Simplified models of spreading flow of dry granular material

Shallow-flow integrated numerical models of landslide and avalanche motion have recently experienced rapid development. An important aspect of model development is verification, to show that models are correct and reasonably robust in their application of basic physical principles. Most existing models have been verified against controlled laboratory experiments using dry granular material. In this article, it is shown that spreading flows such as the "dam-break" problem in frictional material pose problems for shallow-flow analysis. A series of dam-break laboratory experiments have been carried out with several different slope angles and bed materials. A model was then applied using four alternative assumptions regarding the distribution of earth pressure in the sliding mass. It was shown that assumptions commonly used in previous work produce very substantial errors (LIP to 200%) when applied to the prediction of dam-break runout in material with both internal and basal friction. A new model is proposed based on a simple modification of the well-known SH assumptions. This new model provides excellent agreement with experimental results, both for shallow avalanches and spreading flows. It represents a means to greatly expand the applicability of shallow-flow models to real landslide problems involving spreading flow, such as flow slides.