EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Scale Temporal Uncertainty-Aware Hierarchical Adaptive Ensemble for Intelligent Ship Emission Monitoring and Prediction

Duc-Anh Pham, Kyeong-Ju Kong, Jung-Min Kim, Hee-Sung Yoon, Seung-Hun Han

Journal of Marine Science and Engineering · 27.04.2026 · 14 (9) · 799

DOI: 10.3390/jmse14090799 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Marine Science and Engineering, online erschienen am 27.04.2026. Verfasst von Duc-Anh Pham und 4 weiteren Autor:innen. Die Arbeit nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: 2025 Ministry of Oceans and Fisheries (MOF) Marine Blue Tech Future Leader Training Project ‘Training Blue Tech Leaders for Eco-Friendly Ships’.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents a novel Multi-Scale Temporal Uncertainty-aware Hierarchical Adaptive Ensemble (MSTU-HAE) algorithm for intelligent ship emission monitoring and prediction in maritime environmental compliance applications. The maritime shipping industry contributes approximately 3% of global CO2 emissions and significant amounts of nitrogen oxides and sulfur oxides, necessitating advanced predictive monitoring systems. The proposed MSTU-HAE algorithm integrates three key innovations: multi-scale temporal feature extraction using causal convolutions at short-term (5 samples), medium-term (20 samples), and long-term (60 samples) windows; gas-specific attention mechanisms that automatically weight temporal scales based on individual emission gas characteristics; and three-level hierarchical uncertainty quantification encompassing individual model uncertainty, ensemble disagreement, and regulatory compliance risk assessment. Experimental validation was conducted using emission data collected from a fishing vessel over 3 operational days (1732 original samples), augmented to 17,320 samples via controlled replication with noise injection to support model training. Rigorous temporal data splitting with 70%/15%/15% train/validation/test partitioning ensures no data leakage. Comparative analysis against six baseline methods (XGBoost, LSBoost, AdaBoost, Ridge Regression, Random Forest, and K-Nearest Neighbors) demonstrates that MSTU-HAE achieves superior average performance, with R2 = 0.9670 and NSE = 0.9670 across all emission gases. This research contributes a robust, interpretable, and scalable prediction framework that advances the state of the art in maritime environmental monitoring through novel algorithmic innovations in temporal feature learning and uncertainty quantification.

Förderung

  • 2025 Ministry of Oceans and Fisheries (MOF) Marine Blue Tech Future Leader Training Project ‘Training Blue Tech Leaders for Eco-Friendly Ships’

Zitieren

APA

Pham, D., Kong, K., Kim, J., Yoon, H., & Han, S. (2026). Multi-Scale Temporal Uncertainty-Aware Hierarchical Adaptive Ensemble for Intelligent Ship Emission Monitoring and Prediction. Journal of Marine Science and Engineering, 14(9), 799. https://doi.org/10.3390/jmse14090799

Vancouver

Pham D, Kong K, Kim J, Yoon H, Han S. Multi-Scale Temporal Uncertainty-Aware Hierarchical Adaptive Ensemble for Intelligent Ship Emission Monitoring and Prediction. Journal of Marine Science and Engineering. 2026;14(9):799. doi:10.3390/jmse14090799

BibTeX
@article{Pham2026,
  author = {Pham, Duc-Anh and Kong, Kyeong-Ju and Kim, Jung-Min and Yoon, Hee-Sung and Han, Seung-Hun},
  title = {Multi-Scale Temporal Uncertainty-Aware Hierarchical Adaptive Ensemble for Intelligent Ship Emission Monitoring and Prediction},
  journal = {Journal of Marine Science and Engineering},
  year = {2026},
  volume = {14},
  number = {9},
  pages = {799},
  doi = {10.3390/jmse14090799}
}
Kostenlos starten →