Physics-informed offline reinforcement learning reduces worst-case fuel risk in maritime routing

International shipping produces approximately 3% of global greenhouse gas emissions, yet voyage routing remains dominated by heuristic methods that adapt poorly to varying ocean conditions. Here we present Pier (Physics-Informed, Energy-efficient, Risk-aware routing), an offline reinforcement learning framework that learns fuel-efficient, safety-aware routing policies from physics-calibrated environments grounded in historical vessel-tracking and ocean-reanalysis data, requiring no online simulator. Validated on one full year (2023) of Automatic Identification System data across seven Gulf of Mexico routes, Pier reduces mean fuel consumption and, more strongly, its variance and worst-case tail. Across five routes, mean per-voyage CO 2 is 10.2% lower than great-circle routing (bootstrap 95% CI [2.9%, 16.7%]; Monte Carlo [9.3%, 11.0%]). Per-voyage CO 2 variance is 3.7 \(\times\) lower (Levene’s test \(p = 0.0020\) ), and voyages exceeding 2 \(\times\) the median CO 2 fall from 3.0% to 0.3% (2 of 577), with the worst single voyage reduced by 65%. Pier is forecast-independent: in an exploratory experiment, classical path optimization’s wave protection degrades as forecast noise grows ( \(\sim\) 2.2 \(\times\) at \(\sigma = 0.25\) ), while Pier maintains constant performance from local observations alone. Pier demonstrates that physics-informed offline reinforcement learning enables stable, risk-aware decision-making in safety-critical transportation domains where online simulation is unavailable.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-18
DOI
https://doi.org/10.1038/s41598-026-79923-y
Citations
1
Primary Topic
Maritime Transport Emissions and Efficiency
Type
article
Field-Weighted Citation Impact
1.30

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Physics-informed offline reinforcement learning reduces worst-case fuel risk in maritime routing

Aniruddha Bora, Julie Steele Chalfant, Chryssostomos Chryssostomidis
1 citations
Scientific Reports
Maritime Transport Emissions and Efficiency
1.30
article

Physics-informed offline reinforcement learning reduces worst-case fuel risk in maritime routing

Aniruddha Bora, Julie Steele Chalfant, Chryssostomos Chryssostomidis
article en
1 citations

Abstract

International shipping produces approximately 3% of global greenhouse gas emissions, yet voyage routing remains dominated by heuristic methods that adapt poorly to varying ocean conditions. Here we present Pier (Physics-Informed, Energy-efficient, Risk-aware routing), an offline reinforcement learning framework that learns fuel-efficient, safety-aware routing policies from physics-calibrated environments grounded in historical vessel-tracking and ocean-reanalysis data, requiring no online simulator. Validated on one full year (2023) of Automatic Identification System data across seven Gulf of Mexico routes, Pier reduces mean fuel consumption and, more strongly, its variance and worst-case tail. Across five routes, mean per-voyage CO 2 is 10.2% lower than great-circle routing (bootstrap 95% CI [2.9%, 16.7%]; Monte Carlo [9.3%, 11.0%]). Per-voyage CO 2 variance is 3.7 \(\times\) lower (Levene’s test \(p = 0.0020\) ), and voyages exceeding 2 \(\times\) the median CO 2 fall from 3.0% to 0.3% (2 of 577), with the worst single voyage reduced by 65%. Pier is forecast-independent: in an exploratory experiment, classical path optimization’s wave protection degrades as forecast noise grows ( \(\sim\) 2.2 \(\times\) at \(\sigma = 0.25\) ), while Pier maintains constant performance from local observations alone. Pier demonstrates that physics-informed offline reinforcement learning enables stable, risk-aware decision-making in safety-critical transportation domains where online simulation is unavailable.

Scientific Reports
Texas State University (US), MIT Sea Grant (US), Massachusetts Institute of Technology (US)
U.S. Department of Energy, Texas State University, National Oceanic and Atmospheric Administration, Office of Science, Argonne National Laboratory
Climate action, Industry, innovation and infrastructure
Openalex Percentile: Top 29%
Maritime Transport Emissions and Efficiency
1.30
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon