Article
Environmental Sciences
Muhittin Ozan Karaman, Saye Nihan Cabuk, Emrah Pekkan
Summary: Geographical information systems (GIS) were used to create landslide susceptibility maps in the Karaburun Peninsula in Izmir. This study provides important inputs for sustainable planning in the region.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2022)
Article
Geosciences, Multidisciplinary
Gebremedhin Berhane, Abadi Gebrehiwot, Asmelash Abay
Summary: This research developed and evaluated a landslide susceptibility map in Ethiopia using two different approaches: frequency ratio and analytical hierarchy process. The study identified and mapped 175 past landslides and analyzed eight causative factors. The resulting landslide susceptibility maps provided valuable insights for landslide hazard mitigation and adaptation.
GEOMATICS NATURAL HAZARDS & RISK
(2023)
Article
Forestry
Nastaran Zare, Seyed Ata Ollah Hosseini, Mohammad Kazem Hafizi, Akbar Najafi, Baris Majnounian, Marten Geertsema
Summary: The study utilized an integration of ANFIS and frequency ratio models to predict landslide susceptibility along forest road networks in the Hyrcanian Forest, northern Iran. By mapping landslide locations and selecting conditioning factors, the researchers developed models and evaluated their accuracy for natural hazard management applications.
Article
Environmental Studies
Minu Treesa Abraham, Neelima Satyam, Revuri Lokesh, Biswajeet Pradhan, Abdullah Alamri
Summary: Data driven methods such as Machine Learning algorithms are widely used for Landslide Susceptibility Mapping (LSM). The choice of algorithm and sampling strategy play crucial roles in obtaining accurate results. Random Forest, K Nearest Neighbors, and Support Vector Machine algorithms perform better than Naive Bayes and Logistic Regression, with the former three being more sensitive to sampling strategy and data points. Increasing data points leads to better performance for KNN, RF, and SVM algorithms, while NB and LR algorithms are less affected by sampling strategy and data splitting ratio.
Article
Environmental Sciences
S. E. Saranaathan, S. Mani, V. Ramesh, S. Prasanna Venkatesh
Summary: The study utilized a frequency ratio model to create a landslide susceptibility zonation map, dividing the study area into five susceptibility levels. The LSZ map was validated using data from old landslide records, identifying 18 rock vulnerable cut slopes.
JOURNAL OF THE INDIAN SOCIETY OF REMOTE SENSING
(2021)
Article
Geosciences, Multidisciplinary
Faming Huang, Jun Yan, Xuanmei Fan, Chi Yao, Jinsong Huang, Wei Chen, Haoyuan Hong
Summary: In landslide susceptibility mapping (LSM), the expression of landslide boundaries and spatial shapes as points or circles instead of accurate polygons can lead to differences in the predicted landslide susceptibility indexes (LSIs) and introduce uncertainties into the LSM. This study compared the uncertainties of LSM modeling using different representations of landslide boundaries and spatial shapes, and found that using polygonal surfaces to represent the landslide boundaries can significantly improve the accuracy of LSM compared to using points and circles. The results also showed that polygon-based models have higher LSM accuracy compared to point- and circle-based models, and the overall accuracy of the random forest (RF) model is superior to that of the support vector machine (SVM) model.
GEOSCIENCE FRONTIERS
(2022)
Article
Geosciences, Multidisciplinary
Zhiyong Fu, Changdong Li, Wenmin Yao
Summary: This study proposes a novel method that improves the performance of landslide susceptibility (LS) models using the TrAdaBoost transfer learning algorithm. The method transfers useful knowledge from one landslide inventory to another, reducing the effort required to collect landslide data. The results demonstrate that when using the TrAdaBoost model with the landslide inventory from the source area, the performance of LS models is significantly improved.
Article
Geochemistry & Geophysics
Halil Akinci, Ayse Yavuz Ozalp
Summary: This study evaluated landslide susceptibility of the Central district of Artvin in Turkey using the frequency ratio (FR) and modified information value (MIV) models. Results showed that the MIV model performed slightly better than the FR model in terms of prediction and success rates. Additionally, it was found that most village built-up areas and majority of the planned areas within the municipal boundaries in Artvin were located in landslide susceptible zones.
