Using Time-Series NDVI to Model Land Cover Change: A Case Study in the Berg River Catchment Area, Western Cape, South Africa
This study investigates the use of a time-series of
MODIS NDVI data to identify agricultural land cover change on an
annual time step (2007 - 2012) and characterize the trend. Following
an ISODATA classification of the MODIS imagery to selectively
mask areas not agriculture or semi-natural, NDVI signatures were
created to identify areas cereals and vineyards with the aid of
ancillary, pictometry and field sample data for 2010. The NDVI
signature curve and training samples were used to create a decision
tree model in WEKA 3.6.9 using decision tree classifier (J48)
algorithm; Model 1 including ISODATA classification and Model 2
not. These two models were then used to classify all data for the
study area for 2010, producing land cover maps with classification
accuracies of 77% and 80% for Model 1 and 2 respectively. Model 2
was subsequently used to create land cover classification and change
detection maps for all other years. Subtle changes and areas of
consistency (unchanged) were observed in the agricultural classes
and crop practices. Over the years as predicted by the land cover
classification. Forty one percent of the catchment comprised of
cereals with 35% possibly following a crop rotation system.
Vineyards largely remained constant with only one percent
conversion to vineyard from other land cover classes.
[1] D. Yacouba, H. Guangduo and W. Xingping, Assessment of land cover /
land use changes using NDVI and DEM in Puer & Sima Counties
Yuman Province China. World Rural Observations 1(2): 1-11, 2009.
[2] B. D. Wardlow and S. L. Egebert. Large area crop mapping using timeseries
MODIS 250m NDVI data: An assessment for the US Central
Great Plains. Remote Sensing of Environment 112: 1096-1116, 2008.
[3] J. C. Brown et al., Classifying multilayer agricultural land use data from
mato grosso using time series MODIS vegetation index data. Remote
Sensing of Environment 130: 39-50, 2013.
[4] T. Stuckenberg, Land cover change in the Berg river catchment area,
2012.
[5] C. O. Justice and J. R. G. Townshend JRG, Special issue on Moderate
Resolution Imaging Spectroradiometer (MODIS): A new generation of
land surface monitoring. Remote Sensing of Environment 83:1-2, 2002.
[6] B. D. Wardlow, S. L. Egebert and J. H. Kastens JH, Analysis of timeseries
MODIS 250m vegetation index data for crop classification in the
US Central Plains. Remote Sensing of Environment 108: 290-310, 2007.
[7] R. S. Lunneta et al., Land cover change detection using multi-temporal
MODIS NDVI data. Remote Sensing of Environment 105:142-154,
2006.
[8] B. D. Wardlow and S. L. Egebert, A comparison of MODIS 250m EVI
and NDVI data for crop mapping: Case study for south west Kansas.
International Journal of Remote Sensing 31(3): 805-830, 2010.
[9] R. R. Colditz, Time series generation and classification of MODIS data
for land cover Mapping, 2007.
[10] X. Zhang et al., Monitoring vegetation phenology using MODIS.
Remote Sensing of Environment 84: 471-475, 2003.
[11] J. B. Campbell and R. H. Wynne, Introduction to remote sensing 5th ed.
The Guilford Press. New York, 2011.
[12] W. Lück,. CSIR Satellite Application Centre: Earth Observation Service
Centre Land cover class definition report. Pretoria: CSIR, 2006.
[1] D. Yacouba, H. Guangduo and W. Xingping, Assessment of land cover /
land use changes using NDVI and DEM in Puer & Sima Counties
Yuman Province China. World Rural Observations 1(2): 1-11, 2009.
[2] B. D. Wardlow and S. L. Egebert. Large area crop mapping using timeseries
MODIS 250m NDVI data: An assessment for the US Central
Great Plains. Remote Sensing of Environment 112: 1096-1116, 2008.
[3] J. C. Brown et al., Classifying multilayer agricultural land use data from
mato grosso using time series MODIS vegetation index data. Remote
Sensing of Environment 130: 39-50, 2013.
[4] T. Stuckenberg, Land cover change in the Berg river catchment area,
2012.
[5] C. O. Justice and J. R. G. Townshend JRG, Special issue on Moderate
Resolution Imaging Spectroradiometer (MODIS): A new generation of
land surface monitoring. Remote Sensing of Environment 83:1-2, 2002.
[6] B. D. Wardlow, S. L. Egebert and J. H. Kastens JH, Analysis of timeseries
MODIS 250m vegetation index data for crop classification in the
US Central Plains. Remote Sensing of Environment 108: 290-310, 2007.
[7] R. S. Lunneta et al., Land cover change detection using multi-temporal
MODIS NDVI data. Remote Sensing of Environment 105:142-154,
2006.
[8] B. D. Wardlow and S. L. Egebert, A comparison of MODIS 250m EVI
and NDVI data for crop mapping: Case study for south west Kansas.
International Journal of Remote Sensing 31(3): 805-830, 2010.
[9] R. R. Colditz, Time series generation and classification of MODIS data
for land cover Mapping, 2007.
[10] X. Zhang et al., Monitoring vegetation phenology using MODIS.
Remote Sensing of Environment 84: 471-475, 2003.
[11] J. B. Campbell and R. H. Wynne, Introduction to remote sensing 5th ed.
The Guilford Press. New York, 2011.
[12] W. Lück,. CSIR Satellite Application Centre: Earth Observation Service
Centre Land cover class definition report. Pretoria: CSIR, 2006.
@article{"International Journal of Earth, Energy and Environmental Sciences:69943", author = "A. S. Adesuyi and Z. Munch", title = "Using Time-Series NDVI to Model Land Cover Change: A Case Study in the Berg River Catchment Area, Western Cape, South Africa", abstract = "This study investigates the use of a time-series of
MODIS NDVI data to identify agricultural land cover change on an
annual time step (2007 - 2012) and characterize the trend. Following
an ISODATA classification of the MODIS imagery to selectively
mask areas not agriculture or semi-natural, NDVI signatures were
created to identify areas cereals and vineyards with the aid of
ancillary, pictometry and field sample data for 2010. The NDVI
signature curve and training samples were used to create a decision
tree model in WEKA 3.6.9 using decision tree classifier (J48)
algorithm; Model 1 including ISODATA classification and Model 2
not. These two models were then used to classify all data for the
study area for 2010, producing land cover maps with classification
accuracies of 77% and 80% for Model 1 and 2 respectively. Model 2
was subsequently used to create land cover classification and change
detection maps for all other years. Subtle changes and areas of
consistency (unchanged) were observed in the agricultural classes
and crop practices. Over the years as predicted by the land cover
classification. Forty one percent of the catchment comprised of
cereals with 35% possibly following a crop rotation system.
Vineyards largely remained constant with only one percent
conversion to vineyard from other land cover classes.", keywords = "Change detection, Land cover, NDVI, time-series.", volume = "9", number = "5", pages = "545-6", }