In the last years, statistically based models (such as Logistic Regression) have been frequently used for evaluating the probability of landslide occurrence over large areas. In the case of Rome, over the years, more than 348 landslides have been recorded throughout the city. For this reason, in this study, we implemented and evaluated three main validation criteria of logistic regression to assess the rainfallinduced landslide susceptibility in a specific area of the city of Rome. Through the evaluation of the predictive performances, the best model has been identified and the results were also compared with those obtained in similar case studies.
Validation of a Shallow Landslide Susceptibility Analysis Through a Real Case Study: An Example of Application in Rome (Italy)
Schiliro L;
2020
Abstract
In the last years, statistically based models (such as Logistic Regression) have been frequently used for evaluating the probability of landslide occurrence over large areas. In the case of Rome, over the years, more than 348 landslides have been recorded throughout the city. For this reason, in this study, we implemented and evaluated three main validation criteria of logistic regression to assess the rainfallinduced landslide susceptibility in a specific area of the city of Rome. Through the evaluation of the predictive performances, the best model has been identified and the results were also compared with those obtained in similar case studies.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
