Predictive Urban Growth Planning for a Mid-Size City Bhilwara Using Geospatial Analysis & AI-based Techniques

Abstract

The rapid urbanization of Bhilwara City, Rajasthan, has posed serious difficulties for infrastructure, sustainable development & resource management . Traditional urban planning methods often fall short of anticipating future urban growth, leading to unplanned expansion and inefficient resource allocation. This research proposes a datacentric approach to predict and guide urban development in Bhilwara using advanced Geographic Information Systems (GIS), remote sensing, Artificial Intelligence (AI), and Machine Learning (ML) techniques. By integrating spatial remote sensing data and GIS with AI-driven predictive models, this study aims to simulate future growth patterns, assess infrastructure needs, and optimize resource distribution for Bhilwara as it evolves into a smart city. The research methodology involves collecting high-resolution spatial data through remote sensing, which will be processed and analyzed within a GIS framework. Machine learning algorithms will be employed to develop predictive models that simulate various growth scenarios, allowing for informed decision-making on infrastructure development and urban resource planning. The study gives policymakers a strong decision support tool to predict population increase, change in land use ,and infrastructure demands by visualizing these projections. This interdisciplinary approach ensures that the city\'s expansion is not only anticipated but strategically planned to enhance liveability, sustainability, and smart city initiatives. The findings of this research will contribute to more systematic, predictive approach to urban planning, ensuring that Bhilwara’s development is aligned with modern smart city standards while addressing the local context\'s unique challenges. Ultimately, this project’s goal is to fill the gap between data-driven forecasts and actual implementations of urban policies.

Introduction

Urbanization is accelerating globally, particularly in developing countries like India. Cities face critical challenges such as infrastructure deficits, environmental stress, and unplanned growth due to reactive planning methods and incomplete data. Traditional urban planning is insufficient to cope with the dynamic pace of urban growth.

To address this, cities—including Bhilwara, Rajasthan—are exploring data-driven, predictive planning using Geographic Information Systems (GIS), Remote Sensing, Artificial Intelligence (AI), and Machine Learning (ML). These tools enable smarter planning by predicting growth patterns, optimizing resources, and supporting sustainable development.

2. Case Focus: Bhilwara City

• Bhilwara, known for its textile industry, has seen rapid and unregulated urban expansion, leading to problems such as traffic congestion, poor infrastructure, and inefficient resource use.

• With aspirations of becoming a smart city, Bhilwara requires predictive planning to guide future growth using advanced modelling techniques.

3. Technological Integration

GIS

• Captures and analyzes spatial data like land use, population, and infrastructure.

• Allows planners to overlay multiple datasets for better insights and scenario visualization.

Remote Sensing

• Provides real-time, high-resolution imagery for monitoring urban sprawl.

• Enhances GIS models with updated land use and environmental data.

AI & ML

• Analyze massive datasets (e.g., satellite images, census, infrastructure).

• Predict future urban growth, traffic patterns, and resource needs.

• Models like Random Forest, SVM, and Neural Networks are effective for forecasting due to their ability to capture non-linear trends.

4. Predictive Urban Planning

This research proposes a decision-support system that uses:

• Historical and real-time spatial data

• AI/ML models for forecasting

• Simulation tools for visualizing future growth scenarios

• Policy recommendations based on predicted needs

5. Literature Review & Research Gaps

• Prior studies validate the role of GIS, remote sensing, and AI in urban planning.

• Gaps remain in applying these tools to mid-sized cities like Bhilwara, especially with:

  • Limited data availability

  • Lack of interdisciplinary approaches

  • Insufficient focus on ethical and governance concerns

  • Integration challenges in developing countries

6. Research Objectives

1. Develop a predictive model for Bhilwara’s urban growth.

2. Simulate infrastructure needs based on predicted expansion.

3. Provide policy suggestions for sustainable urban planning.

7. Methodology

A. Model Development

• Combines GIS, Remote Sensing, and AI/ML.

• Extracts features like land use, population density, and infrastructure from spatial data.

• Applies ML algorithms (Random Forest, SVM, CNNs, RNNs) to train prediction models.

B. Data Processing

• Feature extraction, normalization, and scaling for model compatibility.

• Uses historical urban data to train and test models.

C. Model Validation

• Techniques: Cross-validation, performance metrics like MAE, RMSE, R².

