Neural network-based machine learning is capable of approximating functions in very high dimension with unprecedented efficiency and accuracy. This has opened up many exciting new possibilities, one which to use algorithms assist multi-scale modeling. In this review, we three examples illustrate the process involved using modeling: ab initio molecular dynamics, meso-scale models, such as Landau...

Hydrologic modeling in the watershed scale is a key topic field of hydrology [...]

the main purpose of this investigation is to study the effect of near miscible co2 injection in different porous mediums on both lab and field scales. this effect can be traced by the change of two-phase gas-oil relative permeability curves. in this work, the experiments have been performed on three rock types (i.e. sandstone, dolomite, and artificial fractured sandstone) based on an incrementa...

0 2000 (a) Figure 4: Lossless modeling of audio segments using MSDEs. (a) A segment of audio (violin) signal, (b) modeling coeecients for two scale modeling with = 2, (c) coeecients for two scale modeling with = 3, and (d) coeecients for three scale modeling with = 2.