9:15 AM - 9:30 AM
[HDS05-02] Development of AI Algorithms for landslides prediction (Emilia-Romagna Region, Italy)
Keywords:Landslide, Rainfall thresholds, Machine learning, Northern Italian Apennines
Landslide risk is one of the most relevant hazard that affects the Emilia-Romagna Region. Almost 80,000 landslides were mapped in the mountainous part, and the percentage of land covered by landslides exceeds in some areas 25%. Although most of the regional landslides are relatively slow, the economic impact is critical: in 2019, 1 million euros was allocated for urgent safety interventions, and it is estimated that at least another 80 would be needed to complete the plan. These numbers place the Emilia-Romagna Region among the areas with the highest landslide risk in the world. The geological characteristics of the Region, combined with the growing exploitation of the territory and the climatic changes underway, are making this problem more and more dramatic. It is now clear that emergency responses are no longer sufficient and that they must be accompanied by prevention actions devoted to mitigate the risk. More efforts are needed to forecast the critical rainfall conditions leading to slope instability as well as to predict the reactivation of dormant landslides and the triggering factors of first-time failures. Unfortunately, such goals are difficult to reach due to the substantial unpredictability of landslides.
The main objective of this work is to develop Artificial Intelligence models for the prediction of landslides in the Emilia-Romagna Region. The idea is to exploit the data collected by the University of Bologna in the last 75 years, as part of the research activities carried out in collaboration with the Regional Agency for Civil Protection and the Geological Survey of the Emilia-Romagna Region.
Machine learning and conventional approaches were applied to the Emilia-Romagna region of Italy using a historical landslide and rainfall data archive. The methods included Bayesian approach, Neural Networks, XGBoost, TPOT, Random Forest, LDA, QDA, and Linear Regression. Results showed that landslides in the area were mostly caused by rainfall event parameters such as precipitation during the event and its location, while antecedent rainfall was found to be less important. The results indicated that a rain event of 90-100 mm was necessary to trigger a landslide after the dry summer season, but this decreased as the day of the year increased. The algorithm had an F2 score test result of 0.54, meaning it could correctly predict a true positive (rainfall causing landslide) every 3 positive instances and correctly predict a true negative (rainfall not causing landslide) 95.5% of the time.
The main objective of this work is to develop Artificial Intelligence models for the prediction of landslides in the Emilia-Romagna Region. The idea is to exploit the data collected by the University of Bologna in the last 75 years, as part of the research activities carried out in collaboration with the Regional Agency for Civil Protection and the Geological Survey of the Emilia-Romagna Region.
Machine learning and conventional approaches were applied to the Emilia-Romagna region of Italy using a historical landslide and rainfall data archive. The methods included Bayesian approach, Neural Networks, XGBoost, TPOT, Random Forest, LDA, QDA, and Linear Regression. Results showed that landslides in the area were mostly caused by rainfall event parameters such as precipitation during the event and its location, while antecedent rainfall was found to be less important. The results indicated that a rain event of 90-100 mm was necessary to trigger a landslide after the dry summer season, but this decreased as the day of the year increased. The algorithm had an F2 score test result of 0.54, meaning it could correctly predict a true positive (rainfall causing landslide) every 3 positive instances and correctly predict a true negative (rainfall not causing landslide) 95.5% of the time.