Search

Landslides are disasters that cause damage to anthropic activities, innumerable loss of human life, and affect the natural ecosystem and its services globally. The landslide risk evaluated by integrating susceptibility and vulnerability maps has recently become a manner of studying sites prone to landslide events and managing these regions well. Developing countries, where the impact of landslides is frequent, need risk assessment tools to address these disasters, starting with their prevention, with free spatial data and appropriate models. However, to correctly understand their interrelationships and social affection, studying the different ecosystem services that relate to them is necessary. This study is the first that has been attempted in which an integrated application methodology of ecosystem services is used to know in a systematic way if the information that ecosystem services provide is useful for landslide risk assessment. For the integration of ecosystem services into the landslide risk evaluation, (1) eight ecosystem services were chosen and mapped to improve understanding of the spatial relationships between these services in the Guerrero State (México), and (2) areas of synergies and trade-offs were identified through a principal component analysis, to understand their influence on risk analysis better. These are extracted from the models of the ARIES platform, artificial intelligence, and big data platform. Finally, (3) the similarity between the risk characteristics (susceptibility and vulnerability, already mapped by the authors) and the ecosystem services assessment was analysed. The results showed that the ecosystem services that most affect the synergy are organic carbon mass and the potential value of outdoor recreation; meanwhile, the possible removed soil mass was the most important trade-off. Furthermore, the lowest similarity value was found between landslide vulnerability and ecosystem services synergy, indicating the importance of including these ecosystem services as a source of valuable information in the risk analysis methodologies, especially with respect to risk vulnerability. [ABSTRACT FROM AUTHOR]

Landslides are recognized as high-impact natural hazards in different regions around the world; therefore, they are extensively researched by experts. Landslide inventories are essential to identify areas that are likely to be affected in the future, thereby enabling interventions to prevent loss of life. Today, through combined approaches, such as remote sensing and machine learning techniques, it is possible to apply algorithms that use data derived from satellite images to produce landslide inventories. This work presents the performance of five machine learning methods—k-nearest neighbor (KNN), stochastic gradient descendent (SGD), support vector machine radial basis function (SVM RBF Kernel), support vector machine (SVM linear kernel), and AdaBoost—in landslide detection in a zone of the state of Guerrero in southern Mexico, using continuous change maps and primary landslide factors, such as slope angle, terrain orientation (aspect), and lithology, as inputs. The models were trained with 2/3 of ground truth samples of 671 slidden/non-slidden polygons. The obtained inventory maps were evaluated with the remaining 1/3 of ground truth samples by generating a confusion matrix and applying the Kappa concordance coefficient, accuracy, precision, recall, and F1 score as evaluation metrics, as well as omission and commission errors. According to the results, the AdaBoost classifier reached greater spatial and statistical coherence than the other implemented methods. The best input layer combination for detection was the continuous change maps obtained by the linear regression and image differencing detection methods, together with the slope angle, aspect, and lithology conditioning factors. [ABSTRACT FROM AUTHOR]