☆ 4.7 Article

Spatial risk assessment of maritime transportation in offshore waters of China using machine learning and geospatial big data

OCEAN & COASTAL MANAGEMENT (2024)

Related references

Note: Only part of the references are listed.

Article Transportation

A survey of the opportunities and challenges of supervised machine learning in maritime risk analysis

Andrew Rawson et al.

Summary: Identifying and assessing the likelihood and consequences of maritime accidents has been a key focus of research within the maritime industry. This comprehensive review of academic literature in the maritime domain compares the purpose, methods, datasets, and features of studies on accident prediction, severity, ship detentions, and ship collision risk. The review also identifies challenges and highlights novel applications and key areas for further research in order to strengthen the methodological approach.

TRANSPORT REVIEWS (2023)

Add to Collection

Article Engineering, Marine

A deep spatiotemporal approach in maritime accident prediction: A case study of the territorial sea of South Korea

Zahra Nourmohammadi et al.

Summary: This study investigates the application of deep learning in short- and long-term predictions of accident risks associated with small vessels. Multiple influencing factors are considered, and machine learning and deep learning algorithms are implemented and compared. The results show that the proposed deep spatiotemporal ocean accident prediction model performs well in predicting accidents with a high accuracy.

OCEAN ENGINEERING (2023)

Add to Collection

Article Environmental Studies

Empirical analysis of the effectiveness of the legislative framework in the maritime industry

Sabine Knapp et al.

Summary: We analyze the effectiveness of the legislative framework of the maritime industry developed by international organizations and regional regulators. Using 310 time series data spanning 44 years, we examine the impact of 116 legislative milestones on various endpoints such as safety, pollution, and crime. The results show improvements in fleet quality, with safety-related milestones having the most significant negative effects.

MARINE POLICY (2023)

Add to Collection

Article Computer Science, Artificial Intelligence

Transparent deep machine learning framework for predicting traffic crash severity

Karim Sattar et al.

Summary: This study models the injury severity of motor vehicle crashes using advanced machine learning approaches and provides an interpretation of the modeling framework through feature importance analysis. The research findings have important implications for improving highway safety and predicting possible damage from traffic accidents.

NEURAL COMPUTING & APPLICATIONS (2023)

Add to Collection

Article Ergonomics

Using computer vision and machine learning to identify bus safety risk factors

Becky P. Y. Loo et al.

Summary: Bus crashes in road safety research are significant due to the large number of bus passengers involved and the challenges they pose to the road network and public health care system. This study utilizes bus dashcam footage to identify high-risk factors and suggest planning interventions for improving bus safety in cities heavily reliant on buses as a major means of public transport. Key risk factors identified include pedestrian exposure factors, pedestrian jaywalking, bus stop crowding, sidewalk railing, and sharp turning locations. Road safety administrations should focus on improving bus safety on pedestrian-heavy streets, recognizing the importance of protection railing, and addressing bus stop crowding to prevent minor bus injuries.

ACCIDENT ANALYSIS AND PREVENTION (2023)

Add to Collection

Article Automation & Control Systems

Application of machine learning models in the behavioral study of forest fires in the Brazilian Federal District region

Jesus N. S. Rubi et al.

Summary: Ecosystems, settlements, and human lives are at risk from forest fires annually. This research focuses on predicting the spread and behavior of wildfires to help minimize damages. Machine Learning models, using a dataset compiled from various data sources, accurately predict the affected areas.

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE (2023)

Add to Collection

Article Engineering, Marine

Exploring spatial patterns and environmental risk factors for global maritime accidents: A 20-year analysis

Xiao Zhou et al.

Summary: This study investigates the evolutionary patterns of global maritime accidents and identifies key environmental risk factors through a novel framework combining spatial density analysis and machine learning. The results show fluctuations in the number of accidents over time and significant spatial variation in their distribution.

OCEAN ENGINEERING (2023)

Add to Collection

Article Engineering, Marine

A decision support model for ship navigation in Arctic waters based on dynamic risk assessment

Zhuang Li et al.

Summary: This study proposes a route planning method based on a risk map, which can objectively reflect the temporal and spatial risk distributions of different types of ships in the Arctic waters, providing a basis for ship navigation.

