Authors : D Rahul Kumar Reddy; P Rahul Prabhakar; S Harsha Vardhan; Udayagiri Munna; John Bennet; Josephine R

Volume/Issue : Volume 10 - 2025, Issue 5 - May

Google Scholar : https://tinyurl.com/dsedz774

DOI : https://doi.org/10.38124/ijisrt/25may192

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Cloudbursts present significant risks to urban infrastructure and public safety due to their abrupt and localized characteristics, frequently leading to flash floods and landslides. This study introduces the Advanced Cloudburst Prediction System, a hybrid AI-driven framework aimed at providing real-time assessments of cloudburst risks specific to cities. The system combines a Random Forest classifier with an LSTM neural network, utilizing both historical simulations and current weather data sourced from the OpenWeatherMap API. Its outputs feature dynamic risk probabilities, visual analytics, regional risk maps, and emergency notifications through a Gradio web interface. By delivering timely warnings and practical insights, this system enables both authorities and citizens to improve their disaster preparedness and response strategies.

Keywords : Cloudburst Prediction, LSTM, Random Forest, Real-Time Weather Data, Disaster Risk Management, AI in Meteorology, Gradio, Flash Floods, Emergency Alerts, Openweathermap.

References :

1. Shi, X., et al. "Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model."
2. Darwish, A., Hassanien, A. E. "Wireless Sensor Networks and Neural Network-Based Approach for Real-Time Flood and Cloudburst Detection." Sensors, Volume 21, Issue 2, 2021, Article 438.
3. Ravuri, S., et al. "Skilful precipitation nowcasting using deep generative models of radar." Nature, Vol. 597, 2021, pp. 672–677.
4. Siregar, V.P., Gunawan, D. "An Ensemble Machine Learning Model for Flash Flood Prediction." Water, 2021, 13(24), 3636.
5. Li, Y., Huang, H., Wu, J. "Flash Flood Prediction Through Weather Radar and Machine Learning." Remote Sensing, 2019, 11(15), 1828.
6. SONIKA, KM. Cloudburst Prediction In Northern India Region Using Machine Learning And Deep Learning. Diss. DEFENCE INSTITUTE OF ADVANCED TECHNOLOGY, 2022.
7. Reddy, G. Bhuvaneswar, J. Chethan, and M. Saravanamuthu. "CLOUD BURST FORECAST USING EXPERT SYSTEMS." (2022).
8. Garg, Sourabh, et al. "Performance evaluation of high‐resolution IMDAA and IMERG for detecting cloudburst events over the Northwest Himalayas." International Journal of Climatology 43.8 (2023): 3730-3748.
9. Schmith, Torben, et al. "Regional variation of climatological cloudburst frequency estimated from historical observations of daily precipitation sums." International Journal of Climatology 43.16 (2023): 7761-7774.
10. https://www.irjmets.com/uploadedfiles/paper//issue_5_may_2024/55445/final/fin_irjmets1715079952.pdf
11. Hassan, Md Mehedi, et al. "Machine learning-based rainfall prediction: Unveiling insights and forecasting for improved preparedness." IEEE Access 11 (2023): 132196-132222.
12. Jain, Harshita, et al. "Leveraging machine learning algorithms for improved disaster preparedness and response through accurate weather pattern and natural disaster prediction." Frontiers in Environmental Science 11 (2023): 1194918.