Improvement of the predictive performance of landslide mapping models in mountainous terrains using cluster sampling

Riaz, Muhammad Tayyib; Basharat, Muhammad; Pham, Quoc Bao; Sarfraz, Yasir; Shahzad, Amir; Ahmed, Khawaja Shoaib; Ikram, Nawaz; Waseem, Muhammad

doi:10.1080/10106049.2022.2066202

Cited by 8 publications

(11 citation statements)

References 146 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Slope, TRI, NDVI, distance to streams, faults and TWI are influential LCFs using random partitioning techniques. The slope angle was shown to be the most important factor in both cluster and random partitioning approaches, which is consistent with the observations of Pham et al (2021), Ali et al (2021) and Riaz et al (2022). When compared to gentle slopes, steeper slopes have a greater impact on mass wasting (Basharat et al, 2021).…”

Section: Landslide Susceptibility Mapping Via Random Forestsupporting

confidence: 84%

“…Landcover receives the most weight, followed by lithology and slope gradient, according to Riaz et al (2018). Recently Riaz et al (2022) used MLAs for LSM in the largest district of AJK (Kashmir Himalayas) and found that slope gradient is the most influential LCF in the region. Our results confirm that landslide patterns are clustered and cluster training sampling enhances the prediction efficacy in the selected landslide-prone and mountainous district.…”

Section: Comparison Of Model Performance and Validationmentioning

confidence: 99%

“…In complex mountainous terrain like northern Pakistan, landslides are among the primary disasters that cause fatalities, damage to communication linkages, loss of fertile soil and economic losses (Riaz et al, 2022). Steep slopes, active tectonics, unstable rock units and heavy rains in the northern region of Azad Kashmir make it vulnerable to natural hazards, particularly landslides.…”

Section: ⅰ Introductionmentioning

confidence: 99%

“…This model has been employed by several researchers in recent years (e.g. Zhao et al, 2020; Pham et al, 2021; El-Magd et al, 2021; Riaz et al, 2022). The Naïve Bayes (NB) model is based on Bayes theory; defined as a supervised probabilistic algorithm that has been used in numerous landslide research in the recent past (El-Magd et al, 2021; Pham et al, 2021).…”

Section: ⅰ Introductionmentioning

confidence: 99%

“…It has the potential to enable remote training, interact with a cloud dataflow system and use standardized models to tackle the problems related to over-fitting. So far, the XGBoost model has only been used in a few studies in the past 2 years (Mirzaei et al, 2021; Pham et al, 2021; Riaz et al, 2022). The K-Nearest Neighbour (KNN) (Merghadi et al, 2020) is also a commonly used approach.…”

Section: ⅰ Introductionmentioning

confidence: 99%

See 4 more Smart Citations

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

Riaz

Basharat

Brunetti

2022

Progress in Physical Geography: Earth and Environment

View full text Add to dashboard Cite

Several devastating landslides have occurred in the NW Himalayas, which has prompted several researchers to strive for improvement in landslide susceptibility modelling (LSM) methodologies. This research analyzes the effectiveness of alternative landslide partitioning techniques on LSM in the landslide-prone district, Muzaffarabad, Pakistan. We developed a landslide inventory of 961 landslides and then traditionally divided it into training (672; 70%) and testing (289; 30%) samples. These training samples (672) are processed by the Average Nearest Neighbour Index (ANNI) method to estimate the spatial pattern of landslides in nature. The results provide an ANNI ratio of 0.672 confirming that the landslides distribution pattern is cluster in the complex Himalayan terrain of Muzaffarabad. Among 672, the majority of landslides (529; 79%) depict cluster behaviour, while 189 landslides (21%) depict random behaviour. To evaluate the effectiveness of landslide cluster samples in prediction, five machine learning algorithms (MLAs), that is, K-Nearest Neighbour (KNN), Naïve Bayes (NB), Random Forest (RF), Extreme Gradient Boosting (XGBoost) and Logistic Regression (LR) using proposed cluster (529) and traditional (672) random training samples along with 17 geo-environmental factors are executed. However, testing samples (289; 30%) separated at the initial stage remained the same to check the model’s effectiveness. The areas under the curve (AUC-ROC), sensitivity, specificity, Kappa index and accuracy (ACC) have been used to evaluate the MLA’s performances. An alternative partitioning technique (cluster) shows the highest predictive power with AUC-ROC values ranging from 0.96 to 0.86, Kappa index ranges from 0.76 to 0.60 and ACC ranges from 0.90 to 0.83. Conversely, the random partitioning approach performs less well with AUC-ROC values ranging from 0.95 to 0.83, Kappa index ranges from 0.70 to 0.49 and ACC ranges from 0.87 to 0.80. In comparison, the RF cluster sampling-based model outperforms the other models and their counterparts. The RF model achieved the highest accuracy (0.902), highest AUC (0.962) and highest Kappa index (0.755) followed by XGboost having ACC (0.885), AUC (0.95) and Kappa index (0.724) employing proposed cluster training samples. However, traditional random training samples yield comparatively low ACC of RF (0.868) and XGboost (0.862). These results confirm that cluster training sampling performs well in obtaining reliable and precise LSMs for complex Himalayan terrain. Although random landslide partitioning for training datasets is seldom utilized in LSM, this study highlights that cluster partitioning for landslide training datasets might be a realistic and reliable approach.

show abstract