Potential impacts of future climate on the spatio-temporal variability of landslide susceptibility in Iran using machine learning algorithms and CMIP6 climate-change scenarios

Abstract

The objective of this research is to examine the possible impacts of climate change on landslide susceptibility in Iran. To accomplish this, 15 independent variables including 11 static variables, and 4 climatic dynamic variables that can affect landslide susceptibility were applied to predict landslide susceptibility from 3903 landslide susceptibility locations. These data points were separated into two phases for training and testing. Phase 6 of the Coupled Model Intercomparison Project (CMIP6) downscaled the data and enabled the combination of nine global climate models (GCMs) under shared socio-economic pathways (SSPs) to examine the impacts of climate change. The combination of demographic (SSP) and climatic (representative concentration pathways) scenarios were used (e.g., SSP1-2.6 and SSP5-8.5 were used to predict precipitation impacts resulting from climate change at four future dates – 2030, 2050, 2070, and 2090. The machine learning algorithms extreme gradient boosting (XGBoost) and random forest (RF) were employed to model and map landslide susceptibility. The area under curve (AUC) results generated with the testing (validation) phase demonstrates that the predictive power is suitable. The RF model produced the best results (AUC = 0.95). The XGBoost model was not as robust (AUC = 0.93). The investigation of how climate change effects on landslide susceptibility in Iran revealed that climate change should cause shifts in the ranges of susceptibility at different times. The RF model using CMIP SSP1-2.6 predicted the proportion of sites with very-high susceptibility in 2030, 2050, 2070, and 2090 would be 11.45, 11.42, 11.55, and 11.38%. The proportion of sites with high susceptibility would be 15.93, 16.03, 15.79, and 15.95%. And sites with moderate susceptibility will comprise 21.54, 20.92, 21.41, and 20.92%. With the CMIP SSP5-8.5 model, the percentages of locations with very-high susceptibility would be 11.59, 11.70, 11.88, and 12.17%.