Fluid flow and transport through porous media with inhomogeneous electrical charge distributions are central to science and engineering. For example, flows through capillary networks, membranes, or rock and sediment formations are central to biology, medicine, geology, chemistry, and physics. In energy sciences, the transport of charged species through narrow, charged pores, occurs in a wide spectrum of systems, ranging from fuel cells and batteries, to materials for water filtration, catalysis, and CO2 storage. As a fluid phase flows through a pore, it exchanges momentum, mass, electric charge, and energy with its surroundings. Furthermore, it does so in an ever-changing, non-equilibrium manner. From a fundamental point of view, fluid flow in porous media encompasses all possible interactions that may arise between fluid phase molecules, suspended charged objects or solutes (SCOs), and the structural materials that form the pore. Furthermore, flow and transport occur over multiple time and length scales, ranging from picoseconds and angstroms to minutes and millimeters. As such, a comprehensive description of flow through heterocharged porous media represents a grand scientic challenge that remains to be solved. In this work, a multiscale approach is proposed that relies on state-of-the-art molecular, mesoscale, and continuum modeling, coupled to high-performance computing, sophisticated deep learning, and algorithmic and software advances to tackle the problem of flow and transport through heterocharged porous media in a manner that is without precedent in the scientic literature. A platform will be developed that embraces in a synergistic manner molecular modeling, fluid mechanics, and transport phenomena of charged systems, in a \direct" multiscale modeling approach. The methodologies and code frameworks that will be built in this project will have important applications, such as improved water filtration, DNA sequencing, drug delivery to cells, and battery performance, by providing high-fidelity modeling capabilities where before there were none.