Portfolio
Projects
Analytics, geospatial, and machine learning projects spanning energy, climate, logistics, and e-commerce.
Avalanche Canada Wildfire Explorer
Interactive web application exploring wildfire perimeters within Avalanche Canada forecast regions. It includes localised and national summary statistics, plus a derived Burn Severity Patches layer using Landsat reflectance-based burn severity and a minimum patch-size threshold to highlight areas for follow-on assessment.
CityBike Trends in Lisbon, PT
Explored how local business density and types (e.g., cafes, bars, restaurants) correlate with bike availability at Lisbon's CityBike stations. Integrated geospatial APIs, statistical modelling, and regression analysis.
Climate Kegs – Carbon Neutrality Campaign
Partnering initially with Climate Neutral to measure emissions across RMU's global operations, I redirected the project into a community-driven philanthropic sustainability campaign in response to funding limitations. This led to the creation of "Climate Kegs", a tree-planting beer initiative launched in partnership with One Tree Planted.
European Alps Snowpack Depths
PostgreSQL and Python project analysing monthly snowpack trends across the European Alps using data from 2,794 weather stations. Focused on visualising seasonal changes, geographical differences, and high-elevation declines.
Sales Analytics: Ecommerce Growth to $500K
Led the development and expansion of RMU Skis' ecommerce channel, achieving 40% year-over-year growth across two consecutive years. Analyzed website traffic, conversion rates, and SKU-level profitability to drive targeted marketing, optimize product strategy, and support data-driven decision-making.
Salifort Motors Attrition Rates
A capstone project for the Google Advanced Data Analytics certification, this exploration investigates trends and variable associations through classification models between employee departures at the fictional Salifort Motors company.
Solar Farm Asset Performance Anomaly Detection
An AI-assisted Python project for anomaly detection across three geographically distinct solar sites, with synthetically injected fault scenarios.
Synthetic Inventory Demand Forecasting
A Python project comparing ARIMA and LSTM approaches to inventory demand forecasting - built on synthetic data to demonstrate end-to-end analytical workflow and model evaluation.
Tree Canopy Segmentation
Data science competition hosted by Solafune, focused on training a machine learning model to detect tree canopies in diverse urban environments using aerial and satellite imagery.