Abstract
Landuse/landcover (LULC) variations play a significant role in the
investigation and monitoring of worldwide alterations. LULC and regular adjustments
have generally brought about biodiversity misfortune, deforestation, an unnatural
weather change, and increased flood events. With the creation of GIS (Geographical
Information System) and remote sensing approaches, LULC planning has specified a
valuable and comprehensive approach to enhance the choice of zones intended for
industrial, urban, and agricultural regions of an area. Various strategies have been
designed for extracting information about the earth’s surface by means of image
classification, which are commonly divided as supervised and unsupervised
classification, based on the availability of reference data. In this chapter, the supervised
method of classification has been used to find the available classes. The land use/land
cover classification has been done for satellite images of 2000, 2009, 2014, and 2019
through ERDAS IMAGINE 2015 software. It has been identified that land use has
undergone major changes from the year 2000 – 2019. The drastic increase of the builtup
area or urban area was from 3.12% to 20.25%, an increase in vegetation area was
from 8.81% to 19.60%, an increase in water bodies was from 0.24% to 1.12%, while a
reduced land cover in agriculture was from 77.24% to 57.44% and a decrease in barren
land was from 10.59% to 1.59% from the year 2000 to 2019. This investigation clearly
reveals the critical influence of population and its advancement exercises on LULC
change. The current examination outlines that GIS and remote sensing are significant
advancements for temporal examination and measurement of spatial occurrence, which
is generally impractical to endeavor through ordinary planning strategies. Additionally,
in this chapter, an attempt has been made to predict the amount of power generation
through solar energy by installing solar panels in the identified barren land, which is
obtained by image processing technique. It is predicted that 3 MW of power equivalent
to around 4800 MWh of solar energy can be generated.
Keywords: Bina River Basin, GIS, LULC, Remote Sensing, Supervised Classification.