MUMBAI, India, Aug. 10 -- Intellectual Property India has published a patent application (202641080294 A) filed by Dr. N. Gopinath; Dr. Sejal Dhyanesh Desai; Tanuja Sajid Mulla; Hrucha Chandrashekhar Deshmukh; Dr. Rajeswari V; Divya Dilipkumar Chechani; Dr. Rekha Shashikant Kadam; Shilpa Katre; Parul Jha; and Aishwarya Churi on June 30, 2026, for Iot-Based Smart Coastal Monitoring System For Tsunami Risk Reduction Using Ai And Ml.
Inventors include Dr. N. Gopinath; Dr. Sejal Dhyanesh Desai; Tanuja Sajid Mulla; Hrucha Chandrashekhar Deshmukh; Dr. Rajeswari V; Divya Dilipkumar Chechani; Dr. Rekha Shashikant Kadam; Shilpa Katre; Parul Jha; and Aishwarya Churi.
The application for the patent was published on July 31, 2026, under issue no. 31/2026.
Abstract: The present invention relates to an IoT-Based Smart Coastal Monitoring System for Tsunami Risk Reduction Using Artificial Intelligence (Al) and Machine Learning (ML), designed to provide real-time monitoring, prediction, and early warning capabilities for coastal regions vulnerable to tsunami events. The system comprises a distributed network of IoT-enabled sensing devices, including ocean-bottom pressure sensors, water level sensors, seismic sensors, wave height sensors, tide gauges, weather monitoring stations, and GPS-enabled smart buoys deployed across offshore and coastal locations. These sensors continuously collect environmental, oceanographic, and geological data and transmit the information through communication technologies such as LoRaWAN, 5G, satellite links, or cellular networks to a centralized cloud-based processing platform. The collected data is preprocessed and analyzed using Al and ML models, including deep neural networks, recurrent neural networks (RNNs), long short-term memory (LSTM) networks, and ensemble learning algorithms, to identify abnormal sea-level variations, underwater seismic disturbances, and wave propagation patterns associated with potential tsunami generation. The predictive engine compares real-time observations with historical disaster datasets to estimate tsunami occurrence probability, expected wave height, arrival time, inundation zones, and severity levels with improved accuracy and reduced false alarm rates. The system further incorporates a Geographic Information System (GlS)-based visualization module for mapping high-risk coastal areas and generating dynamic evacuation routes. Automated alerts are disseminated through mobile applications, SMS services, emergency sirens, public display systems, and disaster management control centers. By integrating IoT sensing, Al-driven analytics, and intelligent decision-support mechanisms, the proposed invention significantly enhances tsunami preparedness, enables timely emergency response, reduces potential loss of life and infrastructure damage, and contributes to the development of resilient and sustainable coastal communities.
Disclaimer: Curated by HT Syndication.
