Analyze the rainfall of landslide on Apache Spark

Lee, Chou‐Yuan; Huang, Jian-Qiong; Ma, Wanli; Weng, Yu-Lin; Lee, Yuan-Chih; Lee, Zne-Jung

doi:10.1109/icaci.2018.8377482

Cited by 2 publications

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When it comes to the combination of these aspects, we can consider to be in the context of Big Data, for volume, variety, velocity, veracity, and value of data. Moreover, with the aim of producing predictions in a data driven approach, many different machine learning and deep learning algorithms have been applied in a variety of use cases: Logistic regression (LR), Support Vector Machine (SVM), Random forest (RF), Boosting, Convolutional Neural Network (CNN), as stated in [14], [17], [19], [20] [21]. The SIGMA algorithm, which was firstly developed in Emilia Romagna Region [6] and then tested in India [22], is a landslide early warning model based on the analysis of the probability related to exceedance of defined rainfall amounts.…”

Section: Introductionmentioning

confidence: 99%

Predicting and Understanding Landslide Events With Explainable AI

et al. 2022

View full text Add to dashboard Cite

Rainfall induced landslide is one of the main geological hazard in Italy and in the world. Each year it causes fatalities, casualties and economic and social losses on large populated areas. Accurate shortterm predictions of landslides can be extremely important and useful, in order to both provide local authorities with efficient prediction/early warning and increase the resilience to manage emergencies. There is an extensive literature addressing the problem of computing landslide susceptibility maps (which is a classification problem exploiting a large range of static features) and only few on actual short terms predictions (spatial and temporal). The short-term prediction models are still empirical and obtain unsatisfactory results, also in the identification of the predictors. The new aspects addressed in this paper are: (i) a short-term prediction model (1 day in advance) of landslide based on machine learning, (ii) real time features as good predictors. The introduction of explainable artificial intelligence techniques allowed to understand global and local feature relevance. In order to find the best prediction model, a number of machine learning solutions have been implemented and assessed. The models obtained overcome those of the literature. The validation has been performed in the context of the Metropolitan City of Florence, data from 2013 to 2019. The method based on XGBoost achieved best results, demonstrating that it is the most reliable and robust against false alarms. Finally, we applied explainable artificial intelligence techniques locally and globally to derive a deep understand of the predictive model's outputs and features' relevance, and relationships. The analysis allowed us to identify the best feature for short term predictions and their impact in the local cases and global prediction model. Solutions have been implemented on Snap4City.org infrastructure.

show abstract