OCEAN ENGINEERING (2022)

Add to Collection

Article Engineering, Marine

GIS-based analysis on the spatial patterns of global maritime accidents

Huanxin Wang et al.

Summary: Based on the global maritime accident data from 2010 to 2019, the spatial patterns of maritime accidents in terms of accident frequency and severity were analyzed using density analysis and clustering analysis. The study identified low severity accident clustering in the North Sea, the Baltic Sea, and the Mediterranean Sea, while high severity accident clustering was found in the coastal waters surrounding China, Japan, South Korea, Vietnam and the Philippines, the Singapore-Malacca Strait, and the Bay of Biscay. The majority of accidents, including serious and very serious ones, occurred within 30 nm to the coastline.

OCEAN ENGINEERING (2022)

Add to Collection

Article Public, Environmental & Occupational Health

Spatial Modeling of Maritime Risk Using Machine Learning

Andrew Rawson et al.

Summary: This article introduces a novel method for spatial modeling of maritime risk using machine learning, which aggregates historical accident data and vessel traffic into a spatial grid and implements classification algorithms to predict annual accident occurrence for various vessel types. The method shows remarkable capability at characterizing maritime risk, with accuracies and area under curve scores exceeding 90% in most implementations in the United Kingdom. The ensemble tree-based algorithms of XGBoost and Random Forest consistently outperform other machine learning algorithms tested, providing decisionmakers with actionable intelligence for targeting risk mitigation measures.

RISK ANALYSIS (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

A neural network boosting regression model based on XGBoost

Jianwei Dong et al.

Summary: The paper discusses the characteristics of boosting models and neural networks, and proposes a Neural Network Boosting (NNBoost) regression model that uses shallow neural networks as weak classifiers. The model approximates the target loss function using the Taylor expansion and applies a gradient descent algorithm for optimization. It addresses issues in deep learning such as gradient vanishing and overfitting, and achieves improved regression accuracy.

APPLIED SOFT COMPUTING (2022)

Add to Collection

Article Engineering, Marine

A comprehensive framework for assessing navigation risk and deploying maritime emergency resources in the South China Sea

Xiao Zhou

Summary: This study proposes a framework for assessing navigation risk and deploying maritime search and rescue (SAR) resources. The framework combines multiple criteria decision making, geospatial techniques, and game theory. By calculating a composite risk index and Banzhaf values, the allocation of SAR resources in different bases can be determined. The results show that this approach is feasible and can improve navigation safety.

OCEAN ENGINEERING (2022)

Add to Collection

Article Forestry

Spatio-temporal analysis of forest fire events in the Margalla Hills, Islamabad, Pakistan using socio-economic and environmental variable data with machine learning methods

Aqil Tariq et al.

Summary: This study analyzes how human behavior affects the risk of forest fires in the Margalla Hills by considering both environmental and socioeconomic factors. Using Maxent and RF models to predict fire probabilities and spatial diffusion patterns, it was found that urban areas with higher accessibility and human activity are more prone to fires.

JOURNAL OF FORESTRY RESEARCH (2022)

Add to Collection

Article Green & Sustainable Science & Technology

Flood Hazard and Risk Mapping by Applying an Explainable Machine Learning Framework Using Satellite Imagery and GIS Data

Gerasimos Antzoulatos et al.

Summary: Flooding is a destructive natural phenomenon worldwide, and real-time solutions are needed to assess flood hazards and risks. By combining remote sensing and GIS data, flood hazards can be effectively evaluated, and flood hazard maps can be generated using machine learning techniques.

SUSTAINABILITY (2022)

Add to Collection

Article Engineering, Marine

Study on the prediction model of accidents and incidents of cruise ship operation based on machine learning

Zhaoqian Su et al.

Summary: This study used machine learning to build an ensemble learning model to predict accidents and incidents during cruise ship operations in China. By analyzing the characteristics of accidents and incidents, 10 machine learning algorithms were selected and evaluated using two performance indices. An improved ensemble learning model was proposed, which showed the best predictive performance compared to other models.

OCEAN ENGINEERING (2022)

Add to Collection

Article Oceanography

A systematic analysis for maritime accidents causation in Chinese coastal waters using machine learning approaches

Kezhong Liu et al.

