scholarly journals Landslide Susceptibility Mapping Using Logistic Regression Analysis along the Jinsha River and Its Tributaries Close to Derong and Deqin County, Southwestern China

2018 ◽  
Vol 7 (11) ◽  
pp. 438 ◽  
Author(s):  
Xiaohui Sun ◽  
Jianping Chen ◽  
Yiding Bao ◽  
Xudong Han ◽  
Jiewei Zhan ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Regression Analysis ◽  
Influencing Factors ◽  
Logistic Regression Analysis ◽  
Landslide Susceptibility ◽  
Landslide Susceptibility Mapping ◽  
Susceptibility Map ◽  
Key Factors ◽  
Jinsha River ◽  
Landslide Occurrence

The objective of this study was to identify the areas that are most susceptible to landslide occurrence, and to find the key factors associated with landslides along Jinsha River and its tributaries close to Derong and Deqin County. Thirteen influencing factors, including (a) lithology, (b) slope angle, (c) slope aspect, (d) TWI, (e) curvature, (f) SPI, (g) STI, (h) topographic relief, (i) rainfall, (j) vegetation, (k) NDVI, (l) distance-to-river, (m) and distance-to-fault, were selected as the landslide conditioning factors in landslide susceptibility mapping. These factors were mainly obtained from the field survey, digital elevation model (DEM), and Landsat 4–5 imagery using ArcGIS software. A total of 40 landslides were identified in the study area from field survey and aerial photos’ interpretation. First, the frequency ratio (FR) method was used to clarify the relationship between the landslide occurrence and the influencing factors. Then, the principal component analysis (PCA) was used to eliminate multiple collinearities between the 13 influencing factors and to reduce the dimension of the influencing factors. Subsequently, the factors that were reselected using the PCA were introduced into the logistic regression analysis to produce the landslide susceptibility map. Finally, the receiver operating characteristic (ROC) curve was used to evaluate the accuracy of the logistic regression analysis model. The landslide susceptibility map was divided into the following five classes: very low, low, moderate, high, and very high. The results showed that the ratios of the areas of the five susceptibility classes were 23.14%, 22.49%, 18.00%, 19.08%, and 17.28%, respectively. And the prediction accuracy of the model was 83.4%. The results were also compared with the FR method (79.9%) and the AHP method (76.9%), which meant that the susceptibility model was reasonable. Finally, the key factors of the landslide occurrence were determined based on the above results. Consequently, this study could serve as an effective guide for further land use planning and for the implementation of development.

GIS-based Landslide Susceptibility Mapping Using Logistic Regression Analysis: A Case study in the Kadernath valley, Central Himalaya.

2020 ◽  
Author(s):  
Suman Das
Keyword(s):  
Logistic Regression ◽  
Regression Analysis ◽  
Logistic Regression Analysis ◽  
Roc Curve ◽  
Landslide Susceptibility ◽  
Sensor Data ◽  
Landslide Susceptibility Mapping ◽  
Slope Aspect ◽  
Anthropogenic Factors ◽  
Susceptibility Map

<p>Himalayan Terrain is highly susceptible to landslide events triggered by frequent earthquakes and heavy rainfall. In the recent past, cloud burst events are on rising, causing massive loss of life and property, mainly attributed to climate change and extensive anthropogenic activities in the mountain region as experienced in case of 2013 Kedarnath Tragedy. The study aimed to identify the potential landslide hazard zone in Mandakini valley by utilizing different types of data including Survey of India toposheet, geological (lithological and structural) maps, IRS-1D, LISS IV multispectral and PAN satellite sensor data and field observations. Relevant 18 thematic layers pertaining to the causative factors for landslide occurrences, such as slope, aspect, relative relief, lithology, tectonic structures, lineaments, LULC, NDVI, distance to drainage, drainage density and anthropogenic factors like distance to road, have been generated using remote sensing images, field survey, ancillary data and GIS techniques.  A detailed landslide susceptibility map was produced using a logistic regression method with datasets developed in GIS. which has further been categorized into four landslide susceptibility zones from high to very low. Finally, the receiver operating characteristic (ROC) curve was used to evaluate the accuracy of the logistic regression analysis model. ROC curve analysis showing an accuracy of 87.3 % for an independent set of test samples. The result also showed a strong agreement between the distribution of existing landslides and predicted landslide susceptibility zones. Consequently, this study could serve as an effective guide for further land-use planning and for the implementation of development.</p>

