# thunil/Physics-Based-Deep-Learning

Links to works on deep learning algorithms for physics problems, TUM-I15 and beyond

Repository: https://github.com/thunil/Physics-Based-Deep-Learning
Canonical: https://ross.abutalabs.com/products/physics-based-deep-learning
License Family: other
Last push: 2025-10-10T08:18:46+00:00

## Health v2 (maintenance only)
Score: 53/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 46, release rhythm 35, longevity 100
- inputs: {"age_days": 2909, "days_push": 327, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1908, forks 317 (observed 2026-08-28T04:05:52.646834+00:00)

## What it is
A curated collection of links to research works on physics-based deep learning (PBDL), combining physical modeling with deep learning techniques, with emphasis on fluid flow and Navier-Stokes problems. It accompanies a comprehensive digital PBDL book from the I15 lab at TUM.

## Use cases
- find papers on deep learning for physics simulation
- learn differentiable physics methods
- research neural network approaches to fluid simulation
- study physics-informed loss functions for training neural networks
- find resources on inverse problems in physical systems
- get started with physics-based deep learning via the PBDL book

## When to choose
- you need a curated reading list of physics + deep learning research
- you want to learn about differentiable physics and neural fluid simulation
- you are looking for the accompanying PBDL book and overview material

## When to avoid
- you need runnable code or a software library rather than paper links
- you need machine learning for physics outside deep learning (e.g., classical ML)
- you need an exhaustive bibliography of all groups in the field

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, deep-learning, simulation, documentation
- domain: machine-learning, deep-learning, simulation, tutorials, awesome-lists
- platform: cross-platform
- tags: awesome-list, physics-based-deep-learning, differentiable-physics, fluid-simulation, research-papers, navier-stokes, physics

## Member repositories
- thunil/Physics-Based-Deep-Learning (main) score 53

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:52.646834+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:11:14.132121+00:00, confidence not recorded.
  - readme: https://github.com/thunil/Physics-Based-Deep-Learning (fetched 2026-08-28T04:05:52.646834+00:00, sha ad2cd1b2dc00)
- Data as of 2026-08-30T08:39:29.467469+00:00.