Article
Geosciences, Multidisciplinary
K. Khusulio, Rohan Kumar
Summary: The feasibility of three methods, analytical hierarchy process, frequency ratio and binary logistic regression, were assessed for landslide susceptibility analysis. Twelve causal factors and a landslide inventory were used to calculate and generate a landslide susceptibility map. The validation of the models showed moderate to high accuracy. These susceptibility maps can be useful for city or village planners for planning, development, mitigation, and disaster prevention.
JOURNAL OF EARTH SYSTEM SCIENCE
(2023)
Article
Computer Science, Information Systems
Sandeep Panchal, Amit K. Shrivastava
Summary: This study compared three models, frequency ratio, Shannon's entropy, and AHP, for landslide susceptibility mapping in Shimla district, India. The frequency ratio model showed the highest accuracy, followed by Shannon's entropy, and AHP had the lowest accuracy. The results can be used by engineers and planners for better landslide management in the study area.
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2021)
Article
Geosciences, Multidisciplinary
Wenwu Chen, Shuai Zhang
Summary: This study employed the Hoeffding Tree (HT) algorithm for landslide susceptibility prediction in Muchuan County, China, and compared the results with the Logistic Model Tree (LMT) and Bayes Network (BN) models. The models showed satisfactory performance, with the LMT model exhibiting the highest AUC in the training dataset, and the HT model showing the highest AUC in the validation dataset. The study revealed that areas with higher human activities tend to have higher landslide susceptibility, providing important insights for landslide prevention and urban planning in Muchuan, China.
Article
Environmental Studies
Gbenga Olamide Adesola, Kgabo Humphrey Thamaga, Oswald Gwavava, Benedict Kinshasa Pharoe
Summary: In order to sustainably develop and manage groundwater resources, this study used geospatial-based analytical hierarchy process (AHP) and frequency ratio (FR) techniques to delineate groundwater potential zones (GWPZs) and created corresponding maps by combining influencing factors. Through model validation, the findings showed that the FR model was more efficient than the AHP model. The research demonstrated that these models are reliable and can be adopted to characterize GWPZs in arid or semi-arid environments.
Article
Environmental Sciences
Sonia Akter, Syed Aaqib Javed
Summary: The FR and SE models were used to generate a landslide susceptibility map for CHA, Bangladesh, and their accuracy was compared through validation. The study found that the FR model was more accurate than the SE model.
GEOCARTO INTERNATIONAL
(2022)
Article
Multidisciplinary Sciences
Mojgan Bordbar, Hossein Aghamohammadi, Hamid Reza Pourghasemi, Zahra Azizi
Summary: This study developed a multi-hazard map for identifying at-risk areas in Kermanshah province, Iran by integrating SWARA-ANFIS-PSO and SWARA-ANFIS-GWO models. The study incorporated various factors to generate susceptibility maps for earthquakes, floods, and landslides. The results showed that the ensemble model, SWARA-ANFIS-PSO, performed the best in generating flood susceptibility maps. The multi-hazard map obtained can serve as a practical guide for sustainable development.
SCIENTIFIC REPORTS
(2022)
Article
Engineering, Electrical & Electronic
Pingheng Li
Summary: This study explores the pollution risk and resource utilization potential of vegetable waste on land resources through the analysis of remote sensing data and literature collection. By establishing a land use reference database and using geographical information system, key areas for controlling vegetable waste pollution are determined, and the possibility of waste utilization is compared. In addition, the study conducts a preliminary analysis of the causes and cumulative characteristics of polluted soil.
JOURNAL OF SENSORS
(2022)
Article
Environmental Sciences
Sung-Min Kim, Jangwon Suh, Sungchan Oh, Jin Son, Chang-Uk Hyun, Hyeong-Dong Park, Seung-Han Shin, Yosoon Choi
ENVIRONMENTAL EARTH SCIENCES
(2016)