A hierarchical approach of hybrid image classification for land use and land cover mapping

Abstract

Remote sensing data analysis can provide thematic maps describing land-use and land-cover (LULC) in a short period. Using proper image classification method in an area, is important to overcome the possible limitations of satellite imageries for producing land-use and land-cover maps. In the present study, a hierarchical hybrid image classification method was used to produce LULC maps using Landsat Thematic mapper TM for the year of 1998 and operational land imager OLI for the year of 2016. Images were classified using the proposed hybrid image classification method, vegetation cover crown percentage map from normalized difference vegetation index, Fisher supervised classification and object-based image classification methods. Accuracy assessment results showed that the hybrid classification method produced maps with total accuracy up to 84 percent with kappa statistic value 0.81. Results of this study showed that the proposed classification method worked better with OLI sensor than with TM. Although OLI has a higher radiometric resolution than TM, the produced LULC map using TM is almost accurate like OLI, which is because of LULC definitions and image classification methods used.

Impacts of spatio-temporal change of landscape patterns on habitat quality across Zayanderud Dam watershed in central Iran

“…The Zayanderud Dam watershed gives the highest part of water yield. The average temperature of the basin is 8–13 °C with 350–1250 mm precipitation 23 . This region used to have a significant capacity for livestock grazing, with its primary LU/LC being forests and rangelands.…”

“…The destruction of natural forests and rangelands has been driven by economic growth, mainly related to the expansion of agricultural land and build-up development. LUC in the Zayanderud Dam watershed has an incredibly damaging effect on natural forests and rangelands, as well as on the expansion of agricultural and construction areas 23 . The study has concentrated only on the spatial distribution of habitat quality due to time and cost constraints.…”

Are the Sundarbans, the World's largest mangroves region under threat?—An ecosystem‐based geospatial approach to assess changes past, present, and future in relation to natural and human‐induced factors

“…The hybrid classification approach, for example, maximum likelihood supervised classification followed by on‐screen visual interpretation/correction, was chosen to delineate the different land and water classes in the Sundarbans region using spatial tools in ArcGIS 10.6. Using a hybrid approach, the errors are eliminated to make sure that land types are classified from coarse‐resolution images with more precision (Rahdari et al, 2018).…”

Dynamics of land‐use changes and their future trends using spatial analysis and the CA‐Markov model—A case‐study with a special emphasis on aquaculture development in India

“…Researchers have used a hybrid classification approach while using LANDSAT images to delineate the land‐use classes (Kumar, Singh, & Rani, 2013). By adopting a hybrid approach, we eliminate human errors and also make sure that land types are classified with more accuracy from medium resolution images (Rahdari, Soffianian, Pourmanafi, Mosadeghi, & Ghaiumi, 2018). Researchers observed that the hybrid approach could be applied in a regular image processing software package (ERDAS Imagine) to make land‐use maps with higher accuracy from satellite images of moderate spatial resolution, where both discrete and continuous land‐use types occur side by side (Mas et al, 2017).…”