Spatio-temporal relevance and controls of preferential flow at the landscape scale

The spatial and temporal controls of preferential flow (PF) during infiltration are still not fully understood. As soil moisture sensor networks allow us to capture infiltration responses in high temporal and spatial resolution, our study is based on a large-scale sensor network with 135 soil moisture profiles distributed across a complex catchment. The experimental design covers three major geological regions (slate, marl, sandstone) and two land covers (forest, grassland) in Luxembourg. We analyzed the responses of up to 353 rainfall events for each of the 135 soil moisture profiles. Non-sequential responses (NSRs) within the soil moisture depth profiles were taken as one indication of bypass flow. For sequential responses maximum porewater velocities (v(max)) were determined from the observations and compared with velocity estimates of capillary flow. A measured v(max) higher than the capillary prediction was taken as a further indication of PF. While PF was identified as a common process during infiltration, it was also temporally and spatially highly variable. We found a strong dependence of PF on the initial soil water content and the maximum rainfall intensity. Whereas a high rainfall intensity increased PF (NSR, v(max)) as expected, most geologies and land covers showed the highest PF under dry initial conditions. Hence, we identified a strong seasonality of both NSR and v(max) dependent on land cover, revealing a lower occurrence of PF during spring and increased occurrence during summer and early autumn, probably due to water repellency. We observed the highest fraction of NSR in forests on clay-rich soils (slate, marl). v(max) ranged from 6 to 80 640 cm d(-1) with a median of 120 cm d(-1) across all events and soil moisture profiles. The soils in the marl geology had the highest flow velocities, independent of land cover, especially between 30 and 50 cm depth, where the clay content increased. This demonstrates the danger of treating especially clay soils in the vadose zone as a low-conductive substrate, as the development of soil structure can dominate over the matrix property of the texture alone. This confirms that clay content and land cover strongly influence infiltration and reinforce PF, but seasonal dynamics and flow initiation also have an important impact on PF.