholar
  24. Mack, B., Roscher, R., & Waske, B. (2014). Can I trust my one-class classification? Remote Sensing, 6(9), 8779–8802.CrossRefGoogle Scholar
  25. Rodrigues, A., Marçal, A. R., & Cunha, M. (2013). Identification of potential land cover changes on a continental scale using NDVI time-series from SPOT-VEGETATION. International Journal of Remote Sensing, 34(22), 8028–8050.CrossRefGoogle Scholar
  26. Singh, N., Sharma, D., & Chand, H. (2016). Impact of climate change on apple production in India: A review. Current World Environment, 11(1), 251–259.CrossRefGoogle Scholar
  27. Tax, D. M. J. (2001). One-class classification: Concept-learning in the absence of counterexamples. Ph.D. thesis, Delft University of Technology.Google Scholar
  28. Vintrou, E., Desbrosse, A., Bégué, A., Traoré, S., Baron, C., & Seen, D. L. (2012). Crop area mapping in West Africa using landscape stratification of MODIS time series and comparison with existing global land products. International Journal of Applied Earth Observation and Geoinformation, 14(1), 83–93.CrossRefGoogle Scholar
  29. 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 Sensing of Environment, 108(3), 290–310.CrossRefGoogle Scholar
  30. Wu, W., Shibasaki, R., Yang, P., Zhou, Q., & Tang, H. (2008). Remotely sensed estimation of cropland in China: A comparison of the maps derived from four global land cover datasets. Canadian Journal of Remote Sensing, 34(5), 467–479.CrossRefGoogle Scholar
  31. Wu, Z., Thenkabail, P. S., Mueller, R., Zakzeski, A., Melton, F., Johnson, L., et al. (2014). Seasonal cultivated and fallow cropland mapping using the MODIS-based automated cropland classification algorithm. Journal of Applied Remote Sensing, 8(1), 083685.CrossRefGoogle Scholar
  32. Yang, Y., Liu, Y., Zhou, M., Zhang, S., Zhan, W., Sun, C., et al. (2015). Landsat 8 OLI image based terrestrial water extraction from heterogeneous backgrounds using a reflectance homogenization approach. Remote Sensing of Environment, 171, 14–32.CrossRefGoogle Scholar

Copyright information

© Indian Society of Remote Sensing 2018

Authors and Affiliations

  1. 1.Department of Remote SensingBirla Institute of Technology (BIT), MesraRanchiIndia

Personalised recommendations