An AI-Driven Framework for Urban Heat Island (UHI) Analysis and Mitigation Simulation in Bengaluru

References

[1] T. Ramachandra and U. Kumar, “Greater bangalore: Emerging urban heat island,” GIS India, vol. 4, no. 8, pp. 1–12, 2010.

[2] H. E. Sussman, “The urban heat island of bengaluru, india: Charac- teristics, trends, and mechanisms,” Ph.D. dissertation, Yale University, 2022.

[3] D. Zhou, J. Xiao, S. Bonafoni, C. Berger, K. Deilami, Y. Zhou, S. Frolking, R. Yao, Z. Qiao, and J. A. Sobrino, “Satellite remote sensing of surface urban heat islands: Progress, challenges, and perspectives,” Remote Sensing, vol. 11, no. 1, p. 48, 2019.

[4] M. Mohan, S. Gunthlia, and S. K. Singh, “Urban heat island effect in megacity delhi, india using satellite-derived land surface temperature and meteorological parameters,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 13, pp. 629–637, 2020.

[5] K. Gowda, L. S. R. Kumar, V. V. Raj, and V. S. R. R. L. V. R. Kumar, “Analysis of uhi over bengaluru using landsat data,” in 2015 IEEE International Conference on Technological Advancements in Power and Energy (TAP Energy). IEEE, 2015, pp. 410–415.

[6] A. Mathew, S. Khandelwal, and N. Kaul, “Investigating spatial and temporal urban heat island effect over jaipur city using geospatial techniques,” in 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS). IEEE, 2016, pp. 5744–5747.

[7] S. Guha, H. Govil, and P. Diwan, “Monitoring the land surface temper- ature and urban heat island over a semi-arid city using landsat data,” Journal of the Indian Society of Remote Sensing, vol. 48, no. 4, pp. 585–601, 2020.

[8] Q. Weng, D. Lu, and J. Schubring, “Estimation of land surface temperature–vegetation abundance relationship for urban heat island studies,” Remote sensing of Environment, vol. 89, no. 4, pp. 467–483, 2004.

[9] F. Salata, I. Golasi, R. de Lieto Vollaro, and M. Coppi, “Decision support systems for urban planning: integration of multi-criteria analysis and energy simulation,” Sustainable Cities and Society, vol. 26, pp. 146– 153, 2016.

[10] A. Karimi, A. M. Beni, E. Rodriguez-Ubinas, L. Ruiz-Valero, and S. Soutullo, “Granular mapping of uhi and heatwave effects: Impli- cations for building performance and urban resilience,” Building and Environment, vol. 273, p. 112705, 2025.

[11] J. Yang, Y. Wang, C. Xiu, X. Xiao, J. Xia, and C. Jin, “Simulating the impacts of urban expansion on surface urban heat islands and landscape pattern using a cellular automata based model in the greater toronto area, canada,” Sustainable Cities and Society, vol. 61, p. 102319, 2020.

[12] S.-B. Duan, Y. Lian, Z. Wu, P. Chen, and Z.-L. Li, “A novel approach to all-weather lst estimation using xgboost model and multisource data,” IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1– 13, 2023.

[13] Y. Liu, J. Li, and J. Fang, “Prediction of urban heat island using xgboost and remote sensing data,” in 2019 10th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS), vol. 1. IEEE, 2019, pp. 433–437.

[14] H. H. Le, L. H. Nguyen, and T. M. Bui, “Application of machine learning for land surface temperature prediction from remote sensing data,” IEEE Access, vol. 9, pp. 143 828– 143 839, 2021.

[15] T. Chen and C. Guestrin, “Xgboost: A scalable tree boosting system,” in Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 2016, pp. 785–794.

[16] T. Chakraborty and X. Lee, “A simplified urban- extent algorithm to characterize surface urban heat islands on a global scale and examine vegetation control,” Remote sensing of environment, vol. 225, pp. 117– 133, 2019.

