About the publication
ML·Energy·Bio publishes research notes at the intersection of scientific machine learning, energy systems, and the mathematics of flow — from polymer dynamics in blood to off-grid energy in rural Nepal.
The work here spans representation learning for molecular conformations, physics-informed methods, techno-economic modeling of distributed energy systems, and the boundary where simulation meets data. Each note is written to explain the ideas behind ongoing research — the physics, the methods, and the reasoning that does not always fit into a paper.
Physics tells you what to look for. Machine learning tells you where it hides. The interesting problems live at the boundary.
Notes here engage with the published literature, with references and DOIs included so you can follow the work back to its sources.