Prediction of rainfall-triggered landslides: A test of the antecedent water status model

A rainfall-based landslide-triggering model, developed from previous landslide episodes in Wellington City, New Zealand, is tested for its ability to provide a 24-hour forecast of landslide occurrence. The model, referred to as the Antecedent Water Status Model, calculates an index of soil water, by running a daily water balance and applying a soil drainage factor to excess precipitation, over the preceding ten days. Together with the daily rainfall input, the soil water status has been used empirically to identify a threshold condition for landslide triggering. The prediction process provides a daily update of the soil water status and thereby the amount of rainfall required on the following day to equal or exceed the triggering threshold. The probability that this triggering rainfall will occur is then determined from the frequency/magnitude distribution of the local rainfall record. The model produces a satisfactory level of prediction, particularly for periods of concentrated landslide activity. Copyright (C) 1999 John Wiley & Sons, Ltd.