Skip to content
DraconiticResearch
Search Sources API
194,216 studies31 sourcesUpdated 14 min ago
Peer-reviewedCC BYTransportation Research Part D Transport and Environment

Data-driven investigation of ship fuel consumption integrating causal inference and hierarchical analysis

  • Wenjie Cao1,2
  • Xinjian Wang1,2,3
  • Wei Zhang4
  • Hui Li5
  • Siming Fang6
  • Zaili Yang1
6 affiliations
  1. 1Liverpool Logistics, Offshore and Marine (LOOM) Research Institute, Liverpool John Moores University, Liverpool L3 3AF, UK
  2. 2Navigation College, Dalian Maritime University, Dalian 116026, PR China
  3. 3State Key Laboratory of Maritime Technology and Safety, Dalian 116026, PR China
  4. 4Centre for Maritime and Logistics Management, Australian Maritime College, University of Tasmania, Maritime Way, Newnham, TAS 7248, Australia
  5. 5School of Engineering, University of Southampton, Southampton SO17 1, UK
  6. 6Navigation College, Jimei University, Xiamen 361021, PR China
Open at sourceDOICite

Abstract

This study develops a data-driven analytical framework that integrates causal inference with hierarchical analysis to reveal the underlying mechanisms influencing ship fuel consumption (SFC). The framework combines multi-source data fusion, direct linear non-gaussian acyclic model-based causal discovery, and double machine learning with causal forests model to estimate Average Treatment Effects (ATEs), followed by interpretive structural modelling for hierarchical decomposition. Experimental results under the expanded DAG-derived adjustment specification indicate that Daily sailing hours has the strongest positive conditional effect on SFC (ATE = 2.058), followed by Main engine RPM with a positive but more uncertain effect estimate (ATE = 0.268). The hierarchical analysis further organises the directional-dependence network into interpretable structural levels, thereby illustrating possible multi-level transmission patterns among operational and environmental factors. This framework provides an exploratory and graph-informed analytical basis for interpreting directional dependencies and observed-covariate conditional effect patterns in SFC, offering cautious decision support for data-driven energy management. The source code is publicly available at: https://github.com/AdvMarTech/ship_fuel_consum_causalinfer .

Related

  1. From standard to data-driven flow-based design of urban drainage and wastewater management systems: integrating variability, open data, and standardization
    Marcello Serrao, Natalia Duque Villarreal, Thibaud Maruejouls +8
    Water Science and TechnologyPeer-reviewedCC BY 4.0Full textEnvironmental science & pollutionHAL
  2. An investigation of novel population models to control aphid outbreaks via a data driven “adaptive” framework
    Aniket Banerjee, Urvashi Verma, Satyam Narayan Srivastava +1
    PLOS EcosystemsPeer-reviewedCC BY 4.0EcologyZoology & animal behaviourPLOS
  3. Matching Wind-Solar Portfolios with Electricity Consumption Across Climates: A Physical Framework to Minimize Residual Demand
    Justine Duval, Fabien Perdu, Arthur Clerjon +1
    HALPreprintPublisher termsFull textEnvironmental science & pollutionHAL
  4. Market Inequalities and Ecological Distinction: The Moral Ruses of Sustainable Consumption across the North-South Divide
    Manisha Anantharaman, Sophie Dubuisson-Quellier
    SociologicaPeer-reviewedCC BY 4.0Full textEnvironmental science & pollutionHAL
  5. Depleting Nucleation: Out-of-Equilibrium Effects of Monomer Consumption and System Adiabaticity on the Activation Energy Barrier
    Peter J. Skrdla
    ChemRxivPreprintCC BYFull textAtmospheric science & meteorologyChemRxiv

Cite

BibTeXRIS
BibTeX
@article{cao2026datadriven,
  title = {{Data-driven investigation of ship fuel consumption integrating causal inference and hierarchical analysis}},
  author = {Wenjie Cao and Xinjian Wang and Wei Zhang and Hui Li and Siming Fang and Zaili Yang},
  journal = {Transportation Research Part D Transport and Environment},
  year = {2026},
  month = jun,
  doi = {10.1016/j.trd.2026.105491},
  url = {https://doi.org/10.1016/j.trd.2026.105491},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Data-driven investigation of ship fuel consumption integrating causal inference and hierarchical analysis
AU  - Wenjie Cao
AU  - Xinjian Wang
AU  - Wei Zhang
AU  - Hui Li
AU  - Siming Fang
AU  - Zaili Yang
PY  - 2026
DA  - 2026/06/29
JO  - Transportation Research Part D Transport and Environment
DO  - 10.1016/j.trd.2026.105491
UR  - https://doi.org/10.1016/j.trd.2026.105491
AB  - This study develops a data-driven analytical framework that integrates causal inference with hierarchical analysis to reveal the underlying mechanisms influencing ship fuel consumption (SFC). The framework combines multi-source data fusion, direct linear non-gaussian acyclic model-based causal discovery, and double machine learning with causal forests model to estimate Average Treatment Effects (ATEs), followed by interpretive structural modelling for hierarchical decomposition. Experimental results under the expanded DAG-derived adjustment specification indicate that Daily sailing hours has the strongest positive conditional effect on SFC (ATE = 2.058), followed by Main engine RPM with a positive but more uncertain effect estimate (ATE = 0.268). The hierarchical analysis further organises the directional-dependence network into interpretable structural levels, thereby illustrating possible multi-level transmission patterns among operational and environmental factors. This framework provides an exploratory and graph-informed analytical basis for interpreting directional dependencies and observed-covariate conditional effect patterns in SFC, offering cautious decision support for data-driven energy management. The source code is publicly available at: https://github.com/AdvMarTech/ship_fuel_consum_causalinfer .
SN  - 1361-9209
SN  - 1879-2340
ER  -