Integration and comparison of algorithmic weight of evidence and logistic regression in landslide susceptibility mapping of the Orumba North erosion-prone region, Nigeria

Nwazelibe, Vincent E.; Unigwe, Chinanu O.; Egbueri, Johnbosco C.

doi:10.1007/s40808-022-01549-6

Cited by 25 publications

(24 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, they can also intensify forces acting on slopes, potentially causing landslides to occur. Similar inferences also apply to plan curvature (Nwazelibe et al, 2023a(Nwazelibe et al, , 2023b. Furthermore, landslides are more common at higher elevations due to steeper slopes and a more complex topography, which increases the potential for slope instability (Nebeokike et al, 2020;Sassa et al, 2018).…”

Section: Conditioning Factors For Landslidesmentioning

confidence: 65%

“…For this purpose, determining the accurate location of landslides is prominent for preparing landslide susceptibility maps. Various approaches such as field studies, interpretation of aerial photographs/satellite images and also historical landslide records are used for landslide inventory mapping (Nwazelibe et al, 2023a(Nwazelibe et al, , 2023b. For the present research, 317 landslide events have been recorded in the study area, covering an area of 112.45 km 2 and corresponding to 13.87% of the total area.…”

Section: Landslide Inventory Mappingmentioning

confidence: 99%

“…The road factor maps with 1:50,000 scale were obtained from National Geographic Organization of Iran (www.ngo-org.ir). Rainfall map extracted from 30 years average data of different stations The occurrence of landslides can be significantly affected by the LULC, as alterations in surface runoff patterns, soil properties and vegetation can modify slope stability and raise the likelihood of landslides Nwazelibe et al, 2023aNwazelibe et al, , 2023bWang, Yang, et al, 2023). Removing vegetation covers, whether for domestic and agricultural purposes, industrial or commercial development, can result in higher rates of increased surface runoff and soil erosion and a reduction in soil strength.…”

Section: Conditioning Factors For Landslidesmentioning

confidence: 99%

“…This phenomenon results in diminished soil shear strength and a heightened susceptibility to failure. Regions characterized by a high degree of saturation (DD) often exhibit more infiltration of water into the soil, leading to reduced soil cohesiveness and heightened susceptibility to slope instability and soil failure, particularly in instances of excessive rainfall (Nwazelibe et al, 2023a).…”

Section: Conditioning Factors For Landslidesmentioning

confidence: 99%

“…Unlike the south, slopes facing north receive less sunlight, which makes them damper and colder. With more moisture content, they have less soil strength and higher pore pressure, with more likelihood to experience landslides (Nwazelibe et al, 2023a(Nwazelibe et al, , 2023b. Lithologies with higher permeability, such as sandstone, typically have better drainage and may result in drier soil conditions, decreasing the probability of landslides.…”

Section: Conditioning Factors For Landslidesmentioning

confidence: 99%

See 4 more Smart Citations

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

Yang,

Jiang,

Arabameri

et al. 2023

Geological Journal

Self Cite

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

Section: Conditioning Factors For Landslidesmentioning

confidence: 65%

Section: Landslide Inventory Mappingmentioning

confidence: 99%

Section: Conditioning Factors For Landslidesmentioning

confidence: 99%

Section: Conditioning Factors For Landslidesmentioning

confidence: 99%

Section: Conditioning Factors For Landslidesmentioning

confidence: 99%

See 3 more Smart Citations

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

Yang,

Jiang,

Arabameri

et al. 2023

Geological Journal

Self Cite

View full text Add to dashboard Cite

show abstract

Strategies for sampling pseudo-absences of landslide locations for landslide susceptibility mapping in complex mountainous terrain of Northwest Himalaya

Singh

Chhetri

et al. 2023

Bull Eng Geol Environ

View full text Add to dashboard Cite

Geospatial analysis of factors driving gully erosion: a case study from Southeastern Nigeria

2023

View full text Add to dashboard Cite

Gully erosion studies are usually complex and expensive due to the multiple nature of the causative factors, heterogeneity of the underlying geologic materials, and the high volume of point source data required within a given area. For this reason, thorough gully erosion studies are rarely carried out especially in developing countries with little resources allocated to environmental studies. Thus, it becomes di cult in solving problems arising from such geologic hazard in those areas. However, the availability of data emanating from remotely sensed operations can be utilized in solving complex gully erosional problems using modern geospatial analytical tools. Consequently, gully erosion studies within the study area were carried out by integration of geomorphologic and environmental data which were acquired remotely, and geotechnical information derived from eld and laboratory investigations of the underlying geologic materials. The integrated geomorphologic, environmental, and geotechnical data was analysed with analytical tools such as ArcGIS, Google Earth, and Microsoft Excel, following the frequency ratio method. Results from the study revealed that slope angle, soil plasticity, angle of internal friction, cohesion, and population density contributed about 20%, 23%, 20%, 18%, and 9%, respectively to soil's susceptibility to gullying. Slope angle and population density were positively correlated with the frequency of gully erosion, whereas plasticity, cohesion, and angle of internal friction were negatively correlated with frequency of gully erosion. The spatial distribution of the data revealed areas that are susceptible to gullying in their various degrees; thus providing affordable information for proper environmental planning and development.

show abstract

Integration and comparison of algorithmic weight of evidence and logistic regression in landslide susceptibility mapping of the Orumba North erosion-prone region, Nigeria

Cited by 25 publications

References 66 publications

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

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

Strategies for sampling pseudo-absences of landslide locations for landslide susceptibility mapping in complex mountainous terrain of Northwest Himalaya

Geospatial analysis of factors driving gully erosion: a case study from Southeastern Nigeria

Contact Info

Product

Resources

About