Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jeongon Eom has a total of 14 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Uncertainty-Aware Superpixel Segmentation and Bayesian Optimization for Sampling Strategy Development Using Activation Analysis of OPR-1000

    by Jeongon Eom, Sewon Kim, Seokjun Hong, Chang Je Park

    Radiological characterization of activated structural materials is a critical task in nuclear power plant decommissioning, where strong spatial heterogeneity and limited sampling accessibility introduce significant epistemic uncertainty in radionuclide inventory estimation and waste classification. This study proposes an uncertainty-aware representative sampling framework that integrates superpixel-based spatial segmentation, Gaussian process (GP) surrogate modeling, and Bayesian optimization to minimize uncertainty under constrained sampling conditions. High-resolution activation fields derived from three-dimensional Monte Carlo neutron transport and activation analyses for the OPR-1000 reactor were processed using superpixel segmentation to reduce dimensionality while preserving spatial heterogeneity. Sensitivity analysis indicated that discretizing the activation field into 25 layers provides an effective balance between uncertainty representation and computational efficiency. The segmented representation was used to construct GP surrogate models that explicitly quantify predictive uncertainty and guide sequential sampling through Bayesian optimization. The proposed framework was applied to representative activation cases for Ag-110m and C-14. Results show that uncertainty converges rapidly, with approximately five optimized sampling locations sufficient to achieve near-minimal posterior variance. The selected sampling points were consistently located in transition zones with strong activation gradients, indicating that the uncertainty-driven acquisition function effectively prioritizes regions with the highest information gain. The proposed approach reduces the number of required samples while maintaining representativeness under practical decommissioning constraints. The integration of superpixel segmentation and Bayesian optimization provides a transparent and defensible strategy for sampling design, supporting reliable radionuclide inventory estimation, reduced analytical costs, and improved decision-making for waste classification in OPR-1000 decommissioning.

  • Open Access

    Development of a Reinforcement Learning-Based Ship Voyage Planning Optimization Method Applying Machine Learning-Based Berth Dwell-Time Prediction as a Time Constraint

    by Youngseo Park, Suhwan Kim, Jeongon Eom, Sewon Kim

    Global container shipping faces increasing pressure to reduce fuel consumption and greenhouse gas (GHG) emissions while still meeting strict port schedules under highly uncertain terminal operations and met-ocean conditions. However, most existing voyage-planning approaches either ignore real port operation variability or treat fuel optimization and just-in-time (JIT) arrival as separate problems, limiting their applicability in actual operations. This study presents a data-driven just-in-time voyage optimization framework that integrates port-side uncertainty and marine environmental dynamics into the routing process. A dwell-time prediction model based on Gradient Boosting was developed using port throughput and meteorological–oceanographic variables, achieving a validation accuracy of R2 = 0.84 and providing a data-driven required time of arrival (RTA) estimate. A Transformer encoder model was constructed to forecast fuel consumption from multivariate navigation and environmental data, and the model achieved a segment-level predictive performance with an R2 value of approximately 0.99. These predictive modules were embedded into a Deep Q-Network (DQN) routing model capable of optimizing headings and speed profiles under spatially varying ocean conditions. Experiments were conducted on three container-carrier routes in which the historical AIS trajectories served as operational benchmark routes. Compared with these AIS-based baselines, the optimized routes reduced fuel consumption and CO2 emissions by approximately 26% to 69%, while driving the JIT arrival deviation close to zero. The proposed framework provides a unified approach that links port operations, fuel dynamics, and ocean-aware route planning, offering practical benefits for smart and autonomous ship navigation.


  • Open Access

    Ship Voyage Route Waypoint Optimization Method Using Reinforcement Learning Considering Topographical Factors and Fuel Consumption

    by Juhyang Lee, Youngseo Park, Jeongon Eom, Hungyu Hwang, Sewon Kim

    As the IMO and the EU strengthen carbon emission regulations, eco-friendly voyage planning is increasingly recognized by ship owners as one of the most important performance factors of the vessel fleet. The eco-friendly voyage planning aims to reduce carbon emissions and fuel consumption while satisfying voyage constraints. In this study, a novel route waypoint optimization method is proposed, which combines a fuel consumption forecasting model based on the Transformer and a Proximal Policy Optimization (PPO) algorithm for adaptive waypoint planning. The developed framework suggests a multi-objective methodology unlike the traditional approaches where a single objective is sought after, which characterizes fuel efficiency against navigational safety and operational simplicity. The methodology consists of three sequential phases. First, the transformer model is employed to predict ship fuel consumption using navigational and environmental data. Next, the predicted consumption values are utilized as a reward function in a PPO-based reinforcement learning framework to generate fuel-efficient routes. Finally, the number and placement of waypoints are further optimized with respect to terrain and bathymetric constraints, improving the practicality and safety of the navigational plan. The results show that the proposed method could decrease average fuel consumption by up to 11.33% across three real-world case studies: Busan–Rotterdam, Busan–Los Angeles, and Mokpo–Houston, compared to AIS-based routes. The transformer model outperformed Long Short-Term Memory (LSTM) and Random Forest baselines with the highest prediction accuracy, achieving an R2 score of 86.75%. This study is the first to incorporate transformer-based forecasting into reinforcement learning for maritime route planning and demonstrates how the method adaptively controls waypoint density in response to environmental and geographical conditions. These results support the practical application of the approach in smart ship navigation systems aligned with IMO’s decarbonization goals.