• Compared against baseline models to assess improvements.

D. Model Refinement

• Iterative improvement of features, parameters, and algorithms based on validation performance.

8. Expected Outcomes

• A robust model to predict Bhilwara’s future growth patterns.

• Simulated infrastructure planning scenarios.

• AI-informed policy suggestions to promote smart, sustainable urban development.

9. Future Scope

• Scalability to other mid-sized cities.

• Incorporate technological advancements (e.g., improved remote sensing, new AI methods).

• Develop strategies for long-term sustainability, including regular model updates and interdisciplinary collaboration.

10. Study Area: Bhilwara Overview

• Location: Southern Rajasthan, ~250 km from Jaipur.

• Population: ~400,000 and growing rapidly.

• Growth Drivers: Industrialization (mainly textiles), residential sprawl, and infrastructure development.

References

[1] Gupta, S. N., Arora, Y. K., Mathur, R. K., Iqbal Uddin, B. P., Sahai, T. N., Sharma, S. B., & Murthy, M. V. N. (1980). Lithostratigraphic map of Aravalli region, southern Rajasthan and northeastern Gujarat. Geol. Surv. India, Hyderabad. [2] S. L. Borana, A. Vaishnav, S. K. Yadav, and S. K. Parihar, \"Urban Growth Assessment Using Remote Sensing, GIS and Shannon’s Entropy Model: A Case Study of Bhilwara City, Rajasthan,\" in Proc. 2020 3rd Int. Conf. Emerging Technologies in Computer Engineering: Machine Learning and Internet of Things (ICETCE), Jaipur, India, 2020, pp. 1-6, doi: 10.1109/ICETCE48199.2020.9091771. [3] T. Ghosh, A. Chattopadhyay, G. Verma, S. Srivastava, A. Sarkar, and D. Bhattacharjee, \"Digital mapping and GIS-based spatial analyses of the Pur-Banera Group in Rajasthan, India, with special reference to the structural control on base-metal mineralization,\" J. Struct. Geol., vol. 166, p. 104762, 2023. [4] M. Batty, \"Defining Urban Science,\" in Urban Informatics, W. Shi, M. F. Goodchild, M. Batty, M. P. Kwan, and A. Zhang, Eds., Singapore: Springer, 2021, pp. 31-46, doi: 10.1007/978-981-15-8983-6_3. [5] P. Xie, T. Li, J. Liu, S. Du, X. Yang, and J. Zhang, \"Urban flow prediction from spatiotemporal data using machine learning: A survey,\" Inf. Fusion, vol. 59, pp. 1-12, 2020. [6] Y. Zhou, T. Wu, and Y. Wang, \"Urban expansion simulation and development-oriented zoning of rapidly urbanising areas: A case study of Hangzhou,\" Sci. Total Environ., vol. 807, p. 150813, 2022. [7] Y. Song, M. Kalacska, M. Gašparovi?, J. Yao, and N. Najibi, \"Advances in geocomputation and geospatial artificial intelligence (GeoAI) for mapping,\" Int. J. Appl. Earth Obs. Geoinformation, vol. 120, p. 103300, 2023. [8] R. Ghosh and D. Sengupta, \"Smart urban metabolism: a big-data and machine learning perspective,\" in Urban Metabolism and Climate Change: Perspective for Sustainable Cities, Cham: Springer International Publishing, 2023, pp. 325-344. [9] E. Mostafa, X. Li, M. Sadek, and J. F. Dossou, \"Monitoring and forecasting of urban expansion using machine learning-based techniques and remotely sensed data: A case study of Gharbia governorate, Egypt,\" Remote Sens., vol. 13, no. 22, p. 4498, 2021. [10] Y. L. U., X. U. Sun, L. I. U. Songxue, and J. U. Jiayu, \"An approach to urban landscape character assessment: Linking urban big data and machine learning,\" Sustainable Cities Soc., vol. 83, p. 103983, 2022. [11] H. Xia, Z. Liu, M. Efremochkina, X. Liu, and C. Lin, \"Study on city digital twin technologies for sustainable smart city design: A review and bibliometric analysis of geographic information system and building information modelling integration,\" Sustainable Cities Soc., vol. 84, p. 104009, 2022.

Copyright

Copyright © 2025 Richa Sharma, Vikas Somani. 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.