Using landslide-inventory mapping for a combined bagged-trees and logistic-regression approach to determining landslide susceptibility in eastern Kentucky, United States

2021 ◽  
pp. qjegh2020-177
Author(s):  
Matthew M. Crawford ◽  
Jason M. Dortch ◽  
Hudson J. Koch ◽  
Ashton A. Killen ◽  
Junfeng Zhu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Standard Deviation ◽  
Landslide Susceptibility ◽  
Engineering Geology ◽  
Susceptibility Mapping ◽  
Landslide Inventory ◽  
Landslide Susceptibility Mapping ◽  
Susceptibility Map ◽  
Landslide Occurrence

High-resolution LiDAR-derived datasets from a 1.5-m digital elevation model and a detailed landslide inventory (N ≥ 1,000) for Magoffin County, Kentucky, USA, were used to develop a combined machine-learning and statistical approach to improve geomorphic-based landslide-susceptibility mapping.An initial dataset of 36 variables was compiled to investigate the connection between slope morphology and landslide occurrence. Bagged trees, a machine-learning random-forest classifier, was used to evaluate the geomorphic variables, and 12 were identified as important: standard deviation of plan curvature, standard deviation of elevation, sum of plan curvature, minimum slope, mean plan curvature, range of elevation, sum of roughness, mean curvature, sum of curvature, mean roughness, minimum curvature, and standard deviation of curvature. These variables were further evaluated using logistic regression to determine the probability of landslide occurrence and then used to create a landslide-susceptibility map.The performance of the logistic-regression model was evaluated by the receiver operating characteristic curve, area under the curve, which was 0.83. Standard deviations from the probability mean were used to set landslide-susceptibility classifications: low (0–0.10), low–moderate (0.11–0.27), moderate (0.28–0.44), moderate–high (0.45–0.7), and high (0.7–1.0). Logistic-regression results were validated by using a separate landslide inventory for the neighboring Prestonsburg 7.5-minute quadrangle, and running the same regression function. Results indicate that 74.9 percent of the landslide deposits were identified as having moderate, moderate–high, or high landslide susceptibility. Combining inventory mapping with statistical modelling identified important geomorphic variables and produced a useful approach to landslide-susceptibility mapping.Thematic collection: This article is part of the Digitization and Digitalization in engineering geology and hydrogeology collection available at: https://www.lyellcollection.org/cc/digitization-and-digitalization-in-engineering-geology-and-hydrogeology

scholarly journals Remote Sensing and GIS Approach for Landslide Susceptibility Mapping: A Case Study in Hofu City, Yamaguchi, Japan

2017 ◽  
Vol 1 (1) ◽  
Author(s):  
Benita Nathania ◽  
Fusanori Muira
Keyword(s):  
Remote Sensing ◽  
Logistic Regression ◽  
Landslide Susceptibility ◽  
Slope Angle ◽  
Remote Sensing Data ◽  
Bare Soil ◽  
Landslide Susceptibility Mapping ◽  
Susceptibility Map ◽  
Landslide Occurrence ◽  
Landslide Event

Landslide is one of the natural hazards that often initiates by the interaction between environmental factors and triggering factor. The identi?cation of areas where landslides are likely to occur is important for the reduction of potential damage. This study utilizes remote sensing data and Geographic Information System (GIS) to identify areas where landslides are likely to occur and generates landslide susceptibility map based on logistic regression model. The study area is located in Hofu city, Yamaguchi prefecture, Japan. The data that were used in this study are satellite imagery from ALOS AVNIR-2, elevation and geology data from GSI, Rainfall data from AMEDAS, and landslide inventory map provided from Ministry of Land, Infrastructure, Transportation and Tourism. The result from this study revealed that elevation from > 50 to < 350 m, slope angle from> 5° to < 50°, slope direction of north and northeast, land cover of agriculture, urban, bare soil, and forest, and lithology of graniodorite, fan deposits, and middle terrace are favorable for landslide occurrence. The landslide susceptiility map showed that 98% of the result calculations of logistic regression are similar to the historical data of landslide event which is among 911 landslide points, 899 points were existed in high and very high susceptibility areas.

scholarly journals Landslides susceptibility modelling using Multivariate Logistic Regression Model in the Sahla Watershed in Northern Morocco

2021 ◽  
Vol 33 ◽  
Author(s):  
Mohammed El-Fengour ◽  
Hanifa El Motaki ◽  
Aissa El Bouzidi
Keyword(s):  
Logistic Regression ◽  
Landslide Susceptibility ◽  
Slope Angle ◽  
Google Earth ◽  
Slope Aspect ◽  
Multivariate Logistic Regression Model ◽  
Susceptibility Map ◽  
Potential Hazard ◽  
Topographic Wetness Index ◽  
Landslide Occurrence

This study aimed to assess landslide susceptibility in the Sahla watershed in northern Morocco. Landslides hazard is the most frequent phenomenon in this part of the state due to its mountainous precarious environment. The abundance of rainfall makes this area suffer mass movements led to a notable adverse impact on the nearby settlements and infrastructures. There were 93 identified landslide scars. Landslide inventories were collected from Google Earth image interpretations. They were prepared out of landslide events in the past, and future landslide occurrence was predicted by correlating landslide predisposing factors. In this paper, landslide inventories are divided into two groups, one for landslide training and the other for validation. The Landslide Susceptibility Map (LSM) is prepared by Logistic Regression (LR) Statistical Method. Lithology, stream density, land use, slope curvature, elevation, topographic wetness index, slope aspect, and slope angle were used as conditioning factors. The Area Under the Curve (AUC) of the Receiver Operating Characteristic (ROC) was employed to examine the performance of the model. In the analysis, the LR model results in 96% accuracy in the AUC. The LSM consists of the predicted landslide area. Hence it can be used to reduce the potential hazard linked with the landslides in the Sahla watershed area in Rif Mountains in northern Morocco.

scholarly journals Landslide susceptibility mapping on a global scale using the method of logistic regression

2017 ◽  
Vol 17 (8) ◽  
pp. 1411-1424 ◽  
Author(s):  
Le Lin ◽  
Qigen Lin ◽  
Ying Wang
Keyword(s):  
Logistic Regression ◽  
Soil Moisture ◽  
Landslide Susceptibility ◽  
Confusion Matrix ◽  
Area Under The Curve ◽  
Global Scale ◽  
Landslide Susceptibility Mapping ◽  
Landslide Occurrence ◽  
Explanatory Factors ◽  
Five Factors

Abstract. This paper proposes a statistical model for mapping global landslide susceptibility based on logistic regression. After investigating explanatory factors for landslides in the existing literature, five factors were selected for model landslide susceptibility: relative relief, extreme precipitation, lithology, ground motion and soil moisture. When building the model, 70 % of landslide and nonlandslide points were randomly selected for logistic regression, and the others were used for model validation. To evaluate the accuracy of predictive models, this paper adopts several criteria including a receiver operating characteristic (ROC) curve method. Logistic regression experiments found all five factors to be significant in explaining landslide occurrence on a global scale. During the modeling process, percentage correct in confusion matrix of landslide classification was approximately 80 % and the area under the curve (AUC) was nearly 0.87. During the validation process, the above statistics were about 81 % and 0.88, respectively. Such a result indicates that the model has strong robustness and stable performance. This model found that at a global scale, soil moisture can be dominant in the occurrence of landslides and topographic factor may be secondary.

Analysis of cognitive characteristics and influencing factors of mass sports rehabilitation in Taiyuan

2019 ◽  
Author(s):  
Yaye He ◽  
Jiangong Wang ◽  
Liangyuan Zhao
Keyword(s):  
Logistic Regression ◽  
Regression Analysis ◽  
Health Status ◽  
Influencing Factors ◽  
Logistic Regression Analysis ◽  
Education Level ◽  
Factors Affecting ◽  
Exercise Rehabilitation ◽  
And Gender ◽  
Socio Economic Factors

Abstract Background: To assess the awareness regarding sports rehabilitation among residents of Taiyuan. Method: From September 27, 2018 to March 29, 2019, 1200 residents who met the inclusion/ criteria were selected using convenient sampling method. The population was surveyed by self-designed questionnaires, and single factor and two-category logistic regression analysis (stepwise forward method) was used to identify the factors influencing awareness of mass sports rehabilitation in Taiyuan. Results: A total of 1200 questionnaires were issued, of which 1167 were collected and 1101 were valid. The corresponding recovery and effective recovery rates were 97.25% and 94.34% respectively. The overall rate of awareness of exercise rehabilitation was 80.7%, and education level, occupation, income and health status were significant influencing factors (R<0.05). The results of two-class logistic regression analysis showed that age, occupation, education level, income level and health status were the influencing factors affecting the public's perception of the sports rehabilitation concept (R<0.05), whereas gender, occupation, education level and health status influenced understanding of the establishment of the rehabilitation department in Taiyuan (R<0.05), and gender, age, education level and health status affected understanding of the types of patients receiving rehabilitation (R<0.05). Conclusion: There is a high general awareness regarding sports rehabilitation, and is influenced by various socio-economic factors.

