Probabilistic frequency ratio (PFR) model for quality improvement of landslide susceptibility mapping from LiDAR-derived DEMs

Pirasteh, Saied; Li, Jonathan

doi:10.1186/s40677-017-0083-z

Cited by 23 publications

(4 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, several soil erosion hazard assessments were conducted by combining the RUSLE model and frequency ratio method [8,27]; and the USLE model and frequency ratio method [23]. The frequency ratio has been employed in several studies to assess the relationship between soil erosion hazard and land-use classes [14,22,28].…”

Section: Introductionmentioning

confidence: 99%

Assessing Soil Erosion Hazards Using Land-Use Change and Landslide Frequency Ratio Method: A Case Study of Sabaragamuwa Province, Sri Lanka

et al. 2020

View full text Add to dashboard Cite

This study aims to identify the vulnerable landscape areas using landslide frequency ratio and land-use change associated soil erosion hazard by employing geo-informatics techniques and the revised universal soil loss equation (RUSLE) model. Required datasets were collected from multiple sources, such as multi-temporal Landsat images, soil data, rainfall data, land-use land-cover (LULC) maps, topographic maps, and details of the past landslide incidents. Landsat satellite images from 2000, 2010, and 2019 were used to assess the land-use change. Geospatial input data on rainfall, soil type, terrain characteristics, and land cover were employed for soil erosion hazard classification and mapping. Landscape vulnerability was examined on the basis of land-use change, erosion hazard class, and landslide frequency ratio. Then the erodible hazard areas were identified and prioritized at the scale of river distribution zones. The image analysis of Sabaragamuwa Province in Sri Lanka from 2000 to 2019 indicates a significant increase in cropping areas (17.96%) and urban areas (3.07%), whereas less dense forest and dense forest coverage are significantly reduced (14.18% and 6.46%, respectively). The average annual soil erosion rate increased from 14.56 to 15.53 t/ha/year from year 2000 to 2019. The highest landslide frequency ratios are found in the less dense forest area and cropping area, and were identified as more prone to future landslides. The river distribution zones Athtanagalu Oya (A-2), Kalani River-south (A-3), and Kalani River- north (A-9), were identified as immediate priority areas for soil conservation.

show abstract

Section: Introductionmentioning

confidence: 99%

Assessing Soil Erosion Hazards Using Land-Use Change and Landslide Frequency Ratio Method: A Case Study of Sabaragamuwa Province, Sri Lanka

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Intermediate complexity statistical methods are used to assess the relative landslide sensitivity on a regional scale [6]. In [7][8], the authors applied the PFR model to consider the influence of landslide-related factors related to high-resolution images of Google Earth and field observations. The results show that compared with the existing data and previous studies in the same area, the LiDAR-derived DEM using the PFR model improves the landslide sensitivity map with an accuracy performance of 92.59%.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Machine Learning Algorithm for Landslide Sensitive Spatial Model Based on GIS Taking the Area along Sichuan-Tibet Railway as an Example

2023

IJETC

View full text Add to dashboard Cite

With the development of GIS-based geospatial information technology, new methods have been provided for landslide disaster research. However, there is currently no suitable way to combine GIS technology with machine algorithms. In order to construct a highly accurate landslide sensitivity spatial model, this paper statistically analyzes the relationship between landslide disasters and various influencing factors in the study area through the GIS spatial analysis function, especially for the actual situation along the Sichuan-Tibet Railway. In this paper, a cross-check method is used to construct a landslide sensitivity evaluation model, and the accuracy of different models is quantitatively evaluated. The results of the fitting accuracy of the logistic regression model and the support vector machine model are: the average accuracy in the modeling stage is 75.722 and 75.65, and the average accuracy in the verification stage is 71.34 and 71.21. At the modeling stage, the SVM model has a fitting accuracy of about 3% higher than that of the logistic regression model; at the verification stage, the fitting accuracy is 0.13% higher than that of the logistic regression model; the AUC results show that the SVM model performs optimally, its AUC value is above 0.9, which achieves a higher accuracy. Compared with the logistic regression model, this value is 0.111 higher in the modeling stage and 0.111 higher in the verification stage.

show abstract

“…Existing statistical methods are divided into classical statistical and machine learning (ML) based methods [12]. Frequency ratio [13,14], weight of evidence (WofE) [15] and information value (InfoVal) [16,17] are classical statistical models, which depend on linear relationships between landslide occurrence and predisposing factors. Considering the mechanism of landslide JSTARS-2020-01073 occurrence is complex, mining non-linear relationships between landslide inventory and predisposing factors is direction for the improvement of LSM reliability [18]; In recent years, ML models, such as logistic regression (LR) [19,20], multi-layer perceptron (MLP) [17,21,22], support vector machine (SVM) [23,24], random forest (RF) [25][26][27], decision tree (DT) [28,29], etc.…”

Section: Introductionmentioning

confidence: 99%

Landslide Susceptibility Mapping Using Feature Fusion-Based CPCNN-ML in Lantau Island, Hong Kong

Chen

Ming

Xiao

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Landslide susceptibility mapping (LSM) is an effective way to predict spatial probability of landslide occurrence. Existing convolutional neural networks (CNN)-based methods apply self-built CNN with simple structure, which failed to reach CNN's full potential on high-level feature extraction, meanwhile ignored the use of numerical predisposing factors. For the purpose of exploring feature fusion based CNN models with greater reliability in LSM, this study proposes an ensemble model based on channel-expanded pre-trained CNN and traditional machine learning model (CPCNN-ML). In CPCNN-ML, pre-trained CNN with mature structure is modified to excavate high-level features of multi-channel predisposing factor layers. LSM result is generated by traditional machine learning (ML) model based on hybrid feature of high-level features and numerical predisposing factors. Lantau Island, Hong Kong is selected as study area, temporal landslide inventory is used for model training and evaluation. Experimental results show that CPCNN-ML has ability to predict landslide occurrence with high reliability, especially the CPCNN-ML based on random forest (RF). Contrast experiments with self-built CNN and traditional ML models further embody the superiority of CPCNN-ML. It is worth noting that coastal regions are newly identified landslide-prone regions compared with previous research. This finding is of great reference value for Hong Kong authorities to formulate appropriate disaster prevention and mitigation policies.

show abstract

Probabilistic frequency ratio (PFR) model for quality improvement of landslide susceptibility mapping from LiDAR-derived DEMs

Cited by 23 publications

References 51 publications

Assessing Soil Erosion Hazards Using Land-Use Change and Landslide Frequency Ratio Method: A Case Study of Sabaragamuwa Province, Sri Lanka

Assessing Soil Erosion Hazards Using Land-Use Change and Landslide Frequency Ratio Method: A Case Study of Sabaragamuwa Province, Sri Lanka

Evaluation of Machine Learning Algorithm for Landslide Sensitive Spatial Model Based on GIS Taking the Area along Sichuan-Tibet Railway as an Example

Landslide Susceptibility Mapping Using Feature Fusion-Based CPCNN-ML in Lantau Island, Hong Kong

Contact Info

Product

Resources

About