Analyzing Urban Sprawl Through Aerial Views of Satellite Imagery using Geospatial Analysis with Generative AI

View at publisher Summarise with VIRAT
Authors: L.Manjula, Prabhavathi K, I. Sakthidevi, S.Sujatha, R. Divya, Sangeetha Sri S
Cited by: 0
References: 23

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Urbanization has drastically altered the landscape, impacting the built environment, vegetation, and water supply. This paper compares satellite imagery from March 2020 and March 2025 to provide a comprehensive analysis of urban expansion in Hyderabad. In this work, Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index (NDWI), Normalized Difference Built-up Index (NDBI), and Urban Sprawl Index (USI) were used to quantify changes in building density, vegetation loss, and water resource depletion. The images are processed using Python libraries such as Rasterio, NumPy, and Matplotlib to gain valuable insights using thresholding and index-based classification methods. The results highlight the need for sustainable urban planning by showing a noticeable increase in built-up areas and a significant decrease in vegetation and water coverage. A unique feature of the proposed approach is the inclusion of ChatGPT to understand and categorize these changes in natural language. ChatGPT helps both experts and non-experts better understand the environmental consequences by providing easy-to-understand summaries of NDVI, NDWI, and density variations over time. The proposed work demonstrates how generative AI and geospatial analysis can be combined to enable well-informed decision-making in environmental management and urban development.

Fields of Study & Subjects

Remote Sensing and Land Use Remote-Sensing Image Classification Land Use and Ecosystem Services

Publication details

Journal / source
International Conference on Image Processing and Capsule Networks (ICIPCN)
Pages
522–527
Publication date
27 January 2026
Language
EN