scholarly journals Ectopic eruption of the maxillary second molar: Predictive factors

2017 ◽  
Vol 87 (4) ◽  
pp. 583-589 ◽  
Author(s):  
Soonshin Hwang ◽  
Yoon Jeong Choi ◽  
Ji Yeon Lee ◽  
Chooryung Chung ◽  
Kyung-Ho Kim
Keyword(s):  
Logistic Regression ◽  
Regression Analysis ◽  
Logistic Regression Analysis ◽  
Predictive Factors ◽  
Multivariate Logistic Regression Analysis ◽  
Key Factors ◽  
Multivariate Logistic Regression ◽  
Factors Associated ◽  
Ectopic Eruption ◽  
Maxillary Tuberosity

ABSTRACT Objective: The purpose of this study was to investigate the diagnostic aspects, contributing conditions, and predictive key factors associated with ectopic eruption of maxillary second molars. Material and Methods: This retrospective study evaluated the study models, lateral cephalographs, and panoramic radiographs of 40 adult subjects (20 men, 20 women) with bilateral ectopic eruption and 40 subjects (20 men, 20 women) with normal eruption of the maxillary second molars. Studied variables were analyzed statistically by independent t-tests, univariate and multivariate logistic regression analysis, followed by receiver-operating characteristic analysis. Results: Tooth widths of bilateral lateral incisors, canines, and premolars were wider in the ectopic group, which resulted in greater arch lengths. The ANB angle and maxillary tuberosity distance (PTV-M1, PTV-M2) were smaller in the ectopic group. The long axes of the maxillary molars showed significant distal inclination in the ectopic group. The multivariate logistic regression analysis showed that three key factors—arch length, ANB angle, and PTV-M1 distance—were significantly associated with ectopic eruption of the second molars. The area under the curve (AUC) was the largest for the combination of the three key factors with an AUC greater than 0.75. PTV-M1 alone was the single factor that showed the strongest association with ectopic eruption (AUC = 0.7363). Conclusions: An increase in arch length, decrease in ANB angle, and decrease in maxillary tuberosity distance to the distal aspect of the maxillary first molar (PTV-M1) were the most predictive factors associated with ectopic eruption of maxillary second molars.

scholarly journals Willingness to Pay for Improved Water Quality and Influencing factors: An Insight from Chia Lagoon, Malawi

2019 ◽  
Author(s):  
Rodgers Makwinja ◽  
Ishmael Kosamu ◽  
Chikumbusko Kaonga
Keyword(s):  
Water Quality ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Influencing Factors ◽  
Logistic Regression Analysis ◽  
Multivariate Logistic Regression Analysis ◽  
Local Communities ◽  
Multivariate Logistic Regression ◽  
Wide Range ◽  
Improve Water Quality

(1) Background: Water resources at Chia lagoon experience possible threat to its sustainability. Communities are seeking alternatives to improve water quality at the lagoon. The study evaluated the extent at which local communities are WTP to improve water quality at Chia lagoon and the influencing factors. (2) Methods: A study was conducted at Chia lagoon, Western Part of Lake Malawi from November, 2015 to March, 2016. Wide range of data collection approaches such as household surveys, exploratory surveys, focus group discussions, key informant interviews and field observation were employed. A sample of 240 households were selected randomly. Qualitative data was analysed using content analysis. Multivariate logistic regression analysis was used to determine factors influence WTP. (3) Results: Out of 240 respondents, 57.4% expressed WTP. Multivariate logistic regression analysis demonstrated significant (P&lt;0.01 or P&lt;0.05) relationship between demographic (Gender, age, literacy level), social-economic (Land ownership, main agriculture water source and income) and institution (civic education and social network, extension, water user rights) factors and WTP. (4) Conclusion: The findings from this study provide significant clues for further research and baseline information for local government and local communities in development of more effective and holistic approaches to improve water quality.

Sign in / Sign up

Export Citation Format

Share Document