Analyzing Urbanization using Satellite Image Processing

Abstract

Urbanization is directly proportional to the increase in population, which contributes to the increase in country’s GDP but affects the environment and ecosystem. This paper introduces an analysis of the satellite imagery of Mumbai for past 5 years (2019-2023). Mumbai has witnessed significant changes in the geographic region. In order to control and prevent the effects of urbanization, it is necessary to analyze the geographical changes and effects of the same. In this proposed analysis, we have analyzed urbanization with respect to changes in water, forest, urban land and barren land. Use of satellite imagery plays an important role in providing the opportunity for this analysis. Google Earth Engine (GEE) is used for the change detection for the selected area using the satellite imagery dataset provider COPERNICUS named Harmonized Sentinel-2 MSI as an input to this analysis. For this analysis we have used 3 classification methods i.e. supervised, unsurprised and NDVI.

Introduction

I. INTRODUCTION

Urbanization plays a vital role in contributing in country’s economy’s GDP. In 1950 the occupants of Mumbai were 3,088,811, which grew up to 21,673,149 in the year 2024.Urbanization is directly proportional to population growth and urban expansion. This growth has led to changes in land use patterns, affecting natural resources such as water bodies, forests, and agricultural land.

Mumbai, as one of India's largest and most crowded cities, represents the dynamics of urbanization. Over the past decades, Mumbai has experienced unprecedented population growth, fueled by factors such as rural to urban migration, industrialization, and financial openings. This demographic shift has led to the expansion of urban infrastructure, increased demand for housing, and increased pressure on natural resources. Understanding these changes and their implications is crucial for sustainable development and environmental management.

The use of satellite imagery and remote sensing technologies has revolutionized our ability to monitor and analyze urbanization trends.

This research highlights the urbanization over the past 5 years using Google Earth Engine (GEE). To perform supervised and unsupervised classification for detecting changes in land cover types i.e. land, water, barren land, urban land and NDVI (Normalized Difference Vegetation Index) here by awakening the Government bodies to take necessary action upon the analysis.

II. LITERATURE SURVEY

The paper titled “Review on The Impact of Satellite Imagery in Urban Policy Planning” by Md. Rakin Sarder Arko1, Mohammed Raihanul Bashar1, Amin A Ali1, Moinul Zaber2, Md Abu Sayed. This paper reviews some of the works done in the field of satellite image sensing-based policy planning, and how they can be fitted into urban settings for faster and effective decision making. Rapid urbanization due to population growth and migration in the past decades had a consequence on the overall planning of the urban areas. Policy planning schemes are now more developing than the past. Satellite remote sensing data can provide enough evidence at a large scale to come to a policy interpretation. Impact analysis of how different researchers in this sector have created a positive impact on different policy planning has been conducted in this research.

The paper titled” Change Detection in Urban Areas using Satellite Data” by M.A. Al-Dail. Satellite data can be regarded as a powerful tool for providing information for urban monitoring that can be used by urban and regional planners in fraction of the cost and time compared to traditional methods (e.g. Aerial photos or field survey). However, most of the methods used in the literature to process such data will need a considerable time and experience. This has limited the application of such technology, since such experience is not always available in urban development sector of the community.

The study was conducted over the city of Riyadh, central Saudi Arabia, to test a simple Image Difference (ID) technique for urban change detection.

Landsat Thematic Mapper (LTM) data on 21 July, 1987 and 15 September, 1996 and SPOT Panchromatic Linear Array (PLA) data on 2 August, 1996 were acquired over the study area. The change detection using image difference procedure involves:

(i) Spatial registration of multi-temporal data sets collected by the different sensors,

(ii) Image difference was then used to detect changes in urban areas which enable the detection of changes in brightness values using Pixel by Pixel subtraction of the registered data sets.

Three small sub-scenes from the whole study area were generated to evaluate the method in more details. It was found that such technique emphasizes temporal changes and provides an excellent and easy to interpret first level indication of change in urban areas.

III. STUDY AREA

The population of Mumbai, which is one of the foremost crowded cities in India, is 21.6 million agreeing to 2024 information, and the population development rate is 1.77‰ [4]. Mumbai, moreover called Bombay, is the capital city of the state of Maharashtra in India, and it's the foremost crowded city in India. Mumbai is 4th most crowded city within the world and one of the crowded urban districts within the world.

Conclusion

This research demonstrates the utility of satellite imagery and remote sensing techniques in analyzing urbanization effects. The research shows how Mumbai Urbanized from the year 2019 to 2023 using satellite images. The smileCart classifier showed that cities grew a lot, replacing forests and barren land with buildings. This is clear in our maps and charts. It\'s important to think about how this affects the environment, aiding decision-makers in sustainable urban development planning and conservation efforts.

References

[1] Kaya, Zelal & Dervisoglu, Adalet. (2023). Determination of Urban Areas Using Google Earth Engine and Spectral Indices; Esenyurt Case Study. International Journal of Environment and Geoinformatics. 10. 1-008. 10.30897/ijegeo.1214001. [2] Aryal, Anisha, Kishor Prasad Bhatta, Sanot Adhikari, and Himlal Baral. 2023. \"Scrutinizing Urbanization in Kathmandu Using Google Earth Engine Together with Proximity-Based Scenario Modelling\" Land 12, no. 1: 25. https://doi.org/10.3390/land12010025. [3] Sarder, Md Rakin & Bashar, Mohammed & Ali, Amin & Moinul, Zaber. (2018). A Review on The Impact of Satellite Imagery in Urban Policy Planning. 10.1109/ICIEVicIVPR43342.2018. [4] Mumbai, India Metro Area Population 1950-2024.www.macrotrends.net. https://www.macrotrends.net/global-metrics/cities/21206/mumbai/population [5] ???????, ??????? & Latue, Philia Christi. (2023). Monitoring Urban Sprawl in Ambon City Using Google Earth Engine. 1. 88-100. [6] Kuc, G. & Chormanski, Jaroslaw. (2019). SENTINEL-2 IMAGERY FOR MAPPING AND MONITORING IMPERVIOUSNESS IN URBAN AREAS. ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. XLII-1/W2. 43-47. 10.5194/isprs-archives-XLII-1-W2-43-2019.

Copyright

Copyright © 2024 Soham Pawar, Asim Dakhway, Arfaat Hashmi, Rishika Tripathi, Chhaya Dhavale. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.