AQI Prediction
Time-series ML system forecasting Air Quality Index using LSTM, Random Forest, and XGBoost with multi-pollutant analysis.
Completed
September 2025
Duration
3 months
Role
ML Engineer
Team
Solo project
Problem
Citizens and policymakers lack accurate short-term AQI forecasts to make informed health and policy decisions.
Solution
Built ensemble forecasting models (Random Forest, XGBoost, LSTM) combining historical pollution data with meteorological factors.
Impact
Short and long-term AQI predictions across 6 pollutant types with weather-factor integration.
About This Project
An environmental data science project that predicts Air Quality Index (AQI) using historical pollution data and meteorological factors.
Implements multiple ML algorithms including Random Forest, XGBoost, and LSTM neural networks for time-series forecasting.
Provides short-term and long-term AQI predictions to help citizens and policymakers make informed decisions.
Key Features
Technical capabilities and highlights
Time-series forecasting with LSTM
Ensemble methods (Random Forest, XGBoost)
Multi-pollutant analysis (PM2.5, PM10, NO2, SO2, CO, O3)
Weather factor integration
Interactive prediction dashboard
Historical trend analysis
Interested in this project?
Let's discuss how similar solutions can be built for your needs.