scholarly journals A Novel Performance Assessment Approach using Photogrammetric Techniques for Landslide Susceptibility Mapping with Logistic Regression, ANN and Random Forest

Sensors ◽  
2019 ◽  
Vol 19 (18) ◽  
pp. 3940 ◽  
Author(s):  
Sevgen ◽  
Kocaman ◽  
Nefeslioglu ◽  
Gokceoglu
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Random Forest ◽  
Performance Assessment ◽  
Landslide Susceptibility ◽  
Machine Learning Algorithms ◽  
Landslide Susceptibility Mapping ◽  
Susceptibility Maps ◽  
Surface Models ◽  
Landslide Susceptibility Maps

Prediction of possible landslide areas is the first stage of landslide hazard mitigation efforts and is also crucial for suitable site selection. Several statistical and machine learning methodologies have been applied for the production of landslide susceptibility maps. However, the performance assessment of such methods have conventionally been carried out by utilizing existing landslide inventories. The purpose of this study is to investigate the performances of landslide susceptibility maps produced with three different machine learning algorithms, i.e., random forest, artificial neural network, and logistic regression, in a recently constructed and activated dam reservoir and assess the external quality of each map by using pre- and post-event photogrammetric datasets. The methodology introduced here was applied using digital surface models generated from aerial photogrammetric flight data acquired before and after the dam construction. Aerial photogrammetric images acquired in 2012 and 2018 (after the dam was filled) were used to produce digital terrain models and orthophotos. The 2012 dataset was used for producing the landslide susceptibility maps and the results were evaluated by comparing the Euclidian distances between the two surface models. The results show that the random forest method outperforms the other two for predicting the future landslides.

scholarly journals Improving Spatial Agreement in Machine Learning-Based Landslide Susceptibility Mapping

2020 ◽  
Vol 12 (20) ◽  
pp. 3347 ◽  
Author(s):  
Mohammed Sarfaraz Gani Adnan ◽  
Md Salman Rahman ◽  
Nahian Ahmed ◽  
Bayes Ahmed ◽  
Md. Fazleh Rabbi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Landslide Susceptibility ◽  
Prediction Accuracy ◽  
Correlation Coefficients ◽  
Machine Learning Algorithms ◽  
Landslide Susceptibility Mapping ◽  
Natural Phenomenon ◽  
Support Vector ◽  
Susceptibility Maps ◽  
Landslide Susceptibility Maps

Despite yielding considerable degrees of accuracy in landslide predictions, the outcomes of different landslide susceptibility models are prone to spatial disagreement; and therefore, uncertainties. Uncertainties in the results of various landslide susceptibility models create challenges in selecting the most suitable method to manage this complex natural phenomenon. This study aimed to propose an approach to reduce uncertainties in landslide prediction, diagnosing spatial agreement in machine learning-based landslide susceptibility maps. It first developed landslide susceptibility maps of Cox’s Bazar district of Bangladesh, applying four machine learning algorithms: K-Nearest Neighbor (KNN), Multi-Layer Perceptron (MLP), Random Forest (RF), and Support Vector Machine (SVM), featuring hyperparameter optimization of 12 landslide conditioning factors. The results of all the four models yielded very high prediction accuracy, with the area under the curve (AUC) values range between 0.93 to 0.96. The assessment of spatial agreement of landslide predictions showed that the pixel-wise correlation coefficients of landslide probability between various models range from 0.69 to 0.85, indicating the uncertainty in predicted landslides by various models, despite their considerable prediction accuracy. The uncertainty was addressed by establishing a Logistic Regression (LR) model, incorporating the binary landslide inventory data as the dependent variable and the results of the four landslide susceptibility models as independent variables. The outcomes indicated that the RF model had the highest influence in predicting the observed landslide locations, followed by the MLP, SVM, and KNN models. Finally, a combined landslide susceptibility map was developed by integrating the results of the four machine learning-based landslide predictions. The combined map resulted in better spatial agreement (correlation coefficients range between 0.88 and 0.92) and greater prediction accuracy (0.97) compared to the individual models. The modelling approach followed in this study would be useful in minimizing uncertainties of various methods and improving landslide predictions.

