Shubham Pawar

Shubham Pawar

PhD Researcher at the University of Stirling

Publications

You can also find my articles on my Google Scholar profile.

Analysis of Residential Location Choices of Different Socio-Economic Groups and Their Impact on the Density in a City Using Agent Based Modelling

Published in Applied Spatial Analysis and Policy, 2022

Urban settlement patterns are shaped by human decision-making during land development. This study proposes an Agent-Based Model (ABM) for residential location choice, integrating socioeconomic data and development suitability factors such as road networks, water supply, amenities, and land rates. Household data is interpolated using census and health survey records, while development suitability is modeled through regression analysis. Simulating residential choices from 2003 to 2019, the model achieved 60% accuracy with Random Forest regression and 53% with Logistic Regression. Findings reveal a socioeconomic divide in urban residential patterns, influenced by the distribution of amenities and services.

Recommended citation: Pawar, S. and Jha, A.K., 2023. Analysis of Residential Location Choices of Different Socio-Economic Groups and Their Impact on the Density in a City Using Agent Based Modelling. Applied Spatial Analysis and Policy, 16(1), pp.119-139.
Download Paper

Prediction of waterlogged zones under heavy rainfall conditions using machine learning and GIS tools: a case study of Mumbai

Published in GeoJournal, 2022

Flooding is a recurrent issue in coastal Indian cities like Mumbai and Chennai. This study employs machine learning techniques, including Logistic Regression, Support Vector Machines, K-Nearest Neighbour (KNN), Random Forest, and Gradient Boosting, to predict flood occurrences in Mumbai. Using historical flood events and contributing factors processed through GIS tools, the models classify flood risk with KNN achieving the highest accuracy (84%), followed by Random Forest (81%). Our model successfully identified flood-prone locations in August 2020, offering valuable insights for flood mitigation and relief planning.

Recommended citation: Khatri, S., Kokane, P., Kumar, V. and Pawar, S., 2023. Prediction of waterlogged zones under heavy rainfall conditions using machine learning and GIS tools: a case study of Mumbai. GeoJournal, 88(Suppl 1), pp.277-291.
Download Paper