Tagged articles
fluid dynamics
12 articles · Page 1 of 1
This tutorial demonstrates how to solve the two‑dimensional steady incompressible Falkner‑Skan viscous boundary‑layer equations using a physics‑informed neural network implemented in JAX, detailing the network architecture, loss construction, two‑stage training strategy, and achieving sub‑0.01 % relative errors with only 1 % interior collocation points.
Falkner‑SkanJAXPINN
0 likes · 17 min read

This tutorial demonstrates how continuous physics‑informed neural networks (PINNs) combined with stream‑function parameterization and nested forward‑mode automatic differentiation (JVP) can accurately identify the convection and viscosity coefficients of a two‑dimensional Navier‑Stokes cylinder‑wake problem from sparse velocity observations, achieving sub‑0.2% error for the convection term and robust performance even with 1% measurement noise, all within a few minutes on a single RTX 4090 GPU.
Deep LearningJAXNavier-Stokes
0 likes · 28 min read

By integrating universal physical symmetries, weak‑form integral transformations, and sparse symbolic regression, the authors devise a hybrid framework that extracts governing Navier‑Stokes equations from high‑dimensional, noisy, and partially observed fluid experiments, while also reconstructing hidden pressure and Lorentz force fields.
Navier-StokesSymbolic Regressionfluid dynamics
0 likes · 12 min read

A recent video showing CO₂ levels rising from 880 ppm to over 2000 ppm inside a high‑speed train cabin sparked analysis that uses fluid‑mechanics and mass‑conservation modeling to explain why passengers often feel sleepy, comparing standards, physiological impacts, and ventilation efficiency.
CO2cognitive effectsfluid dynamics
0 likes · 8 min read

The article examines Paul De Meyer's 49‑foot “Hermes” concept yacht, exploring how its sharp geometry, lightweight composite hull, retractable keel and sail system, and fashion‑driven aesthetics create a bold contrast to Venice’s historic scenery while illustrating interdisciplinary design principles that balance luxury, performance, and sustainability.
concept yachtfashion inspirationfluid dynamics
0 likes · 6 min read

This article examines traditional Feng Shui concepts through the lens of modern environmental science, translating the notion of "qi" into measurable physical variables, building fluid‑dynamic, solar‑geometry, and graph‑theoretic models, and applying them to classic Chinese sites for quantitative evaluation.
Environmental ModelingFeng ShuiSolar Geometry
0 likes · 12 min read

DeepMind, together with researchers from NYU, Stanford and Brown, used physics‑informed neural networks, a Gauss‑Newton optimizer and multi‑stage training to systematically discover previously unknown unstable singularities in three fluid‑dynamics equations, revealing a concise asymptotic formula linking blow‑up rates to instability order.
DeepMindGauss-Newton optimizerPhysics-Informed Neural Networks
0 likes · 9 min read

Google DeepMind, together with researchers from NYU, Stanford and Brown, applied a machine‑learning framework and a high‑precision Gauss‑Newton optimizer to systematically discover new unstable singularities in three fluid equations, achieving solution accuracy that significantly surpasses existing work and revealing an empirical formula linking blow‑up rate to instability order.
DeepMindGauss-Newton optimizerMachine Learning
0 likes · 9 min read

This article explores how digital twin technology is applied to fluid dynamics, detailing the underlying physics, numerical methods, visualization pipelines, and the capabilities of specific platforms while highlighting current challenges and future opportunities across engineering and scientific domains.
Navier-StokesOpenVDBSimulation
0 likes · 20 min read

Confucius watches two children argue about a brick’s sinking time, then uses physics—gravity, buoyancy, drag—and a mathematical model with Python code to estimate how long the brick takes to reach the bottom of various oceans, highlighting differences due to depth and terminal velocity.
PhysicsPythonfluid dynamics
0 likes · 9 min read

Mathematical models have become indispensable alongside experiments in engineering, enabling quantitative predictions for material selection, system design, reliability analysis, and complex simulations—from satellite re‑entry to aircraft design—thereby reducing cost, time, and the need for impractical physical testing.
OptimizationSimulationengineering
0 likes · 7 min read

This article explains the three-step process for constructing differential-equation models, introduces the micro-element analysis method, and demonstrates its application to a hemispherical water-outflow problem, including derivation of the governing equation, solution via separation of variables, and a Python implementation using SymPy.
Pythondifferential equationsfluid dynamics
0 likes · 5 min read
