Contribution of multispectral and multitemporal information from MODIS images to land cover classification

Abstract The goal of this study is to evaluate the relative usefulness of high spectral and temporal resolutions of MODIS imagery data for land cover classification. In particular, we highlight the individual and combinatorial influence of spectral and temporal components of MODIS reflectance data in land cover classification. Our study relies on an annual time series of twelve MODIS 8-days composited images (MOD09A1) monthly acquired during the year 2000, at a 500 m nominal resolution. As our aim is not to propose an operational classifier directed at thematic mapping based on the most efficient combination of reflectance inputs — which will probably change across geographical regions and with different land cover nomenclatures — we intentionally restrict our experimental framework to continental Portugal. Because our observation data stream contains highly correlated components, we need to rank the temporal and the spectral features according not only to their individual ability at separating the land cover classes, but also to their differential contribution to the existing information. To proceed, we resort to the median Mahalanobis distance as a statistical separability criterion. Once achieved this arrangement, we strive to evaluate, in a classification perspective, the gain obtained when the dimensionality of the input feature space grows. We then successively embedded the prior ranked measures into the multitemporal and multispectral training data set of a Support Vector Machines (SVM) classifier. In this way, we show that, only the inclusion of the approximately first three dates substantially increases the classification accuracy. Moreover, this multitemporal factor has a significant effect when coupled with combinations of few spectral bands, but it turns negligible as soon as the full spectral information is exploited. Regarding the multispectral factor, its beneficence on classification accuracy remains more constant, regardless of the number of dates being used.

[1]  Limin Yang,et al.  Development of a global land cover characteristics database and IGBP DISCover from 1 km AVHRR data , 2000 .

[2]  P.K. Varshney,et al.  Multisource fusion for land cover classification using support vector machines , 2005, 2005 7th International Conference on Information Fusion.

[3]  J. A. Gomes,et al.  Land cover update by supervised classification of segmented ASTER images , 2005 .

[4]  Richard A. Johnson,et al.  Applied Multivariate Statistical Analysis , 1983 .

[5]  Zhiliang Zhu,et al.  US forest types and predicted percent forest cover from AVHRR data , 1994 .

[6]  Jan Dempewolf,et al.  Mapping regional land cover with MODIS data for biological conservation: Examples from the Greater Yellowstone Ecosystem, USA and Pará State, Brazil , 2004 .

[7]  J. Townshend,et al.  Global land cover classifications at 8 km spatial resolution: The use of training data derived from Landsat imagery in decision tree classifiers , 1998 .

[8]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[9]  Bernhard Schölkopf,et al.  New Support Vector Algorithms , 2000, Neural Computation.

[10]  Guobin Zhu,et al.  Classification using ASTER data and SVM algorithms;: The case study of Beer Sheva, Israel , 2002 .

[11]  John R. Jensen,et al.  Introductory Digital Image Processing: A Remote Sensing Perspective , 1986 .

[12]  Prasad S. Thenkabail,et al.  Ganges and Indus river basin land use/land cover (LULC) and irrigated area mapping using continuous streams of MODIS data , 2005 .

[13]  David A. Landgrebe,et al.  Hyperspectral data analysis and supervised feature reduction via projection pursuit , 1999, IEEE Trans. Geosci. Remote. Sens..

[14]  Paul M. Mather,et al.  MULTITEMPORAL CLASSIFICATION OF AGRICULTURAL CROPS USING THE SPECTRAL-TEMPORAL RESPONSE SURFACE , 2002 .

[15]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[16]  Sameer Singh,et al.  Multiresolution Estimates of Classification Complexity , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  David L. Verbyla,et al.  Optimistic bias in classification accuracy assessment , 1996 .

[18]  B. Duchemin,et al.  Potential and limits of NOAA-AVHRR temporal composite data for phenology and water stress monitoring of temperate forest ecosystems , 1999 .

[19]  Ralf Möller,et al.  A Self-Stabilizing Learning Rule for Minor Component Analysis , 2004, Int. J. Neural Syst..

[20]  Jun-Qiang Sun,et al.  MODIS reflective solar bands calibration algorithm and on-orbit performance , 2003, SPIE Asia-Pacific Remote Sensing.

[21]  Ruth S. DeFries,et al.  Global and regional land cover characterization from satellite data: an introduction to the Special Issue , 2000 .

[22]  Lorenzo Bruzzone,et al.  An extension of the Jeffreys-Matusita distance to multiclass cases for feature selection , 1995, IEEE Trans. Geosci. Remote. Sens..

