Land Cover Classification Using ICESat/GLAS Full Waveform Data

In the present study, parameters derived from Ice, Cloud, and land Elevation Satellite/Geoscience Laser Altimeter System (GLAS) full waveform were used for land cover classification in western part of Doon valley, Uttarakhand, India. Three parameters, viz, height, front slope angle (afslope) and canopy return ratio (rCanopy) were extracted from the returned full waveform signals. k-means (KM), partitioning around medoids (PAM), and fuzzy c-means (FCM) with different cluster sizes were used for classifying the land cover types with the help of GLAS-derived parameters. Among the clustering methods, KM performed the best. The overall accuracy (89.41 %) of all methods were quite significant with cluster size three i.e. with three classes forest, mango orchard and other class including agriculture, barren/fallow land, settlement, dry river bed, etc. The accuracy of the PAM (60 %) and the FCM (68.4 %) decreased drastically at four clusters with the separation of agriculture from barren/fallow land. The accuracy of the PAM and the FCM further decreased with increase in the number of clusters whereas KM showed reliable results for all clusters. KM with five clusters was able to distinguish five different land covers, viz, forest, mango orchard, agriculture and barren/fallow land and other class including settlement, dry river bed, etc. with an overall classification accuracy of 72.93 %. The study presents a method for classifying land cover types using GLAS full waveform data.

[1]  Ali S. Hadi,et al.  Finding Groups in Data: An Introduction to Chster Analysis , 1991 .

[2]  Joachim Hill,et al.  Fusion of full-waveform lidar and imaging spectroscopy remote sensing data for the characterization of forest stands , 2013 .

[3]  Junjie Wu,et al.  Advances in K-means Clustering , 2012, Springer Theses.

[4]  J. Abshire,et al.  Geoscience Laser Altimeter System (GLAS) on the ICESat Mission: On‐orbit measurement performance , 2005 .

[5]  Norbert Pfeifer,et al.  FULL WAVEFORM ANALYSIS: ICESAT LASER DATA FOR LAND COVER CLASSIFICATIO N , 2006 .

[6]  Congcong Li,et al.  Joint Use of ICESat/GLAS and Landsat Data in Land Cover Classification: A Case Study in Henan Province, China , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[7]  H. Zwally.  ICESat's Laser Measurements of Polar Ice and Atmospheres , 2003 .

[8]  Eréndira Rendón,et al.  Internal versus External cluster validation indexes , 2011 .

[9]  V. H. Duong,et al.  Processing and Application of ICESat Large Footprint Full Waveform Laser Range Data , 2010 .

[10]  R. Nelson,et al.  Regional aboveground forest biomass using airborne and spaceborne LiDAR in Québec. , 2008 .

[11]  D. Harding,et al.  ICESat waveform measurements of within‐footprint topographic relief and vegetation vertical structure , 2005 .

[12]  Steen Savstrup Kristensen,et al.  Basin-scale partitioning of Greenland ice sheet mass balance components (2007–2011) , 2015 .

[13]  S. G. Champion,et al.  A revised survey of the forest types of India. , 1968 .

[14]  S. Nandy,et al.  Study on the utility of IRS 1D LISS-III data and the classification techniques for mapping of Sunderban mangroves , 2011 .

[15]  J. Bezdek,et al.  DETECTION AND CHARACTERIZATION OF CLUSTER SUBSTRUCTURE I. LINEAR STRUCTURE: FUZZY c-LINES* , 1981 .

[16]  A. Belward,et al.  GLC2000: a new approach to global land cover mapping from Earth observation data , 2005 .

[17]  H. Zwally,et al.  Derivation of Range and Range Distributions From Laser Pulse Waveform Analysis for Surface Elevations, Roughness, Slope, and Vegetation Heights , 2012 .

[18]  W. Cohen,et al.  Estimates of forest canopy height and aboveground biomass using ICESat , 2005 .

[19]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[20]  Peter R. J. North,et al.  Vegetation height estimates for a mixed temperate forest using satellite laser altimetry , 2008 .

[21]  Yuhong Zhou,et al.  ICESat waveform-based land-cover classification using a curve matching approach , 2015 .

[22]  Junjie Wu,et al.  Advances in K-means clustering: a data mining thinking , 2012 .

[23]  A. Neuenschwander,et al.  Evaluation of waveform deconvolution and decomposition retrieval algorithms for ICESat/GLAS data , 2008 .