FAA HIMS Program

AirLang: A domain-specific language for aviation flight planning and operations, featuring a complete compiler toolchain with 7-phase compilation, and specialized aviation calculations. Deployed as a standalone application with comprehensive documentation and examples

AirCPA is an offline analysis tool for deterministic air traffic conflict detection based on Closest Point of Approach (CPA) prediction using historic ADS-B state vector data.

Emergency Landing site geospatial tool

Machine Learning-Driven Clear Air Turbulence Prediction for Operational Aviation Safety

av-safety-parser extracts aviation incident details from unstructured text, outputting standardized data on incident type, aircraft, and risks.

a dataset + scripts for all 2010-2025 aviation accidents

a CAROL query API for the National Transportation Safety Board

Aviation Accident Database Analysis Tools for NTSB Datasets (1962-present) - includes MDB extraction scripts, SQL query tools, Python analysis examples, and comprehensive documentation.

EursiaAero AD/CN Explorer – EASA Airworthiness Directives & Consignes de Navigabilité

SkyWalk is a tool that is developed to help pilots become more aware of the various aspects of their flight plan as it can address situations that may need extra attention.

A project analyzing Bird Strike incidents with data visualizations and dashboards.

Risk quantification of UAS (drones) in the real world using OSM data.

iOS App that aims to improve safety amongst glider pilots by making the pilot's practice state easily accessible. Written with SwiftUI.

This project investigates the impact of flight type, crash cause, and region on fatality rates using t-tests, proportion tests, ANOVA, and linear regression. Developed for the Foundations of Machine Learning course, demonstrating proficiency in hypothesis testing, statistical modelling, and data-driven decision-making.

This repository contains the final project for Applied Machine Learning, where we built and evaluated predictive models to assess the risk of bird strikes on aircraft. The project explores various machine learning techniques to classify incidents and determine whether they resulted in aircraft damage.

This project analyzes aviation accident data using machine learning to predict and prevent fatal accidents. By testing models like Linear Regression, Random Forest, and XGBoost, the study found XGBoost to be the most accurate in predicting high-risk scenarios, aiding efforts to improve aviation safety.

The aim of this project is to build a machine learning model that will predict the level of crash severity which is compared to the percentage of deaths with respect to total Souls on board.

Unveiling Aviation's Hidden Dangers: A Data-Driven Exploration of Crashes and Fatalities (1980-2023)

SQL and Python Scripts for OpenSky Trino Database Analysis. This release includes SQL scripts and Python code for analyzing ADS-B messages stored in the OpenSky Trino database.