Evaluating the application of K-mean clustering in Earthquake vulnerability mapping of Istanbul, Turkey

Tehrany, Mahyat Shafapour; Yariyan, Peyman; Özener, Haluk; Pradhan, Biswajeet; Shabani, Farzin

doi:10.1016/j.ijdrr.2022.103154

Cited by 21 publications

(4 citation statements)

References 124 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…ML can extract and classify land coverage and land use from satellite or aerial imagery [9], and pinpoint regions susceptible to natural disasters [10,11] and flooding [12]. The combination of GIS and machine learning is used in several studies to forecast occurrences of rare events, including areas with landmines [13] with an accuracy of 89%, earthquake vulnerability assessments [14] with an accuracy of 96.2%, and wildfire [15] with an accuracy of 88%.…”

Section: Related Workmentioning

confidence: 99%

Bridging Human Expertise with Machine Learning and GIS for Mine Type Prediction and Classification

Saliba,

Claramunt,

Zaki

et al. 2024

Preprint

View full text Add to dashboard Cite

This paper introduces an intelligent model that combines military expertise with the latest ad-vancements in machine learning (ML) and Geographic Information Systems (GIS) to support humanitarian demining decision-making processes. The model is based on direct input and val-idation from field decision-makers for their practical applicability and effectiveness. With a survey polling the inputs of demining experts, 95% of the responses came with an affirmation of the potential of the model to reduce threats and increase operational efficiency. It includes mili-tary-specific factors that factor in the proximity to strategic locations as well as environmental variables like vegetation cover and terrain resolution. With Gradient Boosting algorithms such as XGBoost and LightGBM, the accuracy rate is almost 97%. Such precision levels further enhance threat assessment, better allocation of resources, and around a 30% reduction in the cost and time of conducting demining operations, signifying a strong synergy of human expertise with algo-rithmic precision for maximal safety and effectiveness in demining

show abstract

Section: Related Workmentioning

confidence: 99%

Bridging Human Expertise with Machine Learning and GIS for Mine Type Prediction and Classification

Saliba,

Claramunt,

Zaki

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The complex nature and enduring impacts that natural catastrophe can have on communities and cities in specific can be mostly ascribed to the variable nature of danger dispersion particularly seismic escalated the number of populations at hazard, and environmental vulnerability (Wald et al 2011). Earthquakes posture the most hazard threat to human life due to their damaging and wide run of impacts (Shafapourtehrany et al 2022). Based on the report of the World Health Organization (WHO) from 1998 to 2017, more than 750,000 individuals passed on due to earthquakes and more than 125 million individuals were influenced (Wilkinson, 2000).…”

Section: Introductionmentioning

confidence: 99%

An Innovative Fusion of New Smile Random Forest and Fuzzy Analysis for Comprehensive Seismic hazard Assessment: A Case Study in Mersin, Türkiye

Yakar,

Kamran,

Alptekin

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

This study addresses the critical issue of earthquake vulnerability in Mersin, Türkiye, given its susceptibility to seismic threats due to factors such as high population density, substandard constructions, narrow roads, and urban congestion. The research employs a comprehensive approach, utilizing a multi-criteria evaluation model and a novel hybrid random forest model to estimate the city's vulnerability proportionally. Spatial data encompassing physical, population, building quality, accessibility, relief, and hazard facilities were incorporated into the assessment. Weights for these components were determined through the Analytic Network Process (ANP) model, and a hybrid approach using Linear, Small, and Large functions calculated distances between options with fuzzy-fication. Resampling 10m x 10m maps addressed variations in spatial resolutions, while an 80% training set and 20% test set mitigated overfitting concerns. Expert opinions were pivotal in establishing criteria and sub-criteria for determining safe areas for temporary accommodation, rescue centers, and a seismic vulnerability map. The Smile Random Forest hybrid model was instrumental in generating these outcomes. Notably, the vulnerability map indicated that 24% of Mersin's areas fall within the high and very high vulnerability range. Key contributors to vulnerability included Geology factors (26.4), Land use (16.1), Epicenters (13.1), and slope and DEM (6.4). These findings underscore the imperative for strategic planning and interventions to minimize earthquake-induced damage in Mersin.

show abstract

“…[ 3 , 4 ] The documentation of epidemiological information and management experience regarding these earthquake injuries are critical for creating plans for future similar disasters. [ 5 , 6 ] In this two-part study, as a university clinic of orthopedics located on the edge of the disaster zone, we share our experience of the first 10 days after the earthquake. The subject of the first part is the characteristics of the earthquake victims and their treatment requirements.…”

Section: Introductionmentioning

confidence: 99%

First 10 days after the 6th of February 2023 earthquake disaster: experience of an orthopedic clinic on the border of the disaster zone

Asfuroğlu

2023

Ulus Travma Acil Cerrahi Derg

View full text Add to dashboard Cite

BACKGROUND: The earthquake disaster that occurred on February 06, 2023, caused serious destruction and loss of life in the south of Türkiye. The purpose of this article consisting of two interconnected parts is to report the experience of our orthopedics clinic, which is located just on the border of the disaster area. The subject of the first part of the study is the characteristics of orthopedic traumas in earthquake victims and the treatment methods applied. The subject of the second part is the disaster work plan of the clinic and its consequences in practice. METHODS: For the first step, descriptive information, diagnoses, and treatment methods of 204 earthquake victims who were treated by our clinic in the first 10 days after the disaster were compiled from the archives. In terms of the second phase of the study, an in-clinic work plan was created on the morning of the 1st day of the disaster. The teams and working hours in the emergency department, inpatient service, and operating room were determined. Hospital management and other clinics were contacted and hospital facilities were organized for orthopedic trauma victims. RESULTS: The mean age of the patients was 42.3 years. Among the age groups, the smallest group was children under 10 years old (6.4% of all patients). 132 of the patients had at least one fracture in 135 extremities. Most of the injuries involved the lower extremity. 66 patients had crush injury with or without fracture. 181 orthopedic surgical procedures were performed in 144 patients. The most common operations were internal fracture fixation and debridement. The most used implant was the plate-screw combination. Thanks to the in-clinic work plan and the in-hospital assistance and allocation of facilities, we did not experience serious problems in the hospitalization, surgery, and post-operative follow-ups of the patients. Although we received numerous offers of assistance from external institutions, this was not possible due to bureaucratic obstacles. Among our most important problems were the shortage of sterilized powered surgical drills and the lack of a dynamic patient information database. CONCLUSION: Orthopedic clinics should prepare their in-clinic work plans for earthquake disasters and develop their facilities. In order not to encounter bureaucratic obstacles in emergency assistance, orthopedic clinics in different risk regions should be formally matched beforehand. A patient database table that clinical staff can access and revise using their smartphones facilitates the follow-up of large numbers of simultaneously hospitalized patients.

show abstract

Evaluating the application of K-mean clustering in Earthquake vulnerability mapping of Istanbul, Turkey

Cited by 21 publications

References 124 publications

Bridging Human Expertise with Machine Learning and GIS for Mine Type Prediction and Classification

Bridging Human Expertise with Machine Learning and GIS for Mine Type Prediction and Classification

An Innovative Fusion of New Smile Random Forest and Fuzzy Analysis for Comprehensive Seismic hazard Assessment: A Case Study in Mersin, Türkiye

First 10 days after the 6th of February 2023 earthquake disaster: experience of an orthopedic clinic on the border of the disaster zone

Contact Info

Product

Resources

About