Decoding Urban Growth and Road Networks: Geospatial Insights from Bangalore’s Evolving Metropolis

Decoding Urban Growth and Road Networks: Geospatial Insights from Bangalore’s Evolving Metropolis

Webinar Speaker:

Rahisha Thottolil


IEEE GRSS – R10 Chapter Coordinator

About the Webinar

The rapid urbanization of Indian cities driven by economic liberalization and industry centric growth has resulted in significant transformation of land use and land cover within urban areas and their surrounding regions. This surge in urbanization has exerted substantial pressure on the management of urban land use and infrastructure, exacerbating environmental conditions and have given rise to complex social dynamics. Therefore, understanding the urban evolution and drivers of urban growth are vital for assessing the impacts of urban land use on sustainable urban development. We have utilized cutting-edge geospatial technologies to outline, measure, validate and forecast urban expansion, ultimately offering real-time solutions to address the challenges encountered by developing cities. Spatio-temporal patterns of urban expansion were analysed and quantified the shifts in growth patterns of urban hotspots attributed by specific events or triggers in Bangalore City. The outcomes suggested a decentralised approach for setting up new hubs for increasing economic activities in the form of satellite towns and shifting future industrial corridors to other small and medium-sized towns and cities. Moving forward in this direction, the Ministry of Urban Development, Government of India have already introduced an Integrated Development of Small and Medium Towns (IDSMT) scheme that aims to encourage the planned and sustainable growth of India’s small and medium-sized towns and cities. These smaller towns and cities may act as growth hubs for the nearby regions to promote inclusive growth and balance regional development. As an attempt to estimate the transportation infrastructure requirements (road network density) of future cities, we have used human settlement indices (landscape structures metrics) to predict transportation index. A novel two-step hybrid framework called RidgeGAN (Generative Adversarial Networks) is proposed by combining Kernel Ridge Regression (KRR) and CityGAN for predicting network density in both real and simulated cities. The experimental outcomes are aimed to assist the Government in making informed decisions in transportation development, thereby creating more liveable and sustainable areas. Through the interdisciplinary research on urban land use analysis, event triggered urban expansion, urban growth modelling, topological assessment of road networks and prediction of transportation measures, our research showcases the multifaceted nature of urbanization in the modern era. It is a step towards analysing current challenges in existing cities and predicting important metrics for sustainable future cities that would foster equity and resilient urban structures.

About the Speaker

Mrs. Rahisha Thottolil is pursuing PhD in Spatial Data Science from the Spatial Computing Laboratory, International Institute of Information Technology Bangalore (IIITB). She has received M.Tech degree in Geoinformatics (2016) from Visvesvaraya Technological University (VTU) and B.Tech in Civil Engineering (2009) from Government College of Engineering, Kannur. Her contribution was an integral part of shoreline prediction model in Mangalore region during her master thesis. She had research experience at the National Institute of Technology Calicut, CSIR Centre for Mathematical Modelling & Computer Simulation, Karnataka State Remote Sensing Applications Centre and Institute for Social and Economic Change. She has worked on various geospatial projects such as climate change and its impact studies and coastal zone management, multi-modal Vegetation Index analysis, Field Margin Vegetation mapping and urban studies. She received UGIT Young Technologist Award in 2015, University Honour in the 2014-2016 batch, best paper awards and authored several journal papers, book chapters and international conference papers. Her research interest includes Python for geospatial applications, AI & ML applications for spatial problems, urban sprawl, spatial pattern recognition to take on more challenging real-world problems in her research and strengthen her career as Geospatial Data Scientist.