We use deep Physics-Informed Neural Networks (PINNs) to simulate stratified forced convection in plane Couette flow. This process is critical for atmospheric boundary layers (ABLs) and oceanic thermoclines under global warming. The buoyancy-augmented energy equation is solved under two boundary conditions: Isolated-Flux (single-wall heating) and Flux–Flux (symmetric dual-wall heating). Stratification is parameterized by the Richardson number
representing
thermal perturbations. We employ a decoupled model (linear velocity profile) valid for low-Re, shear-dominated flow. Consequently, this approach does not capture the full coupled dynamics where buoyancy modifies the velocity field, limiting the results to the laminar regime. Novel contribution: This is the first deep PINN to robustly converge in stiff, buoyancy-coupled flows (
) using residual connections, adaptive collocation, and curriculum learning—overcoming standard PINN divergence (errors
). The model is validated against analytical (
) and RK4 numerical (
) solutions, achieving
errors
and
errors
. Results show that stable stratification
suppresses convective transport, significantly reduces local Nusselt number (
) by up to
(driving
towards zero at both boundaries), and induces sign reversals and gradient inversions in thermally developing regions. Conversely, destabilizing buoyancy
enhances vertical mixing, resulting in an asymmetric response:
increases markedly (by up to
) at the lower wall but decreases at the upper wall compared to neutral forced convection. At
lower computational cost than DNS or RK4, this mesh-free PINN framework offers a scalable and energy-efficient tool for subgrid-scale parameterization in general circulation models (GCMs), supporting SDG 13 (Climate Action).
Full article
