Modeling of aggregation processes in space-inhomogeneous systems is extremely numerically challenging since complicated aggregation equations -- Smoluchowski equations are to be solved at each space point along with the computation of particle propagation. Low rank approximation for the aggregation kernels can significantly speed up the solution of Smoluchowski equations, while particle propagation could be done in parallel. Yet the simulations with many aggregate sizes remain quite resource-demanding. Here, we explore the way to reduce the amount of direct computations with the use of modern machine learning (ML) techniques. Namely, we propose to replace the actual numerical solution of the Smoluchowki equations with the respective density transformations learned with the application of the conditional normalising flow. We demonstrate that the ML predictions for the space distribution of aggregates and their size distribution requires drastically less computation time and agrees fairly well with the results of direct numerical simulations. Such an opportunity of a quick forecast of space-dependent particle size distribution could be important in practice, especially for the online prediction and visualisation of pollution processes, providing a tool with a reasonable tradeoff between the prediction accuracy and the computational time.

A Russian spacewalker had to rush back inside the International Space Station on Wednesday when the battery voltage in his spacesuit suddenly dropped. Russian Mission Control ordered Oleg Artemyev, the station commander, to quickly return to the airlock so he could hook his suit to station power. The hatch remained open as his spacewalking partner, Denis Matveev, tidied up outside. NASA said neither man was ever in any danger. Matveev, in fact, remained outside for another hour or so, before he, too, was ordered to wrap it up. Matveev's suit was fine, but Russian Mission Control cut the spacewalk short since flight rules insist on the buddy system.