Answers are grounded in this paper and cite their sources.
An automated knowledge-based classifier has been developed to decipher wetland features (water, aquatic vegetation- floating as well as submerged, mud flats) in Nal-Sarovar wetland, Gujarat, India from Resourcesat-1 LISS-III data acquired on November 24, 2005. Water has further been classified into three qualitative turbidity classes (low turbid, moderate turbid and high turbid). Same dataset has also been classified for wetland features using Maximum Likelihood classifier. Comparison of the results has brought out that overall accuracy of wetland feature delineation and Kappa statistic of Knowledge based classifier (87.78% and 0.85) are better in comparison to MXL classifier derived wetland features (80.22% and 0.76). Estimated total area of wetland features in Nal Sarovar using knowledge based and MXL classifiers is 106.138 sq. km and 123.951 sq. km respectively out of 139.24 sq. km wetland area.
No takes yet. Share an insight, caveat, or question.
Sethwala et al. (2010) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: