In this paper, the updating of the landslide inventory of Tuscany region is presented. To achieve this goal, satellite SAR data processed with persistent scatter interferometry (PSI) technique have been used. The updating leads to a consistent reduction of unclassified landslides and to an increasing of active landslides. After the updating, we explored the characteristics of the new inventory, analysing landslide distribution and geomorphological features. Several maps have been elaborated, as sliding index or landslide density map; we also propose a density-area map to highlight areas with different landslide densities and sizes. A frequency-area analysis has been performed, highlighting a classical negative power-law distribution. We also explored landslide frequency for lithology, soil use and several morphological attributes (elevation, slope gradient, slope curvature), considering both all landslides and classified landslide types (flows, falls and slides).

Accurate early warning systems for landslides are a reliable risk-reduction strategy that may significantly reduce fatalities and economic losses. Several machine learning methods have been examined for this purpose, underlying deep learning (DL) models’ remarkable prediction capabilities. The long short-term memory (LSTM) and gated recurrent unit (GRU) algorithms are the sole DL model studied in the extant comparisons. However, several other DL algorithms are suitable for time series forecasting tasks. In this paper, we assess, compare, and describe seven DL methods for forecasting future landslide displacement: multi-layer perception (MLP), LSTM, GRU, 1D convolutional neural network (1D CNN), 2xLSTM, bidirectional LSTM (bi-LSTM), and an architecture composed of 1D CNN and LSTM (Conv-LSTM). The investigation focuses on four landslides with different geographic locations, geological settings, time step dimensions, and measurement instruments. Two landslides are located in an artificial reservoir context, while the displacement of the other two is influenced just by rainfall. The results reveal that the MLP, GRU, and LSTM models can make reliable predictions in all four scenarios, while the Conv-LSTM model outperforms the others in the Baishuihe landslide, where the landslide is highly seasonal. No evident performance differences were found for landslides inside artificial reservoirs rather than outside. Furthermore, the research shows that MLP is better adapted to forecast the highest displacement peaks, while LSTM and GRU are better suited to model lower displacement peaks. We believe the findings of this research will serve as a precious aid when implementing a DL-based landslide early warning system (LEWS).

We propose a methodology to couple rainfall thresholds and susceptibility maps for dynamic landslide hazard assessment at regional scale. Both inputs are combined in a purposely-built hazard matrix to get a spatially and temporally variable definition of landslide hazard: while statistical rainfall thresholds are used to accomplish a temporal forecasting with very coarse spatial resolution, landslide susceptibility maps provide static spatial information about the probability of landslide occurrence at fine spatial resolution. The test site is the Northern part of Tuscany (Italy), where a recent landslide susceptibility map and a set of recently updated rainfall thresholds are available. These products were modified and updated to meet the requirements of the proposed procedure: the susceptibility map was reclassified and the threshold set was expanded defining additional thresholds. The hazard matrix combines three susceptibility classes (S1, low susceptibility; S2 medium susceptibility; S3 high susceptibility) and three rainfall rate classes (R1, R2, R3), defining five hazard classes, from H0 (null hazard) to H4 (high hazard). A key passage of the procedure is the appropriate calibration and validation of the matrix, letting the hazard classes have a precise meaning in terms of expected consequences and hazard management. The employ of the proposed procedure in a regional warning system brings two main advantages: (i) it is possible to better hypothesize when and where landslide are expected and with which hazard degree, thus fostering a more effective hazard and risk management (e.g., setting priorities of intervention); (ii) the spatial resolution of the regional scale warning system is markedly refined because from time to time the areas where landslides are expected represent only a fraction of the alert zone.

We set up an early warning system for rainfall-induced landslides in Tuscany (23 000 km²). The system is based on a set of state-of-the-art intensity–duration rainfall thresholds (Segoni et al., 2014b) and makes use of LAMI (Limited Area Model Italy) rainfall forecasts and real-time rainfall data provided by an automated network of more than 300 rain gauges. The system was implemented in a WebGIS to ease the operational use in civil protection procedures: it is simple and intuitive to consult, and it provides different outputs. When switching among different views, the system is able to focus both on monitoring of real-time data and on forecasting at different lead times up to 48 h. Moreover, the system can switch between a basic data view where a synoptic scenario of the hazard can be shown all over the region and a more in-depth view were the rainfall path of rain gauges can be displayed and constantly compared with rainfall thresholds. To better account for the variability of the geomorphological and meteorological settings encountered in Tuscany, the region is subdivided into 25 alert zones, each provided with a specific threshold. The warning system reflects this subdivision: using a network of more than 300 rain gauges, it allows for the monitoring of each alert zone separately so that warnings can be issued independently. An important feature of the warning system is that the visualization of the thresholds in the WebGIS interface may vary in time depending on when the starting time of the rainfall event is set. The starting time of the rainfall event is considered as a variable by the early warning system: whenever new rainfall data are available, a recursive algorithm identifies the starting time for which the rainfall path is closest to or overcomes the threshold. This is considered the most hazardous condition, and it is displayed by the WebGIS interface. The early warning system is used to forecast and monitor the landslide hazard in the whole region, providing specific alert levels for 25 distinct alert zones. In addition, the system can be used to gather, analyze, display, explore, interpret and store rainfall data, thus representing a potential support to both decision makers and scientists.

We propose an original approach to develop rainfall thresholds to be used in civil protection warning systems for the occurrence of landslides at regional scale (i.e. tens of thousands of kilometres), and we apply it to Tuscany, Italy (23 000 km²). Purpose-developed software is used to define statistical intensity–duration rainfall thresholds by means of an automated and standardized analysis of rainfall data. The automation and standardization of the analysis brings several advantages that in turn have a positive impact on the applicability of the thresholds to operational warning systems. Moreover, the possibility of defining a threshold in very short times compared to traditional analyses allowed us to subdivide the study area into several alert zones to be analysed independently, with the aim of setting up a specific threshold for each of them. As a consequence, a mosaic of several local rainfall thresholds is set up in place of a single regional threshold. Even if pertaining to the same region, the local thresholds vary substantially and can have very different equations. We subsequently analysed how the physical features of the test area influence the parameters and the equations of the local thresholds, and found that some threshold parameters can be put in relation with the prevailing lithology. In addition, we investigated the possible relations between effectiveness of the threshold and number of landslides used for the calibration. A validation procedure and a quantitative comparison with some literature thresholds showed that the performance of a threshold can be increased if the areal extent of its test area is reduced, as long as a statistically significant landslide sample is present. In particular, we demonstrated that the effectiveness of a warning system can be significantly enhanced if a mosaic of site-specific thresholds is used instead of a single regional threshold.