Hi, I’m Jason Schmidberger
Protein crystallographer turned data scientist. I apply probabilistic models and physics-informed ML pipelines to real-world sensing problems—currently focused on methane emissions analytics, source localisation, and spatial anomaly detection. I lead teams to build end-to-end analytical workflows and deliver actionable insight for clients. My toolkit spans Python (NumPy/Pandas/PyMC), Bayesian inference, Gaussian plume and advection–diffusion modelling, and cloud-based delivery.
- Focus – uncertainty-aware analytics, measurement-informed reporting, and robust, reproducible engineering for operational decision-making.
- Experience – 20+ years across academia and industry (Australia, Sweden, Scotland, UK), combining scientific depth with production data-science delivery.
- Impact – led development of RJ-MCMC and hybrid modelling workflows for leak localisation and quantification; advanced OGMP 2.0–aligned reporting; introduced scalable pipelines and mentored teams in modern, production-grade data science practices.