Summary: The study identified the importance of different risk factors and critical scenarios in China's coastal waters, with small general cargo ships posing the highest risk. Bad weather conditions often lead to catastrophic accidents, while minor accidents tend to occur in areas with lower traffic density. The research findings can offer valuable guidance for risk prevention and improve the maritime safety management system in coastal waters.

OCEAN & COASTAL MANAGEMENT (2021)

Add to Collection

Review Engineering, Industrial

Applications of machine learning methods for engineering risk assessment - A review

Jeevith Hegde et al.

SAFETY SCIENCE (2020)

Add to Collection

Article Engineering, Marine

Featured risk evaluation of nautical navigational environment using a risk cloud model

Yan-Fei Tian et al.

JOURNAL OF MARINE ENGINEERING AND TECHNOLOGY (2020)

Add to Collection

Article Engineering, Marine

Dynamic risk assessment of natural environment based on Dynamic Bayesian Network for key nodes of the arctic Northwest Passage

Heng Qian et al.

OCEAN ENGINEERING (2020)

Add to Collection

Article Engineering, Ocean

A comprehensive path planning framework for patrolling marine environment

Xiao Zhou et al.

APPLIED OCEAN RESEARCH (2020)

Add to Collection

Article Geosciences, Multidisciplinary

A framework for assessing the capability of maritime search and rescue in the south China sea

Xiao Zhou et al.

INTERNATIONAL JOURNAL OF DISASTER RISK REDUCTION (2020)

Add to Collection

Article Engineering, Marine

Assessing and mapping maritime transportation risk based on spatial fuzzy multi-criteria decision making: A case study in the South China sea

Xiao Zhou et al.

OCEAN ENGINEERING (2020)

Add to Collection

Article Green & Sustainable Science & Technology

Identification of the most influential areas for air pollution control using XGBoost and Grid Importance Rank

Jun Ma et al.

JOURNAL OF CLEANER PRODUCTION (2020)

Add to Collection

Article Transportation

Maritime accident risk estimation for sea lanes based on a dynamic Bayesian network

Meizhi Jiang et al.

MARITIME POLICY & MANAGEMENT (2020)

Add to Collection

Article Meteorology & Atmospheric Sciences

Summarizing metocean operating conditions as a climatology of marine hazards

Heather Reid et al.

THEORETICAL AND APPLIED CLIMATOLOGY (2019)

Add to Collection

Article Engineering, Marine

Navigation risk assessment method based on flow conditions: A case study of the river reach between the Three Gorges Dam and the Gezhouba Dam

Shanghong Zhang et al.

OCEAN ENGINEERING (2019)

Add to Collection

Article Computer Science, Information Systems

Integrating Island Spatial Information and Integer Optimization for Locating Maritime Search and Rescue Bases: A Case Study in the South China Sea

Xiao Zhou et al.

ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION (2019)

Add to Collection

Article Environmental Sciences

Flash Flood Risk Analysis Based on Machine Learning Techniques in the Yunnan Province, China

Meihong Ma et al.

REMOTE SENSING (2019)

Add to Collection

Article Environmental Studies

Normalization of maritime accident data using AIS

Rolf Johan Bye et al.

MARINE POLICY (2019)

Add to Collection

Article Engineering, Marine

Marine transportation risk assessment using Bayesian Network: Application to Arctic waters

Al-Amin Baksh et al.

OCEAN ENGINEERING (2018)

Add to Collection

Article Engineering, Industrial

An operational risk analysis tool to analyze marine transportation in Arctic waters

Bushra Khan et al.

RELIABILITY ENGINEERING & SYSTEM SAFETY (2018)

Add to Collection

Article Engineering, Industrial

Development of a quantitative risk assessment model for ship collisions in fairways

Tian Chai et al.

SAFETY SCIENCE (2017)

Add to Collection

Article Engineering, Industrial

Safety assessment of shipping routes in the South China Sea based on the fuzzy analytic hierarchy process

Jiasheng Wang et al.

SAFETY SCIENCE (2014)

Add to Collection

Article Engineering, Industrial

Formal safety assessment based on relative risks model in ship navigation

Shenping Hu et al.

RELIABILITY ENGINEERING & SYSTEM SAFETY (2007)

Add to Collection

© Peeref 2019-2024. All rights reserved.