DeepClouds.ai: Deep learning enabled computationally cheap direct numerical simulations
This work addresses a bottleneck in weather forecasting by enabling computationally cheap simulations of large atmospheric domains, though it is incremental as it builds on existing deep learning and DNS methods.
The authors tackled the challenge of simulating turbulent cloud flows over large domains by introducing DeepClouds.ai, a 3D-UNET that maps inner cube outputs to full cubes from Direct Numerical Simulations, achieving results comparable to traditional models as measured by various score metrics.
Simulation of turbulent flows, especially at the edges of clouds in the atmosphere, is an inherently challenging task. Hitherto, the best possible computational method to perform such experiments is the Direct Numerical Simulation (DNS). DNS involves solving non-linear partial differential equations for fluid flows, also known as Navier-Stokes equations, on discretized grid boxes in a three-dimensional space. It is a valuable paradigm that has guided the numerical weather prediction models to compute rainfall formation. However, DNS cannot be performed for large domains of practical utility to the weather forecast community. Here, we introduce DeepClouds.ai, a 3D-UNET that simulates the outputs of a rising cloud DNS experiment. The problem of increasing the domain size in DNS is addressed by mapping an inner 3D cube to the complete 3D cube from the output of the DNS discretized grid simulation. Our approach effectively captures turbulent flow dynamics without having to solve the complex dynamical core. The baseline shows that the deep learning-based simulation is comparable to the partial-differential equation-based model as measured by various score metrics. This framework can be used to further the science of turbulence and cloud flows by enabling simulations over large physical domains in the atmosphere. It would lead to cascading societal benefits by improved weather predictions via advanced parameterization schemes.