Abstract :

Health And The Environment, Especially In Urban Areas. Predicting The Air Quality Index (AQI) In Advance Helps Authorities And The Public Take Necessary Actions To Reduce Its Impact. This Project Develops An Efficient AQI Forecasting System Using A Combination Of Extreme Learning Machine (ELM) And Genetic Algorithm (GA). ELM Is A Fast Neural Network Model That Can Handle Complex Relationships Between Pollution And Weather Data. However, It Has Limitations Due To Random Weight Selection. To Solve This, GA Is Used To Optimize The Weights And Biases, Improving Prediction Accuracy. The System Uses Historical Data Such As Pollutant Levels (PM2.5, PM10, NO₂, SO₂, CO, NH₃, O₃) And Weather Parameters (temperature, Humidity, Wind Speed, Etc.). The Data Is Preprocessed By Cleaning, Handling Missing Values, And Normalizing Using Min-Max Scaling. The Hybrid GA-ELM Model Is Trained And Tested Using Performance Metrics Like RMSE And MAE, Showing Better Accuracy, Speed, And Stability Compared To Traditional Models. Additionally, A Flask-based Web Dashboard Is Developed To Display Realtime AQI Predictions. It Provides 1–12 Hour Forecasts, Visual Charts, And Color Indicators For Easy Understanding. Overall, This System Offers A Reliable And Scalable Solution For Short-term Air Quality Prediction, Supporting Better Environmental Management And Sustainable Urban Living

Published:

16-4-2026

Issue:

Vol. 26 No. 4 (2026)

Page Nos:

2219 - 2224

Section:

Articles

License:

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

How to Cite