[23]  D. Landgrebe,et al.  On the classification of classes with nearly equal spectral response in remote sensing hyperspectral image data , 1999, IEEE Trans. Geosci. Remote. Sens..

[24]  David A. Landgrebe,et al.  Hyperspectral image data analysis , 2002, IEEE Signal Process. Mag..

[25]  Martin Herold,et al.  Spectral resolution requirements for mapping urban areas , 2003, IEEE Trans. Geosci. Remote. Sens..

[26]  Jiyuan Liu,et al.  Land cover characterization of Temperate East Asia using multi-temporal VEGETATION sensor data , 2004 .

[27]  J. Borak.  Feature selection and land cover classification of a MODIS-like data set for a semiarid environment , 1999 .

[28]  Hugo Carrão,et al.  Land cover classification with Support Vector Machine applied to MODIS imagery. , 2005 .

[29]  Gregory S. Okin,et al.  Mapping North African landforms using continental scale unmixing of MODIS imagery , 2005 .

[30]  Tin Kam Ho,et al.  Complexity Measures of Supervised Classification Problems , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[31]  C. A. Shah,et al.  Some recent results on hyperspectral image classification , 2003, IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data, 2003.

[32]  Matthias W. Seeger,et al.  Gaussian Processes For Machine Learning , 2004, Int. J. Neural Syst..

[33]  J. Cihlar.  Land cover mapping of large areas from satellites: Status and research priorities , 2000 .

[34]  Hugo Carrão,et al.  USE OF INTRA-ANNUAL SATELLITE IMAGERY TIME-SERIES FOR LAND COVER CHARACTERISATION PURPOSE , 2006 .

[35]  S. Frolking,et al.  Sensitivity of vegetation indices to atmospheric aerosols: Continental-scale observations in Northern Asia , 2003 .

[36]  P. Thenkabail,et al.  Hyperspectral Vegetation Indices and Their Relationships with Agricultural Crop Characteristics , 2000 .

[37]  A. Dijk,et al.  Smoothing vegetation index profiles: an alternative method for reducing radiometric disturbance in NOAA/AVHRR data , 1987 .

[38]  David A. Landgrebe,et al.  Hyperspectral Image Data Analysis as a High Dimensional Signal Processing Problem , 2002 .

[39]  Jesslyn F. Brown,et al.  Development of a land-cover characteristics database for the conterminous U.S. , 1991 .

[40]  Giles M. Foody,et al.  Training set size requirements for the classification of a specific class , 2006 .

[41]  L. S. Davis,et al.  An assessment of support vector machines for land cover classi(cid:142) cation , 2002 .

[42]  J. Townshend,et al.  Global land cover classi(cid:142) cation at 1 km spatial resolution using a classi(cid:142) cation tree approach , 2004 .

[43]  Qiong Jackson,et al.  An adaptive classifier design for high-dimensional data analysis with a limited training data set , 2001, IEEE Trans. Geosci. Remote. Sens..

[44]  Paul M. Mather,et al.  Computer Processing of Remotely-Sensed Images: An Introduction , 1988 .

[45]  D. Roy,et al.  Achieving sub-pixel geolocation accuracy in support of MODIS land science , 2002 .

[46]  David A. Landgrebe.  Multispectral land sensing: where from, where to? , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[47]  G. Mercier,et al.  Support vector machines for hyperspectral image classification with spectral-based kernels , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).

[48]  Giles M. Foody,et al.  The use of small training sets containing mixed pixels for accurate hard image classification: Training on mixed spectral responses for classification by a SVM , 2006 .

[49]  Xiangming Xiao,et al.  Land-cover classification of China: Integrated analysis of AVHRR imagery and geophysical data , 2003 .

[50]  M. Matsuoka,et al.  Land cover classification over Yellow River basin using satellite data , 2004, IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium.

[51]  Paul M. Mather,et al.  Support vector machines for classification in remote sensing , 2005 .

[52]  Siamak Khorram,et al.  Regional Scale Land Cover Characterization Using MODIS-NDVI 250 m Multi-Temporal Imagery: A Phenology-Based Approach , 2006 .

[53]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machines , 2002 .

[54]  David A. Landgrebe,et al.  HYPERSPECTRAL DATA ANALYSIS AND FEATURE REDUCTION VIA PROJECTION PURSUIT , 1999 .

[55]  Stephen V. Stehman,et al.  Design and Analysis for Thematic Map Accuracy Assessment: Fundamental Principles , 1998 .

[56]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[57]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[58]  David A. Landgrebe,et al.  Analyzing high-dimensional multispectral data , 1993, IEEE Trans. Geosci. Remote. Sens..