Landslide Susceptibility Mapping and Model Performance Assessment

2013 ◽  
Vol 353-356 ◽  
pp. 3487-3493 ◽  
Author(s):  
Chen Chao Xiao ◽  
Yuan Tian ◽  
Kang Ping Si ◽  
Ting Li
Keyword(s):  
Logistic Regression ◽  
Performance Assessment ◽  
Landslide Susceptibility ◽  
Slope Angle ◽  
Model Performance ◽  
Susceptibility Mapping ◽  
Landslide Susceptibility Mapping ◽  
Susceptibility Maps ◽  
Overall Performance ◽  
Better Than

In this paper landslide susceptibility mapping and model performance assessment was conducted using three models, logistic regression, GAM, and SVM, in a study area in Shenzhen, China. Ten factors, slope angle, aspect, elevation, plan and profile curvature of the slope, lithology, NDVI, building density, the distance to the river, and the distance to the fault were selected as influencing factors for the landslide occurrences. All three models were trained and the resulting susceptibility maps were created. The performances of the three models were then assessed by AUC values through a 10-fold cross-validation. It could be concluded that in the study area GAM had the best overall performance among the three models, while SVM was better than logistic regression. Based on the derived DPR values, the optimum thresholds between stable areas and risky areas for all three models were also determined.

scholarly journals Landslide Susceptibility Mapping Using Integrated Methods: A Case Study in the Chittagong Hilly Areas, Bangladesh

Geosciences ◽  
2020 ◽  
Vol 10 (12) ◽  
pp. 483
Author(s):  
Yasin Wahid Rabby ◽  
Yingkui Li
Keyword(s):  
Logistic Regression ◽  
Landslide Susceptibility ◽  
Regional Scale ◽  
Safe Zone ◽  
Susceptibility Mapping ◽  
Landslide Susceptibility Mapping ◽  
Prediction Rate ◽  
Susceptibility Maps ◽  
Integrated Methods ◽  
Landslide Susceptibility Maps

Landslide susceptibility mapping is of critical importance to identify landslide-prone areas to reduce future landslides, causalities, and infrastructural damages. This paper presents landslide susceptibility maps at a regional scale for the Chittagong Hilly Areas (CHA), Bangladesh. The frequency ratio (FR) was integrated with the analytical hierarchy process (AHP) (FR_AHP) and logistic regression (LR) (FR_LR). A landslide inventory of 730 landslide locations and 13 landslide predisposing factors including elevation, slope, aspect, plan curvature, profile curvature, topographic wetness index (TWI), stream power index (SPI), land use/land cover, rainfall, distance from drainage network, distance from fault lines, lithology, and normalized difference vegetation index (NDVI) were used. Landslide locations were randomly split into training (80%) and validation (20%) sites to support the susceptibility analysis. A safe zone was determined based on a slope threshold for logistic regression using the exploratory data analysis. The same number of non-landslide locations were randomly selected from the safe zone to train the model (FR_LR). Success and prediction rate curves and statistical indices, including overall accuracy, were used to assess model performance. The success rate curves show that FR_LR showed the highest area under the curve (AUC) (79.46%), followed by the FR_AHP (77.15%). Statistical indices also showed that the FR_LR model gave the best performance as the overall accuracy was 0.86 for training and 0.82 for validation datasets. The prediction rate curve shows similar results. The correlation analysis shows that the landslide susceptibility maps produced by FR and FR_AHP are highly correlated (0.95). In contrast, the correlation between the maps produced by FR and FR_LR was relatively lower (0.85). It indicates that the three models are highly convergent with each other. This study’s integrated methods would be helpful for regional-scale landslide susceptibility mapping, and the landslide susceptibility maps produced would be useful for regional planning and disaster management of the CHA, Bangladesh.

scholarly journals Application of Ensemble-Based Machine Learning Models to Landslide Susceptibility Mapping

2018 ◽  
Vol 10 (8) ◽  
pp. 1252 ◽  
Author(s):  
Prima Kadavi ◽  
Chang-Wook Lee ◽  
Saro Lee
Keyword(s):  
Machine Learning ◽  
Landslide Susceptibility ◽  
Susceptibility Mapping ◽  
Landslide Susceptibility Mapping ◽  
Learning Models ◽  
Landslide Occurrence ◽  
Susceptibility Maps ◽  
Multiclass Classifier ◽  
Landslide Susceptibility Maps ◽  
Machine Learning Models

The main purpose of this study was to produce landslide susceptibility maps using various ensemble-based machine learning models (i.e., the AdaBoost, LogitBoost, Multiclass Classifier, and Bagging models) for the Sacheon-myeon area of South Korea. A landslide inventory map including a total of 762 landslides was compiled based on reports and aerial photograph interpretations. The landslides were randomly separated into two datasets: 70% of landslides were selected for the model establishment and 30% were used for validation purposes. Additionally, 20 landslide condition factors divided into five categories (topographic factors, hydrological factors, soil map, geological map, and forest map) were considered in the landslide susceptibility mapping. The relationships among landslide occurrence and landslide conditioning factors were analyzed and the landslide susceptibility maps were calculated and drawn using the AdaBoost, LogitBoost, Multiclass Classifier, and Bagging models. Finally, the maps were validated using the area under the curve (AUC) method. The Multiclass Classifier method had higher prediction accuracy (85.9%) than the Bagging (AUC = 85.4%), LogitBoost (AUC = 84.8%), and AdaBoost (84.0%) methods.

scholarly journals Assessment of Landslide-Prone Areas and Their Zonation Using Logistic Regression, LogitBoost, and NaïveBayes Machine-Learning Algorithms

2018 ◽  
Vol 10 (10) ◽  
pp. 3697 ◽  
Author(s):  
Hamid Pourghasemi ◽  
Amiya Gayen ◽  
Sungjae Park ◽  
Chang-Wook Lee ◽  
Saro Lee
Keyword(s):  
Machine Learning ◽  
Land Use ◽  
Logistic Regression ◽  
South Korea ◽  
Landslide Susceptibility ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Slope Position ◽  
Conditioning Factors ◽  
Susceptibility Maps

The occurrence of landslide in the hilly region of South Korea is a matter of serious concern. This study tries to produce landslide susceptibility maps for Jumunjin Country in South Korea. Three machine learning algorithms, namely Logistic Regression (LR), LogitBoost (LB), and NaïveBayes (NB) are used, and their final model outcomes are compared to each other. Firstly, a landslide inventory map and the associated input data layers of the landslide conditioning factors were developed based on field verification, historical records, and high-resolution remote-sensing data in the geographic information system (GIS) environment. Seventeen landslide conditioning factors were prepared, including aspect, slope, altitude, maximum curvature, profile curvature, topographic wetness index (TWI), topographic positioning index (TPI), distance from fault, convexity, forest type, forest diameter, forest density, land use/land cover, lithology, soil, flow accumulation, and mid slope position. The result showed that the area under the curve (AUC) values of LR, LB, and NB models were 84.2%, 70.7%, and 85.2%, respectively. The results revealed that the LR and LB models produced reasonable accuracy than respect to NB model in landslide susceptibility assessment. The final susceptibility maps would be useful for preliminary land-use planning and hazard mitigation purpose.

scholarly journals Frequency Ratio Density, Logistic Regression and Weights of Evidence Modelling for Landslide Susceptibility Assessment and Mapping in Yanase and Naka Catchments of Southeast Shikoku, Japan

2020 ◽  
Author(s):  
Matebie Meten ◽  
Netra Prakash Bhandary
Keyword(s):  
Logistic Regression ◽  
Landslide Susceptibility ◽  
Frequency Ratio ◽  
Weights Of Evidence ◽  
Landslide Susceptibility Mapping ◽  
Annual Rainfall ◽  
Slope Aspect ◽  
Equal Proportion ◽  
Susceptibility Maps ◽  
Landslide Susceptibility Maps

Abstract Landslide susceptibility mapping is an important tool for disaster management and development activities such as planning of transportation infrastructure, settlement and agriculture. Shikoku Island, which is found in the southwest of Japan, is one of the most landslide prone areas because of heavy typhoon rainfall, complex geology and the presence of mountainous areas and low topographic features (valleys).Yanase and Naka Catchments of Shikoku Island in Japan were chosen as a study area. Frequency Ratio Densisty (FRD), Logistic Regression (LR) and Weights of Evidence (WoE) models were applied in a GIS environment to prepare the landslide susceptibility maps of this area. Data layers including slope, aspect, profile curvature, plan curvature, lithology, land use, distance from river, distance from fault and annual rainfall were used in this study. In FR method, two models were attempted but the FRD model was found slightly better in its performance. In case of LR method, two models, one with equal proportion and the other with unequal proportion of landslide and non-landslide points were carried out and the one with equal proportions was chosen based on its highest performance. A total of five landslide susceptibility maps(LSMs) were produced using FR, LR and WoE models with two, two and one were attempted respectively. However, one best model was chosen from the FR and LR methods based on the highest area under the curve (AUC) of the receiver operating characteristic (ROC) curves. This reduced the total number of landslide susceptibility maps to three with the success rates of 86.7%, 86.8% and 80.7% from FRD, LR and WoE models respectively. For validation purpose, all landslides were overlaid over the three landslide susceptibility maps and the percentage of landslides in each susceptibility class was calculated. The percentages of landslides that fall in the high and very high susceptibility classes of FRD, LR and WoE models showed 82%, 84% and 78% respectively. This showed that the LR model with equal proportions of landslides and non-landslide points is slightly better than FRD and WoE models in predicting the future probability of landslide occurrence.

