PNNL

Abstract

Droplet collision-coalescence is a crucial yet poorly understood process in cloud physics. A proposed future convective-cloud chamber aims to investigate this key process, but the method for observing it remains unclear, even though it is theoretically established that collision-coalescence will occur. This study serves as a proof-of-concept demonstration of how knowledge-informed deep learning, combined with measurement data from local sensors in the chamber, can be used to estimate the collision kernels, which determine how the droplet size distribution evolves during collision-coalescence. In addition to estimating the collision kernel, we also address wall flux, another poorly understood but important process that acts as the source of heat and moisture in the chamber. Ensemble runs of large-eddy simulations are conducted by scaling the wall flux and the collision kernel, while the measured flow and cloud properties are used as inputs for the neural network. Results indicate that this approach successfully maps the scaling of wall flux and the collision kernel with biases of approximately 1% or less relative to the range of the target data. This proof-of-concept lays the groundwork for future applications; when the real measurements are available, real sensor data combined with the trained model presented in this work will enable estimation of the actual wall flux and collision kernel.