Can we infer temperature in turbulent convection from velocity alone?
By forcing a neural network to obey the equations of fluid flow and heat transport, the authors recovered the temperature field of a real turbulent convection experiment from velocity measurements alone to within about 4%.
Source
AIVT: Inference of turbulent thermal convection from measured 3D velocity data by physics-informed Kolmogorov-Arnold networks
Study at a glance
- Design
- Computational / modelling — Physics-informed Kolmogorov-Arnold network trained on Lagrangian particle-tracking velocities from a water-glycerol Rayleigh-Bénard cell, validated against thermochromic-liquid-crystal temperature measurements.
- N
- No participant count; the data are 282 experimental snapshots with about 3000 particle data points each from one convection run.
- Population
- Turbulent Rayleigh-Bénard convection in a hexagonal cell (water-glycerol, Prandtl number 10.6)
- Outcome
- Error of reconstructed velocity and inferred temperature versus measurements; boundary-layer profiles, dissipation-rate and velocity-gradient statistics
Structured fields used in claim comparison tables when every cited study has a complete layer.
What they did
The team heated a hexagonal cell of water-glycerol from below and cooled it from above, tracking temperature-sensitive liquid-crystal particles in 3D with three cameras to record both velocity and temperature. They then trained a physics-informed network (built on Chebyshev Kolmogorov-Arnold networks) on half of the velocity data only, requiring it to satisfy the Navier-Stokes and energy equations in a pressure-free vorticity form. Extra training tricks, including attention-based resampling of high-error points and staged training from simple to full physics, were added, and the held-out velocities and all measured temperatures were used for validation.
What they found
Reconstructed velocities on unseen data had relative errors of about 10% per component, and the inferred temperature matched the measured temperature with a relative error of 3.62% without ever seeing temperature during training. The inferred fields reproduced thermal plumes, regions of negative local heat flux, a thermal boundary-layer thickness consistent with scaling theory, and the teardrop-shaped Q-R velocity-gradient distribution typical of turbulence. Dissipation-rate statistics agreed qualitatively with earlier point measurements and simulations, though the model smoothed out extreme events; adding a few temperature observations reduced that smoothing.
The limits
What it doesn't show
All results come from a single run at one Rayleigh and Prandtl number in a thin slab of one cell, so generalisation to other regimes or geometries is untested. The model systematically underestimates high-magnitude events such as strong heat-flux bursts, and the temperature measurements themselves are biased by the limited sensitivity range of the liquid crystals, especially near the plates. Comparisons with literature dissipation statistics are qualitative and at different parameters. The paper is primarily a method demonstration rather than a new discovery about convection physics.
Key terms
- Rayleigh-Bénard convection
- Flow in a fluid layer heated from below and cooled from above, where buoyancy drives rising hot plumes and sinking cold ones.
- Physics-informed machine learning
- Training a neural network so its output fits data while also satisfying known governing equations, penalising equation residuals in the loss.
- Rayleigh number
- A dimensionless measure of how strongly buoyancy drives convection relative to viscous and thermal diffusion.
- Thermal boundary layer
- The thin region next to a heated or cooled plate where most of the temperature change occurs.
- Lagrangian particle tracking
- Measuring flow by following individual tracer particles in 3D over time to get their positions and velocities.
Flashcards
0 of 11 answers reviewed
Research intelligence for this paper
See its role on concept claims, tensions it is part of, placement history, and related discoveries.
Quiz yourself
What quantity was inferred without being used in training?
Common questions
How can temperature be inferred without measuring it?
In convection, temperature drives the flow through buoyancy, so the governing equations tie the velocity field to the temperature field; a network forced to satisfy those equations and match measured velocities must choose a consistent temperature.
Why use the vorticity form of the equations?
It eliminates pressure, which was not measured, so temperature can be inferred purely from velocity; the authors also report that the usual velocity-pressure form produced a rugged loss landscape with many local minima.
What is the main weakness of the inferred fields?
They are smoother than reality, underestimating rare strong events such as large heat-flux or dissipation spikes, though a handful of temperature measurements reduces this.
More on Turbulence