Comparison of landslide susceptibility models and their robustness analysis: a case study from the NW Himalayas, Pakistan

Assessing the effectiveness of alternative landslide partitioning in machine learning methods for landslide prediction in the complex Himalayan terrain

“…According to factor importance analysis, slope, NDVI, SPI, solar radiations, rainfall, distance to faults and streams and lithological units are the most influential LCFs in the case of the proposed cluster model (Figure 8(a)), while slope, SPI, NDVI, solar radiations, rainfall, distance to fault and TWI are most important LCFs in case of traditional random partitioning technique (Figure 8(b)). The most common triggering cause is rainfall, which creates a risk of landslide hazards on steep terrain (Ikram et al, 2021). Rainfall events that are both intense and prolonged have an impact on the state of slope material, as well as incipient shallow landsliding and the reactivation of old landslides (Shirzadi et al, 2017).…”

“…Land use, distance to the river and drainage density have more value in predicting landslides, according to Chowdhuri et al (2021). MLAs have rapidly improved in recent years to tackle the complexity of data processing with greater prediction output than traditional statistical techniques (Huang et al, 2020; Ikram et al, 2021). Recently, Hussain et al (2022) performed the LSM and found that RF has the highest accuracy compared to XGBoost and KNN.…”

“…XGBoost employing the proposed cluster model depicts that 43.09%, 20.47%, 13.07%, 9. . The most common triggering cause is rainfall, which creates a risk of landslide hazards on steep terrain (Ikram et al, 2021). Rainfall events that are both intense and prolonged have an impact on the state of slope material, as well as incipient shallow landsliding and the reactivation of old landslides (Shirzadi et al, 2017).…”

Information Value Model Based Mapping of Updated Spatial and Temporal Landslide Susceptibility: A Case Study from East Sikkim District, India’s Northeastern Himalayas

“…The local lithology (Figure 6h) has a significant impact on the likelihood of mass movement. Lithology is regarded as a well-known criterion that significantly influences the physical characteristics of surface and subsurface materials and plays a significant role in the slope failure process (Ikram et al,2022). The majority of slope failures occurred in weak, unstable, or brittle lithological units.…”

Application of data‐driven techniques for landslide susceptibility prediction along an earthquake‐affected road section in Kashmir Himalaya

“…Generally, an area closer to the fault lines is more susceptible to slope failures than the area further away (Sun et al, 2020) Equal interval, adopted from Ikram et al, 2021) Slope angle ( ) <10; 10-20; 20-30; 30-40; 40-50; 50-60; > 60 The phenomena of landsliding usually occurs in the landforms with higher slope angles (Saha & Saha, 2020) Classification High relative relief within a unit area indicates high slope and therefore, susceptible for landslide (Basu & Pal, 2019) Equal Interval, Qiu et al, 2018) Topographic wetness index (TWI) <5; 5 to 9; >9 Higher TWI values can relate to higher chances of slope failure (Goetz et al, 2011;Y. Wang, Fang, et al, 2020) Geometric Interval (Ikram et al, 2021) Proximity to drainage (m) 0-100; 100-200; 200-300; >300 Areas near to drainage are more vulnerable to landslide occurrence due to high rate of soil erosion (Du et al, 2017) Influence of drainage transport water in culminating landslides as observed in fieldwork, Equal interval (Ikram et al, 2021) Lineament density (km/km 2 ) 0-0.45; 0.45-0.9; 0.9-1.35; 1.35-1.9; 1.9-3.5…”