Geo-Computational Intelligence for Predictive Cyclone Impact and Multi- Tiered Risk Stratification in Chennai, Tamil Nadu Leveraging AI-Enabled Framework

·        The study has predicted the Cyclone Damage Prediction in Chennai, Tamil Nadu using Artificial Intelligence Techniques with the help of Geospatial Software. ·        A thematic layer was created for all parameter like Slope, Elevation, LULC, Cyclone Track, Stream Range, Rainfall, Wind Speed, Population and Household intensity and then random training points were generated. ·        By using random points trained the Random Forest Classifier Model to predict the cyclone damage by looking many decision trees. In the end, it chooses one single decision and results are shown as spatially distributed. And entire study area is categorized into three damage categories: Low, Moderate, High ·        Results shows that 112 sq.km areas are falls under High Damageable zones, 289 sq.km areas are falls under Moderate Damageable zones and 33 sq.km areas are falls under Low Damageable zones. ·        The high damage zones are Ennore, Thiruvottiyur, Adyar Mouth and parts of coastal Kanchipuram. ·        The moderate damage zones are Tondairpet, Purasawalkam, Egmore, Velachery, Sholinganallur, Western Part of Alandur, Mambalam, Northern Part of Ambattur, Parts of Madhavaram. ·        The low damage zones are Guindy, Saidapet, Alandur, Kolapakkam, Moulivakkam, Adambakkam, Ambattur, Madhavaram, Kodungaiyur. ·        And the study was evaluated by comparing the model spatial output with Flooded area change detection for Chennai 2015 Flood and Cyclone Michaung Flood. ·        It shows similar results in observing both of them. It represents the model’s accuracy is validated and it has a predictive ability. And for one of the short mitigation measure, safe shelter locations are identified according to the prediction model. Over 1000+ shelter points, this prediction model selects 128 shelter locations.

“Cyclone NDMA,” [Online]. Available: https://ndma.gov.in/Natural-Hazards/Cyclone. M. A. -. A. Hoque, “A systematic review of tropical cyclone disaster management research using remote sensing and spatial analysis,” Research Gate, pp. 109-120, 2017. J. S. R. B. Z. E. JM Shultz, “Tropical cyclones in a year of rising global temperatures and a strengthening El Niño,” Taylor & Francis, vol. 2, no. 3-4, pp. 151-162, 2014. “National Disaster Management Authority Government of India,” [Online]. Available: https://nidm.gov.in/PDF/pubs/NDMA/4.pdf. “NOAA,” [Online]. Available: https://www.noaa.gov/jetstream/tropical/tropical-cyclone-introduction/tropical-cyclone-classification. “Indian Meterological Department,” [Online]. Available: https://mausam.imd.gov.in/imd_latest/contents/pdf/cyclone_sop.pdf. I. Assessment of cyclone risk and case study of Gaja cyclone using GIS techniques and machine learning algorithms in coastal zone of Tamil Nadu, “M. Thenmozhi et al.,,” National Library of Medicine, 2024. Sultan Al Shafian et al., “Integrating Machine Learning and Remote Sensing in Disaster Management: A Decadal Review of Post-Disaster Building Damage Assessment,” MDPI, vol. 14, no. 8. Showmitra Kumar Sarkar et al., “Cyclone vulnerability assessment in the coastal districts of Bangladesh,” Science Direct, vol. 10, no. 1, 2024. S. Saravanan, “Multi-Criterion Analysis of Cyclone Risk along the Coast of Tamil Nadu, India—A Geospatial Approach,” MDPI, vol. 12, no. 8, 2023. Hamid Varikkodan et al., “Tropical cyclone risk assessment of Port Blair, Andaman Islands, India by using numerical modelling and geospatial techniques,” Indian Academy of Sciences, 2023. Chaoyong Tu et al., “Tropical Cyclone Damage Assessment using a Projection Pursuit Dynamic Cluster Model,” Research Gate, 2021. Muhammad Al-Amin Hoque et al., “Tropical cyclone risk assessment using geospatial techniques for the eastern coastal region of Bangladesh,” Science Direct, vol. 692, pp. 10-22, 2019. Hal F. Needham et al., “A review of tropical cyclone-generated storm surges: Global data sources, observations, and impacts,” Advancing Earth and Space Sciences, vol. 53, no. 2, pp. 545-591, 2015. Akhila G Nair et al., “A STUDY ON VARIOUS TROPICAL CYCLONE HITS IN INDIA – THROUGH GIS APPROACH,” International Journal of Pure and Applied Mathematics, vol. 119, pp. 589-595, 2018. Ubaydur Rahaman et al., “Cyclonic tracj analysis using GIS over the Bay of Bengal,” International Journal of Applied Sciences and Engineering Research, vol. 1, no. 5, 2012. “Chennai District Profile,” [Online]. Available: https://chennai.nic.in/about-district/district-profile/. “Wikipedia - chennai,” [Online]. Available: https://en.wikipedia.org/wiki/Chennai. “United States Geological Survey,” [Online]. Available: https://earthexplorer.usgs.gov/. “USGS LANDSAT Mission,” [Online]. Available: https://www.usgs.gov/landsat-missions/landsat-9. Xiaogang Guo et al., “Using a Random Forest Model to Predict the Location of Potential Damage on Asphalt Pavement,” MDPI, vol. 11, no. 21. Viet Hung Dang et al., “A Novel GIS-Based Random Forest Machine Algorithm for the Spatial Prediction of Shallow Landslide Susceptibility”. “United Nations office for Disaster Risk Reduction,” [Online]. Available: https://www.undrr.org/. Ubaydur Rahaman Siddiki et al., “Cyclonic track analysis using GIS over the Bay of Bengal,” International Journal of Applied Science and Engineering Research, vol. 1, no. 5, 2012. I. M. Department, “Very Severe Cyclonic Storm “THANE” over the Bay of Bengal : Report,” 2011. [Online]. Available: https://rsmcnewdelhi.imd.gov.in/download.php?path=uploads/report/26/26_b2c778_thane.pdf. “TNSMART,” [Online]. Available: https://beta-tnsmart.rimes.int/index.php/Rainfall.