  • Open Access

    The Development of a Machine Learning-Based Carbon Emission Prediction Method for a Multi-Fuel-Propelled Smart Ship by Using Onboard Measurement Data

    by Juhyang Lee, Jeongon Eom, Jumi Park, Jisung Jo, Sewon Kim

    Zero-carbon shipping is the prime goal of the seaborne trade industry at this moment. The utilization of ammonia and liquid hydrogen propulsion in a carbon-free propulsion system is a promising option to achieve net-zero emission in the maritime supply chain. Meanwhile, optimal ship voyage planning is a candidate to reduce carbon emissions immediately without new buildings and retrofits of the alternative fuel-based propulsion system. Due to the voyage options, the precise prediction of fuel consumption and carbon emission via voyage operation profile optimization is a prerequisite for carbon emission reduction. This paper proposes a novel fuel consumption and carbon emission quantity prediction method which is based on the onboard measurement data of a smart ship. The prediction performance of the proposed method was investigated and compared to machine learning and LSTM-model-based fuel consumption and gas emission prediction methods. The results had an accuracy of 81.5% in diesel mode and 91.2% in gas mode. The SHAP (Shapley additive explanations) model, an XAI (Explainable Artificial Intelligence), and a CO2 consumption model were employed to identify the major factors used in the predictions. The accuracy of the fuel consumption calculated using flow meter data, as opposed to power load data, improved by approximately 21.0%. The operational and flow meter data collected by smart ships significantly contribute to predicting the fuel consumption and carbon emissions of vessels.


  • Open Access

    Coastal Air Quality Assessment through AIS-Based Vessel Emissions: A Daesan Port Case Study

    by Jeong-Hyun Yoon, Se-Won Kim, Jeong-On Eom, Jaeyong Oh, Hye-Jin Kim

    Coastal regions worldwide face increasing air pollution due to maritime activities. This technical note focuses on assessing the air pollution in the Daesan port area, Republic of Korea, using hourly emission measurements. Leveraging Automatic Identification System (AIS) data, we estimate vessel-induced air pollutant emissions and correlate them with real-time measurements. Vessel navigational statuses are categorized from the AIS data, enabling an estimation of fuel oil consumption. Random Forest models predict specific fuel oil consumption and maximum continuous ratings for vessels with unknown engine details. Using emission factors, we calculate the emissions (CO2, NO2, SO2, PM-10, and PM-2.5) from vessels visiting the port. These estimates are compared with actual air pollutant concentrations, revealing a qualitative relationship with an average correlation coefficient of approximately 0.33.


  • Open Access

    Ship Carbon Intensity Indicator Assessment via Just-in-Time Arrival Algorithm Based on Real-Time Data: Case Study of Pusan New International Port

    by Se-Won Kim, Jeong-On Eom

    Decarbonization is the most urgent task for the shipping industry. The International Maritime Organization, which makes the rules for shipping companies, has strengthened their carbon emissions regulation in order to reduce emissions to 70% of 2008’s carbon emissions by 2050. However, 75% of the existing fleet cannot satisfy this carbon emission regulation. The building of new vessels makes it possible to reduce carbon emissions and satisfy this regulation through adopting eco-friendly propulsion methods, such as LNG, ammonia, and methanol propulsion. However, the existing vessels on the sea find it difficult to dock and change their propulsion equipment. This research aims to propose a novel voyage operation method—a just-in-time arrival policy—that converts vessels’ waiting time into voyage time. The proposed method can reduce carbon emissions without propulsion system alteration and expand a vessel’s lifespan, thus satisfying carbon regulations. The carbon intensity indicator, invented by the IMO to regulate vessel carbonization, assesses the quantity of reduced carbon emissions. This research investigated the variation in the carbon intensity indicators of vessels when the just-in-time arrival policy was applied through studying an actual vessel’s arrival and departure dates at the Pusan International container terminal. According to the results of our analysis, ship carbon emissions decreased by an average of 45.8%, and by a maximum of 91%, compared to the levels before applying the proposed method. In addition, 87.0% of vessels obtained a carbon intensity indicator rank improvement and expanded the period that can satisfy the carbon intensity regulation by an average of eleven years and a maximum of twenty-seven years through applying the proposed just-in-time arrival policy. Additionally, the improvement effect of the carbon intensity rank positively correlates with ship size and waiting time at the port.


  • Open Access

    Port Digital Twin Development for Decarbonization: A Case Study Using the Pusan Newport International Terminal

    by Jeong-On Eom, Jeong-Hyun Yoon, Jeong-Hum Yeon, Se-Won Kim

    The maritime industry is a major carbon emission contributor. Therefore, the global maritime industry puts every effort into reducing carbon emissions in the shipping chain, which includes vessel fleets, ports, terminals, and hinterland transportation. A representative example is the carbon emission reduction standard mandated by the International Maritime Organization for international sailing ships to reduce carbon emissions this year. Among the decarbonization tools, the most immediate solution for reducing carbon emissions is to reduce vessel waiting time near ports and increase operational efficiency. The operation efficiency improvement in maritime stakeholders’ port operations can be achieved using data. This data collection and operational efficiency improvement can be realized using a digital twin. This study develops a digital twin that measures and reduces carbon emissions using the collaborative operation of maritime stakeholders. In this study, the authors propose a data structure and backbone scheduling algorithm for a port digital twin. The interactive scheduling between a port and its vessels is investigated using the digital twin. The digital twin’s interactive scheduling for the proposed model improved predictions of vessel arrival time and voyage carbon emissions. The result of the proposed digital twin model is compared to an actual operation case from the Busan New Port in September 2022, which shows that the proposed model saves over 75 % of the carbon emissions compared with the case.