Maritime Risk Assessment: A Cutting-Edge Hybrid Model Integrating Automated Machine Learning and Deep Learning with Hydrodynamic and Monte Carlo Simulations
In this study, a Hybrid Maritime Risk Assessment Model (HMRA) integrating automated machine learning (AML) and deep learning (DL) with hydrodynamic and Monte Carlo simulations (MCS) was developed to assess maritime accident probabilities and risks. The machine learning models of Light Gradient Boost...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/13/5/939 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850126004676198400 |
|---|---|
| author | Egemen Ander Balas Can Elmar Balas |
| author_facet | Egemen Ander Balas Can Elmar Balas |
| author_sort | Egemen Ander Balas |
| collection | DOAJ |
| description | In this study, a Hybrid Maritime Risk Assessment Model (HMRA) integrating automated machine learning (AML) and deep learning (DL) with hydrodynamic and Monte Carlo simulations (MCS) was developed to assess maritime accident probabilities and risks. The machine learning models of Light Gradient Boosting (LightGBM), XGBoost, Random Forest, and Multilayer Perceptron (MLP) were employed. Cross-validation of model architectures, calibrated baseline configurations, and hyperparameter optimization enabled predictive precision, producing generalizability. This hybrid model establishes a robust maritime accident probability prediction framework through a multi-stage methodology that ensembles learning architecture. The model was applied to İzmit Bay (in Türkiye), a highly jammed maritime area with dense traffic patterns, providing a complete methodology to evaluate and rank risk factors. This research improves maritime safety studies by developing an integrated, simulation-based decision-making model that supports risk assessment actions for policymakers and stakeholders in marine spatial planning (MSP). The potential spill of 20 barrels (bbl) from an accident between two tankers was simulated using the developed model, which interconnects HYDROTAM-3D and the MCS. The average accident probability in İzmit Bay was estimated to be 5.5 × 10<sup>−4</sup> in the AML based MCS, with a probability range between 2.15 × 10<sup>−4</sup> and 7.93 × 10<sup>−4</sup>. The order of the predictions’ magnitude was consistent with the Undersecretariat of the Maritime Affairs Search and Rescue Department accident data for İzmit Bay. The spill reaches the narrow strait of the inner basin in the first six hours. This study determines areas within the bay at high risk of accidents and advocates for establishing emergency response centers in these critical areas. |
| format | Article |
| id | doaj-art-c364afc36bce45b1b90fe738bd7bbf05 |
| institution | OA Journals |
| issn | 2077-1312 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj-art-c364afc36bce45b1b90fe738bd7bbf052025-08-20T02:34:01ZengMDPI AGJournal of Marine Science and Engineering2077-13122025-05-0113593910.3390/jmse13050939Maritime Risk Assessment: A Cutting-Edge Hybrid Model Integrating Automated Machine Learning and Deep Learning with Hydrodynamic and Monte Carlo SimulationsEgemen Ander Balas0Can Elmar Balas1Department of Civil Engineering, Faculty of Engineering, Başkent University, Ankara 06790, TürkiyeSea and Aquatic Sciences Application and Research Center, Gazi University, Ankara 06570, TürkiyeIn this study, a Hybrid Maritime Risk Assessment Model (HMRA) integrating automated machine learning (AML) and deep learning (DL) with hydrodynamic and Monte Carlo simulations (MCS) was developed to assess maritime accident probabilities and risks. The machine learning models of Light Gradient Boosting (LightGBM), XGBoost, Random Forest, and Multilayer Perceptron (MLP) were employed. Cross-validation of model architectures, calibrated baseline configurations, and hyperparameter optimization enabled predictive precision, producing generalizability. This hybrid model establishes a robust maritime accident probability prediction framework through a multi-stage methodology that ensembles learning architecture. The model was applied to İzmit Bay (in Türkiye), a highly jammed maritime area with dense traffic patterns, providing a complete methodology to evaluate and rank risk factors. This research improves maritime safety studies by developing an integrated, simulation-based decision-making model that supports risk assessment actions for policymakers and stakeholders in marine spatial planning (MSP). The potential spill of 20 barrels (bbl) from an accident between two tankers was simulated using the developed model, which interconnects HYDROTAM-3D and the MCS. The average accident probability in İzmit Bay was estimated to be 5.5 × 10<sup>−4</sup> in the AML based MCS, with a probability range between 2.15 × 10<sup>−4</sup> and 7.93 × 10<sup>−4</sup>. The order of the predictions’ magnitude was consistent with the Undersecretariat of the Maritime Affairs Search and Rescue Department accident data for İzmit Bay. The spill reaches the narrow strait of the inner basin in the first six hours. This study determines areas within the bay at high risk of accidents and advocates for establishing emergency response centers in these critical areas.https://www.mdpi.com/2077-1312/13/5/939maritime risk assessmentautomated machine learningdeep learningİzmit Bayhydrodynamic coupled Monte Carlo simulationmaritime accident |
| spellingShingle | Egemen Ander Balas Can Elmar Balas Maritime Risk Assessment: A Cutting-Edge Hybrid Model Integrating Automated Machine Learning and Deep Learning with Hydrodynamic and Monte Carlo Simulations Journal of Marine Science and Engineering maritime risk assessment automated machine learning deep learning İzmit Bay hydrodynamic coupled Monte Carlo simulation maritime accident |
| title | Maritime Risk Assessment: A Cutting-Edge Hybrid Model Integrating Automated Machine Learning and Deep Learning with Hydrodynamic and Monte Carlo Simulations |
| title_full | Maritime Risk Assessment: A Cutting-Edge Hybrid Model Integrating Automated Machine Learning and Deep Learning with Hydrodynamic and Monte Carlo Simulations |
| title_fullStr | Maritime Risk Assessment: A Cutting-Edge Hybrid Model Integrating Automated Machine Learning and Deep Learning with Hydrodynamic and Monte Carlo Simulations |
| title_full_unstemmed | Maritime Risk Assessment: A Cutting-Edge Hybrid Model Integrating Automated Machine Learning and Deep Learning with Hydrodynamic and Monte Carlo Simulations |
| title_short | Maritime Risk Assessment: A Cutting-Edge Hybrid Model Integrating Automated Machine Learning and Deep Learning with Hydrodynamic and Monte Carlo Simulations |
| title_sort | maritime risk assessment a cutting edge hybrid model integrating automated machine learning and deep learning with hydrodynamic and monte carlo simulations |
| topic | maritime risk assessment automated machine learning deep learning İzmit Bay hydrodynamic coupled Monte Carlo simulation maritime accident |
| url | https://www.mdpi.com/2077-1312/13/5/939 |
| work_keys_str_mv | AT egemenanderbalas maritimeriskassessmentacuttingedgehybridmodelintegratingautomatedmachinelearninganddeeplearningwithhydrodynamicandmontecarlosimulations AT canelmarbalas maritimeriskassessmentacuttingedgehybridmodelintegratingautomatedmachinelearninganddeeplearningwithhydrodynamicandmontecarlosimulations |