Attempts on representing sink strengths with machine learning formulations and the long-term role of crystalline interfaces in the development of irradiation-induced bubbles

Abstract The present article addresses an early-stage attempt on replacing the analyticity-based sink strength terms in rate equations by means of a surrogate representation. Here we emphasise, in the context of multiscale modelling, a combinative use of machine learning with scale analysis, through which a set of fine-resolution problems of partial differential equations describing the local sink behaviour, can be asymptotically sorted out from the mean-field kinetics. Hence the training of machine learning formulation is restrictively oriented, that is, to express the local and already identified, but analytically unavailable nonlinear functional relationships between the sink strengths and other local continuum field quantities. Besides, the normally faster diffusion mechanisms on crystalline interfaces are particularly modelled by locally planar rate equations, and their linkages with rate equations for bulk diffusion are formulated by imposing an irregular boundary condition where point defect fluxes are discontinuous across the interfaces. Thus the distinctive role of crystalline interfaces as partial sinks and quick diffusion channels can be investigated. Methodologicalwise, the present treatment is also applicable for studying more complicated situation of long-term sink behaviour observed in irradiated materials.