Richa Sharma

Decision tree approach for classification of remotely sensed satellite data using open source support

In this study, an attempt has been made to develop a decision tree classification (DTC) algorithm for classification of remotely sensed satellite data (Landsat TM) using open source support. The decision tree is constructed by recursively partitioning the spectral distribution of the training dataset using WEKA, open source data mining software. The classified image is compared with the image classified using classical ISODATA clustering and Maximum Likelihood Classifier (MLC) algorithms. Classification result based on DTC method provided better visual depiction than results produced by ISODATA clustering or by MLC algorithms. The overall accuracy was found to be 90% (kappa = 0.88) using the DTC, 76.67% (kappa = 0.72) using the Maximum Likelihood and 57.5% (kappa = 0.49) using ISODATA clustering method. Based on the overall accuracy and kappa statistics, DTC was found to be more preferred classification approach than others.

Analysing spatio-temporal footprints of urbanization on environment of Surat city using satellite-derived bio-physical parameters

Our study examines the relationships among various environmental variables in Surat city using remote sensing. Landsat Thematic Mapper satellite data were used in conjugation with geospatial techniques to study urbanization and correlation among satellite-derived biophysical parameters namely, normalized difference vegetation index (NDVI), normalized difference built-up index (NDBI), normalized difference water index (NDWI), normalized difference bareness index (NDBaI) and land surface temperature (LST). A modified NDWI (MNDWI) was used for extracting areas under water. Land use/land cover classification was performed using hierarchical decision tree classification technique using ERDAS IMAGINE Expert classifier with an accuracy of 90.4% for 1990 and 85% for 2009. It was found that city has expanded over 42.75 sq.km within two decades. Built-up, fallow and sediment land use classes exhibited high dynamics with increase of nearly 200% and 50% and decrease of 55% respectively from 1990 to 2009. Vegetation and water classes were less dynamic with 20% decrease and 15% increase. The transformation of land parcels from vegetation to built-up, vegetation to fallow and fallow to built-up has resulted in increase of LST by 5.5 ± 2.6°C, 6.7 ± 3°C and 3.5 ± 2.9°C, respectively.

Analyzing Trends of Urbanization and Concomitantly Increasing Environmental Cruciality—A Case of the Cultural City, Kolkata

The environment in the city of Kolkata has suffered an extensive damage at hands of urban expansion. This study investigates the urban expansion in Kolkata over the last few decades and assesses its impact on environmental criticality using satellite derived parameters. An Environmental Cruciality Indicator (ECI) was developed using the vegetation indices and the land surface temperature (LST). Landsat TM and ETM+ data for the years 1989, 2006, and 2010 have been employed for this study. Land use land cover (LULC) maps were prepared using supervised classification with an accuracy of 86–90 % (0.82–0.87 kappa). Urban expansion amounting up to 109 km2 was observed in the city over the past two decades. These changes modified some other environmental variables such as the moisture intensity of the surface, LST, greenness, and the built-up intensity. These changes further impact the quality of environment that was analyzed using the ECI. The indices used were Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index (NDWI), and Normalized Difference Built-up Index (NDBI). Satellite derived ECI shows a degrading trend for environment in larger parts of the city. The magnitude and spatial extent of higher environmental cruciality are coherent with the urbanization (sparse and dense settlement) patterns in and around the city. LULC has been an important factor determining the health of the environment and hence influencing the local climate.

The Changing Urban Landscape and Its Impact on Local Environment in an Indian Megacity: The Case of Delhi

This chapter presents urbanizing scenario of the megacity, Delhi. The changing land use land cover (LULC) and various environmental variables are discussed using the conjugation of space remote sensing inputs, geospatial analysis and statistical analysis. The two vital components of LULC viz., urban land use and fraction of green cover are important to demonstrate changing urban landscape and its impact on environmental quality. The environmental quality variables like greenness, imperviousness due to built-up intensity, moisture intensity, and bareness can be retrieved from remote sensing data. A general trend of diminishing greenness, especially along the peripheral areas with depleting moisture intensity of the city surface is a common phenomenon. The new industrial developments in the northern and urban expansion in the south-western parts of the city results in drastic and slight decline in moisture respectively. This is accompanied with increase in imperviousness and bareness in some cases in the same areas. The chapter explains the complex interactions between different land uses over the progression of urbanisation explaining the process in details taking Delhi as an example. Eventually the basis for environmental degradation and formation of Urban Heat Island (UHI) in the city is also explained using LULC and environmental variables and their change statistics. The chapter thus presents the process and impacts of urban land transformations in the metropolitan city of a developing nation, India in this case.