Landslides are events that cause great impact in different parts of the world. Their destructive capacity generates loss of life and considerable economic damage. In this research, several Machine Learning (ML) methods were explored to select the most important conditioning factors, in order to evaluate the susceptibility to rotational landslides in a sector surrounding the city of Cuenca (Ecuador) and with them to elaborate landslide susceptibility maps (LSM) by means of ML. The methods implemented to analyze the importance of the conditioning factors checked for multicollinearity (correlation analysis and VIF), and, with an ML-based approach called feature selection, the most important factors were determined based on Classification and Regression Trees (CART), Feature Selection with Random Forests (FS RF), and Boruta and Recursive Feature Elimination (RFE) algorithms. LSMs were implemented with Random Forests (RF) and eXtreme Gradient Boosting (XGBoost) methods considering a landslide inventory updated to 2019 and 15 available conditioning factors (topographic (10), land cover (3), hydrological (1), and geological (1)), from which, based on the results of the aforementioned analyses, the six most important were chosen. The LSM were elaborated considering all available factors and the six most important ones, with the previously mentioned ML methods, and were compared with the result generated by an Artificial Neural Network with resilient backpropagation (ANN rprop-) with six conditioning factors. The results obtained were validated by means of AUC-ROC value and showed a good predictive capacity for all cases, highlighting those obtained with XGBoost, which, in addition to a high AUC value (>0.84), obtained a good degree of coincidence of landslides at high and very high susceptibility levels (>72%). Despite the findings of this research, it is necessary to study in depth the methods applied for the development of future research that will contribute to developing a preventive approach in the study area.

Natural hazards generate disasters and huge losses in several aspects, with landslides being one of the natural risks that have caused great impacts worldwide. The aim of this research was to explore a method based on machine learning to evaluate susceptibility to rotational landslides in an area near Cuenca city, Ecuador, which has a high incidence of these phenomena, mainly due to its environmental conditions, and in which, however, such studies are scarce. The implemented method consisted of an artificial neural network multilayer perceptron (ANN MLP), generated with the neuralnet R package, with which, by means of different backpropagation algorithms (RPROP+, RPROP−, SLR, SAG, and Backprop), five landslide susceptibility maps (LSMs) were generated for the study area. A landslide inventory updated to 2019 and 10 conditioning factors, mainly topographical, geological, land cover, and hydrological, were considered. The results obtained, which were validated through the AUC-ROC value and statistical parameters of precision, recall, accuracy, and F-Score, showed a good degree of adjustment and an acceptable predictive capacity. The resulting maps showed that the area has mostly sectors of moderate, high, and very high susceptibility, whose landslide occurrence percentages vary between approximately 63% and 80%. In this research, different variants of the backpropagation algorithm were implemented to verify which one gave the best results. With the implementation of additional methodologies and correct zoning, future analyses could be developed, contributing to adequate territorial planning and better disaster risk management in the area.

In most countries, landslides have caused severe socioeconomic impacts on people, cities, industrial establishments, and lifelines, such as highways, railways, and communication network systems. Socioeconomic losses due to slope failures are very high and they have been growing as the built environment expands into unstable hillside areas under the pressures of growing populations. Human activities as the construction of buildings, transportation routes, dams, and artificial canals have often been a major factor for the increasing damage due to slope failures. When recovery actions are not durable from an economic point of view, increasing the population’s awareness is the key strategy to reduce the effects of natural and anthropogenic events. Starting from the case study of the Pan-American Highway (the Ecuadorian part), this article shows a multi-approach strategy for infrastructure monitoring. The combined use of (i) DInSAR technique for detection of slow ground deformations, (ii) field survey activities, and (iii) the QPROTO tool for analysis of slopes potentially prone to collapse allowed us to obtain a first cognitive map to better characterize 22 km of the highway between the cities of Cuenca and Azogues. This study is the primary step in the development of a landslide awareness perspective to manage risk related to landslides along infrastructure corridors, increasing user safety and providing stakeholders with a management system to plan the most urgent interventions and to ensure the correct functionality of the infrastructure.

Underground mining can produce subsidence phenomena, especially if orebodies are surficial or occur in soft rocks. In some countries, illegal mining is a big problem for environmental, social and economic reasons. However, when unauthorized excavation is conducted underground, it is even more dangerous because it can produce unexpected surficial collapses in areas not adequately monitored. For this reason, it is important to find quick and economic techniques able to give information about the spatial and temporal development of uncontrolled underground activities in order to improve the risk management. In this work, the differential interferometric synthetic aperture radar (DInSAR) technique, implemented in the SUBSOFT software, has been used to study terrain deformation related to illegal artisanal mining in Ecuador. The study area is located in Zaruma (southeast of El Oro province), a remarkable site for Ecuadorian cultural heritage where, at the beginning of the 2017, a local school collapsed, due to sinkhole phenomena that occurred around the historical center. The school, named “Inmaculada Fe y Alegria”, was located in an area where mining activity was forbidden. For this study, the surface deformations that occurred in the Zaruma area from 2015 to 2019 were detected by using the Sentinel-1 data derived from the Europe Space Agency of the Copernicus Program. Deformations of the order of five centimeters were revealed both in correspondence of known exploitation tunnels, but also in areas where the presence of tunnels had not been verified. In conclusion, this study allowed to detect land surface movements related to underground mining activity, confirming that the DInSAR technique can be applied for monitoring mining-related subsidence.