About Me

I’m a Data Analyst and System Design Engineer with a research-first foundation in LiDAR, hyperspectral remote sensing, and applied machine learning—biased toward systems that scale, ship, and stay useful.

I earned both my BES and MSc (Honours) in Geomatics from the University of Waterloo. At the Geospatial Intelligence and Mapping (GIM) Lab, I defended my master’s thesis Semantic Modelling of an Indoor Parking Garage Using Hand-held GeoSLAM LiDAR Point Clouds , focused on high-definition indoor digital twins in GNSS-denied environments, combining LiDAR-based SLAM, semantic segmentation, and surface reconstruction to produce accurate, navigable 3D indoor models.

After graduation, I joined the Vision and Image Processing Lab (VIP Lab) as a full-time Research Associate, working on hyperspectral remote sensing and applied ML. My work included PRISMA-based vegetation and crop mapping and deep-learning object detection for Arctic imagery, bridging spectral modeling with real-world data constraints.

In industry, I design and deliver automated geospatial ETL pipelines for fiber systems. I build Bash- and Python-based frameworks that turn ad hoc reporting into reliable, repeatable pipelines—cutting turnaround time by ~75%. My scope spans full-lifecycle ETL, PostGIS data modeling, internal analytics tooling, lightweight API prototypes, and production documentation built to scale beyond a single contributor.

My interests converge on hyperspectral imaging, LiDAR and point-cloud processing, digital twins, and pragmatic machine learning deployed in production geospatial systems—where both robustness and novelty matter.