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.

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.

La importancia del espacio radica en que todos los eventos que ocurren en nuestro planeta están ligados a una ubicación, no solo espacial sino también temporal; es decir, todo ocurre en algún lugar y en algún momento dado. Ante esto, es necesario identificar las propiedades relevantes de estos eventos. Estas propiedades se  relacionan tanto con objetos del mundo real como con las relaciones espaciales entre ellos. En el contexto del análisis de datos espaciales, la dependencia espacial en los valores de los atributos se considera como una  propiedad fundamental que se determina por la autocorrelación espacial, que ha sido estudiada por varios autores, quienes han brindado diferentes definiciones de esta; sin embargo se puede decir que la autocorrelación espacial permite analizar la variabilidad de un fenómeno en el espacio para determinar patrones y verificar su comportamiento. Cuando la autocorrelación espacial es fuerte, los valores cercanos de una variable están estrechamente relacionados entre sí; pero cuando es débil, o incluso inexistente, los valores de una variable se distribuyen aleatoriamente en el espacio. Existen varios índices formales que miden la autocorrelación espacial a nivel local o global, los cuales son aplicados en diversos ámbitos de estudio y que se describen en esta breve revisión de literatura. Palabras clave: Autocorrelación espacial, índices, análisis espacial, información geográfica. AbstractImportance of space lies in the fact that all events that occur on our planet are linked not only to a spatial but also to a temporal location, i.e. everything happens somewhere and at some point, in time. In view of this, it is necessary to identify the relevant properties of these events. These properties relate both to real-world objects and to spatial relationships between them. In context of spatial data analysis, spatial dependence in attribute values is considered as a fundamental property determined by spatial autocorrelation that has been studied by several authors, who have provided diferent defnitions of it, however, spatial autocorrelation makes it possible to analyze the variability of a phenomenon in space in order to determine patterns and verify its behavior.When spatial autocorrelation is strong, nearby values of a variable are closely related to each other; but when it is weak, or even nonexistent, the values of a variable are randomly distributed in space.There are several formal indices that measure spatial autocorrelation at local or global level, which are applied in various felds of study and are described in this paper. Keywords: Spatial autocorrelation, indices, spatial analysis, geographic information.