CROP AREA MAPPING BY INTELLIGENT PIXEL INFORMATION INFERRED USING 250M MODIS VEGETATION TIMESERIES IN TRANSBOUNDARY INDUS BASIN
Journal: Big Data In Water Resources Engineering (BDWRE)
Author: Muhammad Mohsin Khan, Muhammad Jehanzeb Masud Cheema, Talha Mahmood, Saddam Hussain, Muhammad Sohail Waqas, Hafiz Muhammad Nauman, Mohsin Nawaz, Muhammad Saifullah
This is an open access article distributed under the Creative Commons Attribution License CC BY 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited
Irrigation water could be managed properly by mapping area of various crops. Remote sensing data can provide useful Land Use Land Cover (LULC) for assessment of different crop area and change detection. The present study was carried out with core objective to map crop area within the Indus Basin’s transboundary. Four major crops (i.e. wheat, rice, cotton and sugarcane) were identified using Normalize Difference Vegetation Index (NDVI) time series that was picked up from MODIS sensors aboard Terra (EOS AM) and Aqua (EOS PM) satellites with 250m pixel resolution. Crop phonological information was used to train each pixel intelligently for interpretation of unanalyzed NDVI data into crops. Eight days of time series data was used for identification and mapping of various crops on the basis of their phenology for the years 2008, 2010 and 2013. Error matrix was prepared to reveal mapping accurateness and ground truthing was also done in particular canal commands within the Indus basin. Furthermore, the temporal variation in cropped area was determined and for accuracy check, secondary data was matched with prepared maps. LULC maps for year 2008, 2010 and 2013 were defined for Rabi and kharif seasons.