This page situates SciML for PS among nearby open materials. It is a positioning note for readers and collaborators, not a claim of uniqueness.
Positioning (honest wording)¶
To our knowledge, there is not yet an established open, collaborative living textbook that organizes scientific machine learning around power-system dynamics, stability assessment, and system identification as three engineering applications with a shared plant, classical baselines, and an assessed lab spine.
Related research codes, short courses, general SciML notes, and energy-system Jupyter Books do exist. This book aims to fill the teaching-product gap: one long-lived narrative you can study, cite by version, and help improve. If you know a resource we have missed, please tell us so this page stays fair.
Neighbors worth knowing¶
Product patterns (how living notes are built)¶
| Resource | Role relative to this book |
|---|---|
| EECS 245 course notes (Rampure) | Living MyST notes + separate course portal; CC BY-NC-ND 4.0 — we link and reimplement patterns, we do not adapt their text |
| Physics-based Deep Learning (Thuerey et al.) | Method textbook with runnable notebooks; ideas cited on chapter pages, rewritten for SMIB |
| The Turing Way, Dive into Deep Learning, Project Pythia | Models for governance, editions, and executable notebooks (patterns only) |
General SciML (methods, not power-system applications)¶
| Resource | Role |
|---|---|
| Introduction to Scientific Machine Learning (Bilionis, Purdue) | Probability-first SciML lecture notes |
| Cornell Virtual Workshop: SciML | Tutorial path on AD, PINNs, operators |
| JHU SciML Course (Drgoňa) | Course materials on SciML for dynamical systems; related research includes SciML for power, but not this book’s three-pillar teaching spine |
Power systems + AI / data (adjacent open teaching)¶
| Resource | Role |
|---|---|
| IEEE course notebooks: AI for Power and Energy Systems (Fran Li) | Modular Colab notebooks across AI tasks; includes a PINN frequency / swing module among load, power-flow, and optimization examples |
| Data Science for Energy System Modelling (TU Berlin) | Jupyter Book on energy-system modelling with data — planning / modelling focus, not TSA / SciML ID |
| Power Systems Optimization | Open Julia/JuMP course on dispatch, UC, OPF, capacity planning |
| Causality in Electricity Markets | Open tutorials on causal ML for markets |
| MIT OCW: Seminar in Electric Power Systems | Classical dynamics and transient stability OER (no SciML) |
PINN / SciML research code for power dynamics (cite; do not treat as a textbook)¶
The DTU group around Spyros Chatzivasileiadis has published foundational papers and open code for PINNs on power-system dynamics and identification, plus toolboxes and tutorials (Colab demos, assignments, PowerPINN, PINNSim). See downloads and the PSCC 2024 tutorial on power-system PINNs and trustworthy AI. These are research and tutorial artifacts, not a collaborative living course book with the Dynamics / Stability / Identification spine used here.
Curated paper and tool lists such as awesome
How we use neighbors¶
Cite and link public literature and docs; rewrite in teaching voice.
Do not paste sealed research metrics or unpublished campaign results into student pages.
Do not copy ND-licensed or unlicensed course text (EECS 245, Math 124 patterns are link-only).
ANDES and similar simulators are installed dependencies, not redistributed sources.
Attribution modes and register: maintainer file docs/references/attribution_register.md. Licence summary: License.
Suggest a missing neighbor¶
If you know another open book, course, or long-lived notes site that covers this niche, open a Feedback issue or discussion with the URL. We will update this page when the comparison changes.