[17] P. Mohammad, A. Goswami, and S. Bonafoni, “The impact of savage urban growth on the vulnerability to land surface temperature in major indian cities,” Remote Sensing, vol. 14, no. 7, p. 1735, 2022.

[18] X. Li, Y. Zhou, G. R. Asrar, Z. Zhu, and X. Li, “Characterizing the surface urban heat island effect from the landscape perspective using thermal remote sensing,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 11, no. 7, pp. 2383– 2392, 2018.

[19] Z. S. Venter, D. N. Barton, T. Chakraborty, T. Simensen, and G. Singh, “Crowdsourced air temperatures contrast satellite measures of the urban heat island and its mechanisms,” Science Advances, vol. 7, no. 22, p. eabb8699, 2021.

[20] H. Shi, G. Xian, R. Auch, K. Gallo, and Q. Zhou, “Urban heat island and its regional impacts using remotely sensed thermal data—a review of recent developments and methodology,” Land, vol. 10, no. 8, p. 867, 2021.

[21] S. P. Mu¨ller, “Overcoming the limitations of tree-based models in time series forecasting,” https://medium.com/@simon.peter.mueller/ overcoming-the-limitations-of-tree-based- models-in-time-series-forecasting- c2c5bd71a8f1, Feb. 2024.

[22] P. Patel, R. Kalyanam, L. He, D. Aliaga, and D. Niyogi, “Deep learning- based urban morphology for city-scale environmental modeling,” PNAS Nexus, vol. 2, no. 3, p. pgad027, 2023.

[23] N. Afzalan, T. W. Sanchez, and J. Evans- Cowley, “Creating smarter cities: Considerations for selecting online participatory tools,” Cities, vol. 67, pp. 21–30, 2017.

[24] M. Marcellus and I. K. Park, “Deep learning for 3d human motion prediction: State-of-the-art and future trends,” IEEE Access, vol. 10, pp. 40 220– 40 243, 2022.

[25] J. Peng, J. Jia, Y. Liu, H. Li, and J. Wu, “Seasonal contrast of the dominant factors for spatial distribution of land surface temperature in urban areas,” Remote sensing of Environment, vol. 215, pp. 255–267, 2018.

@article{1714669,
      author = {Pradeep Nazareth, Ajay T, Prajwal Bhovi, Thilak, Yashwanth B R},
      title = {An AI-Driven Framework for Urban Heat Island (UHI) Analysis and Mitigation Simulation in Bengaluru},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {9},
      number = {8},
      pages = {2536-2543},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1714669.pdf},
      abstract = {The growth rate of Bengaluru has been exacerbated and the resulting UHI effect, were raising temperatures in the city, and, potentially, he was right. more energy use, and community health impacts related to that energy use. While the magnitude of this effect has been measured in. some studies yet lack of high-resolution. tools for simulation that the planner can use in real city envi- ronments. In this paper, we propose a full end-to-end ML- based framework to analyze and forecast the UHI of the city of Bengaluru. Here, we integrated several heterogeneous data including Land Surface Temperature (LST), Normalized Difference Vegetation Index (NDVI) as well as Land Use Land Cover (LULC) derived from satellite images with urban and historical climate data. Every set of data is consolidated into the entire city 100m by 100m grid of the whole city. A Random Forest This data set is exploited to build a regression model to estimate LST with. a large determination coefficient (R 2 =0.85). The major novelty One of the outcomes of this work is a Streamlit-based interactive simulation tool. that enables the policy maker to evaluate the policy from the point of view of the what-if-scenario (e.g., planting more green cover) and get instant visual feedback on. the cooling envelope was so forecast. This tool constitutes the missing one the link between UHI research and urban planning with data.},
      keywords = {Urban Heat Island (UHI), Machine Learning, Random Forest, Remote Sensing, Land Surface Temperature (LST), NDVI, Bengaluru, Urban Planning, Simulation.},
      month = {February},
      doi = {https://doi.org/10.64388/IREV9I8-1714669}
  }