Extreme rainfall events are the major driver of shallow landslide occurrences in mountainous and steep terrain regions around the world. Subsurface hydrology has a dominant role on the initiation of rainfall-induced shallow landslides, since changes in the soil water content affect significantly the soil shear strength. Rainfall infiltration produces an increase of soil water potential, which is followed by a rapid drop in apparent cohesion. Especially on steep slopes of shallow soils, this loss of shear strength can lead to failure even in unsaturated conditions before positive water pressures are developed. We present HYDROlisthisis, a process-based model, fully distributed in space with fine time resolution, in order to investigate the interactions between surface and subsurface hydrology and shallow landslides initiation. Fundamental elements of the approach are the dependence of shear strength on the three-dimensional (3-D) field of soil water potential, as well as the temporal evolution of soil water potential during the wetting and drying phases. Specifically, 3-D variably saturated flow conditions, including soil hydraulic hysteresis and preferential flow phenomena, are simulated for the subsurface flow, coupled with a surface runoff routine based on the kinematic wave approximation. The geotechnical component of the model is based on a multidimensional limit equilibrium analysis, which takes into account the basic principles of unsaturated soil mechanics. A series of numerical simulations were carried out with various boundary conditions and using different hydrological and geotechnical components. Boundary conditions in terms of distributed soil depth were generated using both empirical and process-based models. The effect of including preferential flow and soil hydraulic hysteresis was tested together with the replacement of the infinite slope assumption with the multidimensional limit equilibrium analysis. The results show that boundary conditions play a crucial role in the model performance and that the introduced hydrological (preferential flow and soil hydraulic hysteresis) and geotechnical components (multidimensional limit equilibrium analysis) significantly improve predictive capabilities in the presented case study.

No abstract

The use of fingerprinting localization techniques in outdoor IoT settings has started to gain popularity over the recent years. Communication signals of Low Power Wide Area Networks (LPWAN), such as LoRaWAN, are used to estimate the location of low power mobile devices. In this study, a publicly available dataset of LoRaWAN RSSI measurements is utilized to compare different machine learning methods and their accuracy in producing location estimates. The tested methods are: the k Nearest Neighbours method, the Extra Trees method and a neural network approach using a Multilayer Perceptron. To facilitate the reproducibility of tests and the comparability of results, the code and the train/validation/test split of the dataset used in this study have become available. The neural network approach was the method with the highest accuracy, achieving a mean error of 358 meters and a median error of 204 meters.

Fingerprinting techniques, which are a common method for indoor localization, have been recently applied with success into outdoor settings. Particularly, the communication signals of Low Power Wide Area Networks (LPWAN) such as Sigfox, have been used for localization. In this rather recent field of study, not many publicly available datasets, which would facilitate the consistent comparison of different positioning systems, exist so far. In the current study, a published dataset of RSSI measurements on a Sigfox network deployed in Antwerp, Belgium is used to analyse the appropriate selection of preprocessing steps and to tune the hyperparameters of a kNN fingerprinting method. Initially, the tuning of hyperparameter k for a variety of distance metrics, and the selection of efficient data transformation schemes, proposed by relevant works, is presented. In addition, accuracy improvements are achieved in this study, by a detailed examination of the appropriate adjustment of the parameters of the data transformation schemes tested, and of the handling of out of range values. With the appropriate tuning of these factors, the achieved mean localization error was 298 meters, and the median error was 109 meters. To facilitate the reproducibility of tests and comparability of results, the code and train/validation/test split used in this study are available.

No abstract