We apply deep learning to a synthetic near-surface hydrological response dataset of 4.4 million infiltration scenarios to determine conditions for the onset of positive pore-water pressures. This provides a rapid assessment of hydrologic conditions of potentially hazardous hillslopes where mass wasting is prevalent, and sidesteps the computationally expensive process of solving complex, highly non-linear equations. Each scenario considers antecedent soil moisture and storm depth with varying soil properties based on those measured at a USGS site in the East Bay Hills, CA, USA. Our model combines antecedent soil wetness and storm conditions with soil-hydraulic properties and predicts a binary output of whether or not positive pore pressures were generated. After parameterization, pore-water pressure conditions can be returned for any combination of antecedent soil moisture content and storm depth values. Similar to previous work, a deep learning model reduces computational cost: processing time is decreased by more than an order of magnitude for 1D simulated infiltration scenarios while maintaining high levels of accuracy. While the physical relevance and utility behind process-based numerical modeling cannot be replaced, the comparatively reduced computational cost of deep learning allows for rapid modeling of pore-water pressure conditions where solving complex, highly non-linear equations would otherwise be required. Furthermore, comparing the solution of a deep learning model with a hydrological model exemplifies how similar results can be produced through highly divergent mathematical relationships. This provides a unique opportunity to understand which variables are most relevant for the prediction of positive pore-water pressures on hillslopes, and can represent landslide-relevant hydrologic conditions for hillslopes where rapid analysis is imperative for informing potential hazard mitigation efforts. Ultimately, a calibrated deep learning model may reduce the need for computationally expensive physics-based modeling, which are often time and resource intensive, while providing critical statistical insight for the onset of hazardous conditions in landslide-prone areas.

During the last century, descriptions of sediment transport on the surface of Earth have been mostly deterministic and strongly influenced by concepts from continuum mechanics. The assumption that particle motions on hillslopes and in rivers satisfy the continuum hypothesis has provided an important foundation for this topic. Recent studies, however, have recognized that bed load and hillslope sediment transport conditions often are rarefied and do not satisfy continuum assumptions, therein pointing to the need for new ways of describing particle motions and transport. The problem of rarefied sediment transport is probabilistic in nature, and emerging methods for describing particle motions hark back to the pioneering work of Einstein (1938), who conceptualized bed load transport as a probabilistic problem. Here we provide a data set of particle travel distances and supplemental high-speed videos of particle-surface collisions collected during laboratory experiments to assess a theoretical formulation of the probabilistic physics of rarefied particle motions and deposition on rough hillslope surfaces. The formulation is based on a description of the kinetic energy balance of a cohort of particles treated as a rarefied granular gas, and a description of particle deposition that depends on the energy state of the particles. Both laboratory and field-based measurements are consistent with a generalized Pareto distribution of travel distances and predicted variations in behavior associated with the balance between gravitational heating and frictional cooling by particle-surface collisions. These behaviors vary from a truncated distribution associated with rapid thermal collapse to an exponential distribution representing approximately isothermal conditions to a heavy-tailed distribution associated with net heating of particles. The transition to a heavy-tailed distribution likely involves an increasing conversion of translational to rotational kinetic energy leading to larger travel distances with decreasing effectiveness of collisional friction. The analysis points to the need for further clarity concerning how particle size and shape in concert with surface roughness influence the extraction of particle energy and the likelihood of deposition.