Structure-Oriented Randomized Neural Networks for Poisson-Nernst-Planck and Poisson-Nernst-Planck-Navier-Stokes Systems
arXiv:2606.19912v1 Announce Type: cross Abstract: We develop a structure-oriented randomized neural network framework, termed SO-RaNN, for the Poisson-Nernst-Planck (PNP) system and the Poisson-Nernst-Planck-Navier-Stokes (PNP-NS) system. The decoupled linearized subproblems are solved iteratively by randomized neural networks in a space-time framework. For the concentration variables, a pointwise cut-off is used to enforce positivity at the value level, and discrete mass-scaling factors are computed at selected correction instants and interpolated in time, so as to ensure exact mass matching
The continuous evolution of AI and machine learning techniques provides new avenues for solving complex scientific and engineering problems previously intractable or computationally expensive.
This research advances the application of AI in fundamental physics and chemistry, potentially enabling more accurate and efficient simulations of complex electrochemical and fluidic systems critical to various industries.
The development of structure-oriented randomized neural networks offers a novel, potentially more robust, and computationally efficient method for modeling coupled partial differential equations in scientific computing.
- · Computational physicists & chemists
- · Materials science research
- · Pharmaceutical R&D
- · Battery technology developers
- · Traditional numerical simulation methods (in specific applications)
- · Researchers relying on less efficient computational models
Improved accuracy and speed in simulating complex multi-physics systems for research and development.
Accelerated discovery of new materials or systems with optimal properties due to more efficient predictive modeling.
Reduced time and cost in designing and testing electrochemical devices, leading to faster innovation cycles in related industries.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG