In heterogeneous structured soils, water and transported dissolved substances and suspended particles and colloids may under certain conditions bypass most of the soil porous matrix thereby creating nonequilibrium conditions in pressure heads and solute concentrations between preferential flow paths and the soil matrix pore region. Preferential flow severely limits the applicability of standard models for flow and transport that are mostly based on Richards' equation and the convection-dispersion equation. A number of various model approaches have been proposed to overcome this problem. These models mostly try to separately describe flow and transport in preferred flow paths and slow or stagnant pore regions. Discrete fracture models are more frequently suggested in hydrogeology and often more empirically for cracked clay soils. The two-domain approach assumes two interacting porous continua for either mobile-immobile (compartment models) or mobile-mobile pore systems for solute transport and for water movement. Such models were derived by rigorous "upscaling" methods (microstructure models), or by more empirically assuming two macroscopic scale systems. Representation of effective local (i.e., structural) geometry remains a problem when applying these models to soil systems. The dual-permeability models differ in the description of flow in the preferential flow domain (i.e., either Richards' equation assuming capillarity or kinematic wave approach for gravity flow) and with respect to the mass-transfer formulation (i.e., from pressure head- or saturation-based first-order type formulations to more complex nonlinear formulations or numerical solutions of the local flow equation). Despite the enormous progress that has been accomplished to improve both the modeling as well as the parameter determination, many challenges remain, in particular, how to capture dynamic soil structure effects to improve quantitative understanding and descriptions of preferential flow and transport processes.
