Abstract :

The Increasing Frequency And Intensity Of Extreme Weather Events Pose Serious Challenges To Disaster Preparedness, Environmental Sustainability, And Socio-economic Stability. Traditional Forecasting Models Often Struggle To Capture The Complex, Nonlinear, And Evolving Patterns Of Climate Systems, Limiting Their Ability To Provide Timely And Accurate Predictions. This Paper Presents An Adaptive Climate-aware Machine Learning Framework For The Early Forecasting Of Extreme Weather Events Using Historical And Real-time Meteorological Data. The Proposed Framework Incorporates Key Climate Variables Such As Temperature, Precipitation, Humidity, Wind Speed, And Atmospheric Pressure, Along With Advanced Data Preprocessing And Feature Engineering Techniques To Improve Model Robustness. Machine Learning And Deep Learning Algorithms Are Utilized To Learn Temporal Dependencies And Nonlinear Relationships Inherent In Climate Data, Enabling Reliable Early Forecasts. The Framework Is Designed To Adapt To Changing Climate Patterns And Supports Scalable Deployment For Real-time Forecasting Applications. Experimental Evaluation Demonstrates That The Proposed Approach Enhances Prediction Accuracy And Forecasting Reliability Compared To Conventional Statistical Methods, Thereby Aiding Proactive Decision-making And Effective Disaster Risk Reduction.

Published:

22-12-2025

Issue:

Vol. 25 No. 12 (2025)

Page Nos:

414-419

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite