Tsunami Prediction System — ML Pipeline & Flask Web Application

Designed and deployed an end-to-end ML application predicting tsunami likelihood from seismic activity data (magnitude, depth, intensity) using a Decision Tree Classifier optimized via GridSearchCV
Achieved 89.83% accuracy and 89% tsunami recall (catch rate); best parameters: max_depth=10, criterion=’gini’
Built automated preprocessing pipeline using Scikit-Learn Pipelines with StandardScaler, OneHotEncoder, and missing value imputation; serialized via Joblib for production inference
Wrapped model in a Flask web application with interactive HTML/CSS interface for real-time earthquake parameter input and prediction; deployed to Azure App Service via CLI
Demonstrates full ML lifecycle: data ingestion, preprocessing, hyperparameter tuning, model serialization, web integration, and cloud deployment
Tech stack: Python 3.9, Scikit-Learn, Pandas, Flask, Seaborn/Matplotlib, Gunicorn, Azure App Service