scholarly journals GENETIC ALGORITHM BASED FEATURE SELECTION FOR LANDSLIDE SUSCEPTIBILITY MAPPING IN NORTHERN IRAN

2019 ◽  
Vol XLII-4/W18 ◽  
pp. 821-825
Author(s):  
Z. Nikraftar ◽  
S. Rajabi-Kiasari ◽  
S. T. Seydi
Keyword(s):  
Genetic Algorithm ◽  
Land Use ◽  
Land Use Planning ◽  
Landslide Susceptibility ◽  
Machine Learning Algorithms ◽  
Landslide Susceptibility Mapping ◽  
Support Vector ◽  
Northern Iran ◽  
Susceptibility Maps ◽  
Landslide Susceptibility Maps

Abstract. Recognizing where landslides are most likely to occur is crucial for land use planning and decision-making especially in the mountainous areas. A significant portion of northern Iran (NI) is prone to landslides due to its climatology, geological and topographical characteristics. The main objective of this study is to produce landslide susceptibility maps in NI applying three machine learning algorithms such as K-nearest neighbors (KNN), Support Vector Machines (SVM) and Random Forest (RF). Out of the total number of 1334 landslides identified in the study area, 894 (≈67%) locations were used for the landslide susceptibility maps, while the remaining 440 (≈33%) cases were utilized for the model validation. 21 landslide triggering factors including topographical, hydrological, lithological and Land cover types were extracted from the spatial database using SAGA (System for Automated Geoscientific Analyses), ArcGIS software and satellite images. Furthermore, a genetic algorithm was employed to select the most important informative features. Then, landslide susceptibility was analyzed by assessing the environmental feasibility of influential factors. The obtained results indicate that the RF model with the overall accuracy (OA) of 90.01% depicted a better performance than SVM (OA = 81.06%) and KNN (OA = 83.05%) models. The produced susceptibility maps can be productively practical for upcoming land use planning in NI.

scholarly journals Hybrid Integration Approach of Entropy with Logistic Regression and Support Vector Machine for Landslide Susceptibility Modeling

Entropy ◽  
2018 ◽  
Vol 20 (11) ◽  
pp. 884 ◽  
Author(s):  
Tingyu Zhang ◽  
Ling Han ◽  
Wei Chen ◽  
Himan Shahabi
Keyword(s):  
Support Vector Machine ◽  
Logistic Regression ◽  
Landslide Susceptibility ◽  
Shaanxi Province ◽  
Slope Aspect ◽  
Support Vector ◽  
Operating Characteristics ◽  
Study Region ◽  
Susceptibility Maps ◽  
Landslide Susceptibility Maps

The main purpose of the present study is to apply three classification models, namely, the index of entropy (IOE) model, the logistic regression (LR) model, and the support vector machine (SVM) model by radial basis function (RBF), to produce landslide susceptibility maps for the Fugu County of Shaanxi Province, China. Firstly, landslide locations were extracted from field investigation and aerial photographs, and a total of 194 landslide polygons were transformed into points to produce a landslide inventory map. Secondly, the landslide points were randomly split into two groups (70/30) for training and validation purposes, respectively. Then, 10 landslide explanatory variables, such as slope aspect, slope angle, altitude, lithology, mean annual precipitation, distance to roads, distance to rivers, distance to faults, land use, and normalized difference vegetation index (NDVI), were selected and the potential multicollinearity problems between these factors were detected by the Pearson Correlation Coefficient (PCC), the variance inflation factor (VIF), and tolerance (TOL). Subsequently, the landslide susceptibility maps for the study region were obtained using the IOE model, the LR–IOE, and the SVM–IOE model. Finally, the performance of these three models was verified and compared using the receiver operating characteristics (ROC) curve. The success rate results showed that the LR–IOE model has the highest accuracy (90.11%), followed by the IOE model (87.43%) and the SVM–IOE model (86.53%). Similarly, the AUC values also showed that the prediction accuracy expresses a similar result, with the LR–IOE model having the highest accuracy (81.84%), followed by the IOE model (76.86%) and the SVM–IOE model (76.61%). Thus, the landslide susceptibility map (LSM) for the study region can provide an effective reference for the Fugu County government to properly address land planning and mitigate landslide risk.

Sign in / Sign up

Export Citation Format

Share Document