Monitoring Sahelian floodplains using Fourier analysis of MODIS time‐series data and artificial neural networks

Fourier analysis of Moderate Resolution Image Spectrometer (MODIS) time‐series data was applied to monitor the flooding extent of the Waza‐Logone floodplain, located in the north of Cameroon. Fourier transform (FT) enabled quantification of the temporal distribution of the MIR band and three different indices: the Normalized Difference Vegetation Index (NDVI), the Normalized Difference Water Index (NDWI), and the Enhanced Vegetation Index (EVI). The resulting amplitude, phase, and amplitude variance images for harmonics 0 to 3 were used as inputs for an artificial neural network (ANN) to differentiate between the different land cover/land use classes: flooded land, dry land, and irrigated rice cultivation. Different combinations of input variables were evaluated by calculating the Kappa Index of Agreement (KIA) of the resulting classification maps. The combinations MIR/NDVI and MIR/EVI resulted in the highest KIA values. When the ANN was trained on pixels from different years, a more robust classifier was obtained, which could consistently separate flooded land from dry land for each year.

[1]  A. Huete,et al.  Overview of the radiometric and biophysical performance of the MODIS vegetation indices , 2002 .

[2]  D. Legates,et al.  Crop identification using harmonic analysis of time-series AVHRR NDVI data , 2002 .

[3]  M. J. Burgis,et al.  African wetlands and shallow water bodies = Zones humides et lacs peu profonds d'Afrique , 1987 .

[4]  T. M. Lillesand,et al.  Remote Sensing and Image Interpretation , 1980 .

[5]  P. Xie,et al.  Global Precipitation: A 17-Year Monthly Analysis Based on Gauge Observations, Satellite Estimates, and Numerical Model Outputs , 1997 .

[6]  P. Atkinson,et al.  Introduction Neural networks in remote sensing , 1997 .

[7]  B. Gao.  NDWI—A normalized difference water index for remote sensing of vegetation liquid water from space , 1996 .

[8]  M. Menenti,et al.  Assessment of climate impact on vegetation dynamics by using remote sensing , 2003 .

[9]  R. Singleton.  An algorithm for computing the mixed radix fast Fourier transform , 1969 .

[10]  Massimo Menenti,et al.  Mapping vegetation-soil-climate complexes in southern Africa using temporal Fourier analysis of NOAA-AVHRR NDVI data , 2000 .

[11]  Patrick Denny,et al.  The ecology and management of African wetland vegetation , 1985, Geobotany.

[12]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[13]  Jude H. Kastens,et al.  Time Series Remote Sensing of Landscape-Vegetation Interactions in the Southern Great Plains , 2002 .

[14]  Paul Scholte,et al.  Floodplain rehabilitation in North Cameroon: Impact on vegetation dynamics , 2000 .

[15]  K. Tockner,et al.  Riverine flood plains: present state and future trends , 2002, Environmental Conservation.

[16]  Yong Wang,et al.  Delineation of inundated area and vegetation along the Amazon floodplain with the SIR-C synthetic aperture radar , 1995, IEEE Trans. Geosci. Remote. Sens..

[17]  Frieke Vancoillie.  Design and application of artificial neural networks for digital image classification of tropical savanna vegetation , 2003 .

[18]  L. Eklundh,et al.  Fourier series for analysis of temporal sequences of satellite sensor imagery , 1994 .

[19]  P. Loth,et al.  The return of the water: restoring the Waza Logone floodplain in Cameroon. , 2004 .

[20]  Aaron Moody,et al.  Land-Surface Phenologies from AVHRR Using the Discrete Fourier Transform , 2001 .

[21]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[22]  L. P. C. Verbeke,et al.  Reusing back-propagation artificial neural networks for land cover classification in tropical savannahs , 2004 .

[23]  D. Roy,et al.  An overview of MODIS Land data processing and product status , 2002 .