Regional-scale controls on the spatial activity of rockfalls (Turtmann Valley, Swiss Alps) - A multivariate modeling approach

In mountain geosystems, rockfalls are among the most effective sediment transfer processes, reflected in the regional-scale distribution of talus slopes. However, the understanding of the key controlling factors seems to decrease with increasing spatial scale, due to emergent and complex system behavior and not least to recent methodological shortcomings in rockfall modeling research. In this study, we aim (i) to develop a new approach to identify major regional-scale rockfall controls and (ii) to quantify the relative importance of these controls. Using a talus slope inventory in the Turtmann Valley (Swiss Alps), we applied for the first time the decision-tree based random forest algorithm (RF) in combination with a principal component logistic regression (PCLR) to evaluate the spatial distribution of rockfall activity. This study presents new insights into the discussion on whether periglacial rockfall events are controlled more by topo-climatic, cryospheric, paraglacial or/and rock mechanical properties. (i) Both models explain the spatial rockfall pattern very well, given the high areas under the Receiver Operating Characteristic (ROC) curves of >0.83. Highest accuracy was obtained by the RF, correctly predicting 88% of the rockfall source areas. The RF appears to have a great potential in geomorphic research involving multicollinear data. (ii) The regional permafrost distribution, coupled to the bedrock curvature and valley topography, was detected to be the primary rockfall control. Rockfall source areas cluster within a low-radiation elevation belt (2900-3300 m a.s.l,) consistent with a permafrost probability of >90%. The second most important factor is the time since deglaciation, reflected by the high abundance of rockfalls along recently deglaciated (<100 years), north-faring slopes. However, our findings also indicate a strong rock mechanical control on the paraglacial rockfall activity, declining either exponentially or linearly since deglaciation. The study demonstrates the benefit of combined statistical approaches for predicting rockfall activity in deglaciated, permafrost-affected mountain valleys and highlights the complex interplay between rock mechanical, paraglacial and topo-climatic controls at the regional scale. (C) 2016 Elsevier B.V. All rights reserved.