Abstract Regional-scale forecasting of landslides is not a straight- forward task. In this work, the spatiotemporal forecasting capabil- ity of a regional-scale landslide warning system was enhanced by integrating two different approaches. The temporal forecasting (i.e. when a landslide will occur) was accomplished by means of a system of statistical rainfall thresholds, while the spatial fore- casting (i.e. where a landslide should be expected) was assessed using a susceptibility map. The test site was the Emilia Romagna region (Italy): the rainfall thresholds used were based on the rainfall amount accumulated over variable time windows, while the methodology used for the susceptibility mapping was the Bayesian tree random forest in the tree-bagger implementation. The coupling of these two methodologies allowed setting up a procedure that can assist the civil protection agencies during the alert phases to better define the areas that could be affected by landslides. A similar approach could be easily adjusted to other cases of study. A validation test was performed through a back analysis of the 2004–2010 records: the proposed approach would have led to define a more accurate location for 83% of the land- slides correctly forecasted by the regional warning system based on rainfall thresholds. This outcome provides a contribution to overcome the largely known drawback of regional warning sys- tems based on rainfall thresholds, which presently can be used only to raise generic warnings relative to the whole area of application.