This study uses automatic linear regression (LINEAR) and arti cial neural network (ANN) models to statistically analyze the area of landslides triggered by the 2021 SW Chelgard earthquake (M L = 6) based on controlling parameters. We recorded and mapped the number of 632 landslides into four groups (based on the Hungr et al. 2014): rock avalanche-rock fall, debris avalanche-ow, rock slump, and slide earth ow-soil slump using eld observation, satellite images, and remote sensing method (before and after the earthquake). The results revealed that most landslides are related to debris avalanche-ow, rock avalanche, and slide earth ow under the disruption in uence of slope structures in limestone and shale units and water absorption after the earthquake in young alluviums and terraces. The spatial distribution of landslides showed that the highest values of the landslide area percentage (LAP%) and of the landslide number density (LND, N/km 2 ) occurred in the northern part of the fault on the hanging wall. The ANN models with R 2 = 0.60-0.75 provided more accurate predictions of landslide area (LA, m 2 ) than the LINEAR models, with R 2 = 0.40-0.60 using multiple parameters. The elevation and slope were found to be the most in uential parameters on the rock slump and the debris avalanche using ANN and LINEAR models. Aspect and elevation are the most important parameters for rock avalanches and rockfalls. The sliding earth ow and soil slump are most affected by the slope and elevation parameters. The peak ground acceleration (PGA) and the distance from the epicenter exhibited more effects on the LA than the intensity of Arias (Ia) and the distance from the rupture surface. Thus, the separation of seismic landslides using the classi cation of Hungr et al. ( 2014) can be helpful for predicting the LA more accurately and understanding the failure mechanism better.