The influence of sampling on landslide susceptibility mapping using artificial neural networks

Gameiro, Samuel; Oliveira, Guilherme Garcia de; Guasselli, Laurindo Antônio

doi:10.1080/10106049.2022.2144475

Cited by 8 publications

(6 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…But it is well established that non-landslide sampling reduces the bias of the probabilistic model. There are several methods used for non-landslide sampling such as random choice [ 77 ], buffer analysis [ 78 ], Mahalanobis distances [ 79 ] etc. In Bangladesh non-landslide sampling is always produced arbitrarily (random choice) considering all the areas out of landslide are non-landslide locations.…”

Section: Resultsmentioning

confidence: 99%

“…In Bangladesh non-landslide sampling is always produced arbitrarily (random choice) considering all the areas out of landslide are non-landslide locations. During non-landslide sampling buffer analysis [ 78 ], Mahalanobis distances [ 79 ] should be considered because the distance of non-landslide location has a significant impact on the accuracy of landslide susceptibility map [ 77 , 78 ]. Non-landslide sampling in environmental and lithological heterogeneous and homogeneous areas also affects the accuracy of statistical models [ 80 ].…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A review on landslide susceptibility mapping research in Bangladesh

Chowdhury

2023

Heliyon

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

A review on landslide susceptibility mapping research in Bangladesh

Chowdhury

2023

Heliyon

View full text Add to dashboard Cite

“…In addition, modelling issues such as the extracted attributes can vary if the sample is obtained from different locations with diverse topographic conditions and the mixing problem of landslide inventory (Lai et al, 2019). Therefore, understanding the impact of sample size and location on landslide susceptibility mapping could help produce more accurate and reliable models, which are crucial for risk management and urban planning to prevent damage and harm to people (Gaidzik & Ramírez-Herrera, 2021;Gameiro et al, 2022). Some of the previous studies attempted to estimate the impact of sampling on landslide mapping using ML algorithms such as artificial neural networks (Gameiro et al, 2022;Gao et al, 2020b), boosted regression tree (BRT) model (Pourghasemi et al, 2020); logistic regression (LR), random forest (RF) and support vector machine (SVM) (Dornik et al, 2022;Gao et al, 2020aGao et al, , 2020bLai et al, 2019;Shao et al, 2020;Zhu et al, 2019); and alternating decision tree (ADTree) and information gain ratio (IGR) technique (Shirzadi et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

“…However, there are also several challenges associated with the use of ML, including the risk of overfitting, the need for large and diverse training data sets, and the interpretability of the resulting models (Lv et al, 2022; Merghadi et al, 2020). One key factor influencing the accuracy and reliability of landslide susceptibility maps is the sample size used to develop the model (Gaidzik & Ramírez‐Herrera, 2021; Gameiro et al, 2022). Several studies have been made on landslide susceptibility mapping.…”

Section: Introductionmentioning

confidence: 99%

“…Nevertheless, it is necessary to assess the influence of sample size on the precision of different ML models and to investigate the possible advantages of using varying sample sizes for landslide susceptibility modelling. The allocation of samples between the training and validation sets is a subject of considerable discourse within the sampling procedure (Gameiro et al, 2022; Li et al, 2016; Xiong et al, 2022; Zhu et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Landslide risk assessment and management using hybrid machine learning‐based empirical models

Yang,

Jiang,

Arabameri

et al. 2023

Geological Journal

View full text Add to dashboard Cite

Landslides are a prevalent geologic phenomenon that substantially threatens human life and infrastructure, resulting in considerable loss and destruction. The practice of landslide susceptibility mapping is crucial for the mitigation of risks connected with this natural disaster. This work aims at investigating the influence of varying sample sizes on the precision of landslide susceptibility modelling using a case study conducted in the Alamout basin, Iran. The researchers used a machine learning methodology based on tree algorithms to construct a model for predicting the likelihood of landslides. Additionally, they adopted a multi‐scenario strategy to address the inherent uncertainty associated with the input data. The integration of the naive Bayes tree (NBTree), random forest (RF), logistic model tree (LMT) and J48 algorithms was performed. The modelling process included using 20 predictive parameters across four distinct scenarios. Four models, labelled S1, S2, S3 and S4, were used in this study. These models utilized 25%, 50%, 75% and 100% of the available inventory data. The research presented in this study is distinguished by using a tree‐based methodology for landslide susceptibility modelling and incorporating a multi‐scenario strategy to address the inherent uncertainty associated with the input data. The findings indicated that the augmentation of the sample size improved the precision of the models. The efficacy of using a multi‐scenario strategy in enhancing the dependability of the model is also underscored. Among the 20 input elements used in the modelling process, it was seen that slope angle accounted for the highest relative significance, constituting 25.60% of the overall influence. Following more closely, distance to fault contributed significantly, with a relative importance of 23.40%. Additionally, rainfall and elevation exhibited notable contributions, with relative volumes of 7.91% and 5.50%, respectively. All four landslide models showed adequate learning and forecasting ability throughout the training and testing phases. During the testing phase, the true skill score (TSS) values exhibited a range of 0.631–0.804, while the area under the receiver operating characteristic curve values showed a range of 0.745–0.921. The susceptibility maps indicated that a significant portion of the region exhibits moderate to very high susceptibility zones, with the northern and eastern sectors displaying greater landslide values than the western region. The model's performance showed improvement from S1 to S4 in both the training and testing phases. The performance of the models exhibited the following trend: in scenario 1, the RF model outperformed the J48, LMT and NBTree models; in scenario 2, the RF model surpassed the NBTree and LMT models, while being on par with the J48 model; in scenarios 3 and 4, the RF model showed superior performance compared to the NBTree, J48 and LMT models. Therefore, the RF model proved to be the most effective among the models evaluated. The findings derived from this research have the potential to serve as valuable references for the purposes of land‐use planning and catastrophe risk management.

show abstract