arXiv subjects

Vaishnav Vaidheeswaran

Publications and source records attributed to Vaishnav Vaidheeswaran.

5 recordsLinked to original sources

arXiv2026

Does Latent Context Help? A Controlled Evaluation of Inverse Reinforcement Learning in Arctic Shipping

Artificial Intelligence (AI)-assisted navigation can help Arctic shipping adapt to rapidly changing sea-ice conditions, but reliable deployment requires reward models that are interpretable and robust to changing environments. Inverse reinforcement learning (IRL) provides a framework for recovering such rewards from vessel trajectories, while recent meta-IRL methods introduce latent context variables to capture behavioral heterogeneity. However, it remains unclear whether these latent representations recover genuinely hidden preferences or simply re-encode information already available in the observed state. We conduct a controlled evaluation on 3,186 AIS-derived voyages from 202 vessels across nine Arctic shipping seasons, comparing a linear shared reward, a nonlinear shared reward, and a latent-context model built on the same nonlinear architecture. The nonlinear reward improves held-out likelihood by 50.9% over the linear baseline, whereas adding vessel-specific latent context reduces performance by 16.5%. Behavioral analysis, context probes, and a pre-registered feature-hiding ablation show that apparent vessel-level variation is largely explained by observable route and environmental conditions rather than hidden vessel-specific factors. Moreover, predictive accuracy, route fidelity, and reward transfer yield different model rankings, demonstrating that no single metric is sufficient to evaluate learned rewards. These findings motivate testing whether the observed route, environmental, and vessel features already explain behavioral variation before adding per-vessel latent context. This supports more trustworthy AI deployment in safety-critical domains.

cs.LG↗

arXiv2026

Transferable Dual-Stream Representations for Mesoscale-Preserving Sea Surface Temperature Downscaling

Deep learning models for scientific spatio-temporal downscaling often minimize reconstruction error while failing to preserve physically meaningful multi-scale structure. For sea surface temperature prediction, this can yield outputs that are numerically plausible yet overly smooth, missing mesoscale variability critical to regional ocean dynamics. Existing methods often focus on pixel-wise objectives or single-context conditioning, which limits their ability to preserve spectral fidelity and generalize across regions. To address this, we propose EddyFlow, a representation learning framework for kilometer-scale sea surface temperature downscaling that balances predictive accuracy, scale-dependent structure, and regional generalization. EddyFlow is trained on the Gulf of St.~Lawrence and evaluated in zero-shot and few-shot settings on the Bay of Fundy and the Gulf of Mexico. EddyFlow demonstrates that physics-informed representation learning reduces zero-shot RMSE by 21%, achieves up to 85.6% skill relative to persistence on unseen domains, and maintains near-ideal spectral fidelity with a PSD ratio of $\approx 1.00$.

cs.LG↗

arXiv2026

A Theoretical Framework for Environmental Similarity and Vessel Mobility as Coupled Predictors of Marine Invasive Species Pathways

Marine invasive species spread through global shipping and generate substantial ecological and economic impacts. Traditional risk assessments require detailed records of ballast water and traffic patterns, which are often incomplete, limiting global coverage. This work advances a theoretical framework that quantifies invasion risk by combining environmental similarity across ports with observed and forecasted maritime mobility. Climate-based feature representations characterize each port's marine conditions, while mobility networks derived from Automatic Identification System data capture vessel flows and potential transfer pathways. Clustering and metric learning reveal climate analogues and enable the estimation of species survival likelihood along shipping routes. A temporal link prediction model captures how traffic patterns may change under shifting environmental conditions. The resulting fusion of environmental similarity and predicted mobility provides exposure estimates at the port and voyage levels, supporting targeted monitoring, routing adjustments, and management interventions.

cs.CE↗

arXiv2025

Modeling Maritime Transportation Behavior Using AIS Trajectories and Markovian Processes in the Gulf of St. Lawrence

Maritime transportation is central to the global economy, and analyzing its large-scale behavioral data is critical for operational planning, environmental stewardship, and governance. This work presents a spatio-temporal analytical framework based on discrete-time Markov chains to model vessel movement patterns in the Gulf of St. Lawrence, with particular emphasis on disruptions induced by the COVID-19 pandemic. We discretize the maritime domain into hexagonal cells and construct mobility signatures for distinct vessel types using cell transition frequencies and dwell times. These features are used to build origin-destination matrices and spatial transition probability models that characterize maritime dynamics across multiple temporal resolutions. Focusing on commercial, fishing, and passenger vessels, we analyze the temporal evolution of mobility behaviors during the pandemic, highlighting significant yet transient disruptions to recurring transport patterns. The methodology we contribute to this paper allows for an extensive behavioral analytics key for transportation planning. Accordingly, our findings reveal vessel-specific mobility signatures that persist across spatially disjoint regions, suggesting behaviors invariant to time. In contrast, we observe temporal deviations among passenger and fishing vessels during the pandemic, reflecting the influence of social isolation measures and operational constraints on non-essential maritime transport in this region.

stat.AP↗

arXiv2025

Goal-Conditioned Reinforcement Learning for Data-Driven Maritime Navigation

Routing vessels through narrow and dynamic waterways is challenging due to changing environmental conditions and operational constraints. Existing vessel-routing studies typically fail to generalize across multiple origin-destination pairs and do not exploit large-scale, data-driven traffic graphs. In this paper, we propose a reinforcement learning solution for big maritime data that can learn to find a route across multiple origin-destination pairs while adapting to different hexagonal grid resolutions. Agents learn to select direction and speed under continuous observations in a multi-discrete action space. A reward function balances fuel efficiency, travel time, wind resistance, and route diversity, using an Automatic Identification System (AIS)-derived traffic graph with ERA5 wind fields. The approach is demonstrated in the Gulf of St. Lawrence, one of the largest estuaries in the world. We evaluate configurations that combine Proximal Policy Optimization with recurrent networks, invalid-action masking, and exploration strategies. Our experiments demonstrate that action masking yields a clear improvement in policy performance and that supplementing penalty-only feedback with positive shaping rewards produces additional gains.

cs.LG↗