• Kolhe Parag Namdeo
• Dr. Rajesh Keshavrao Deshmukh

The Real-Time Climate Monitoring and Early Warning System (RT-CMEWS) is designed to enhance disaster preparedness by providing accurate climate predictions and timely early warnings for extreme weather events. This study evaluates the RT-CMEWS's performance in predicting climate events such as heavy rainfall, heatwaves, and floods, using advanced machine learning models including Random Forest, Long Short-Term Memory (LSTM), and Support Vector Machine (SVM). The system achieved a prediction accuracy of 92.5%, with the Random Forest model demonstrating superior performance. Early warnings were issued with an average lead time of 4-5 hours, effectively allowing for preparation and response. Stakeholder feedback indicated high satisfaction, with 75% rating the system as "Very Useful," although usability issues with the mobile app were noted. Challenges identified include improving flood prediction accuracy and enhancing the app's user interface. Future improvements will focus on refining predictive models, enhancing system scalability, and integrating advanced technologies to better meet the needs of diverse communities and address the evolving impacts of climate change.

Real-Time Climate Monitoring, Early Warning System, Machine Learning, Random Forest, Climate Predictions, Disaster Preparedness, Flood Forecasting, User Interface, Climate Resilience

"Development of a Real-Time Climate Monitoring and Early Warning System: Integrating IoT and Machine Learning for Enhanced Predictive Accuracy", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 1, page no.h500-h513, January-2024, Available :http://www.jetir.org/papers/JETIR2401760.pdf

"Development of a Real-Time Climate Monitoring and Early Warning System: Integrating IoT and Machine Learning for Enhanced Predictive Accuracy", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 1, page no. pph500-h513, January-2024, Available at : http://www.jetir.org/papers/JETIR2401760.pdf