Archive
For years this lived as two separate blogs. One on physics, materials science and industrial engineering. The other on data science, statistics and machine learning. Each still stands on its own — posts are grouped in different strands, like:
- Energy & industrial systems modeling, where physical process understanding mixes with ML and optimization
- Experimental & sensor data pipelines, from instrumentation and data acquisition through to production-grade analytics and dashboards
- Applied ML and AI for scientific & engineering teams — time series, symbolic regression, forecasting methods, grounded in the physics of the system being modeled
- Standalone issues in fundamental aspects of data science — from dimensionality to feature engineering to data representation
- Discussions on physics
Often the technical problem I touch draws on several of these at once, whether the problem shows up in text, in code, or in technical depth.
Physics & Engineering
Industrial R&D notebook
Data acquisition & control, experimental physics, materials and process work.
Data Science & ML
Bits and chews
R, Python, and the data science pipeline — nine posts from 2016, several cross-published on DataCamp and RPubs.