SWR-Viz: AI-assisted Interactive Visual Analytics Framework for Ship Weather Routing
Subhashis Hazarika, Leonard Lupin-Jimenez, Rohit Vuppala, Ashesh Chattopadhyay, Hon Yung Wong
TL;DR
This work tackles the challenge of rapid, emissions-aware ship weather routing by delivering SWR-Viz, an interactive framework that combines a physics-informed AI wave forecast emulator based on the Fourier Neural Operator with SIMROUTE routing and emissions analytics. The wave forecast uses a hard Predictor-Error-Corrector constraint and soft physics losses, models the sea state via $dx/dt = F(x(t))$ with rollout $x(t+\Delta t) = x(t) + \tfrac{1}{2}\Delta t\left(N'[x(t)] + N'[x(t) + N'[x(t)]]\right)$, and incorporates data assimilation through an $RBF$ kernel to integrate sparse observations on a grid-agnostic platform. The integrated routing pipeline evaluates routes with engine-power and emissions metrics (e.g., $CO_2$, $NO_x$, $SO_x$, $PM$) and supports interactive digital rehearsals to define avoidance zones and compare up to five alternative paths, with validation across the Japan Coast and Gulf of Mexico showing stability and realistic routing outcomes close to ground-truth reanalysis. Expert feedback highlights usability and the ability to isolate voyage segments with higher emissions-reduction potential, demonstrating the framework’s practicality as a human-centered decision-support tool in complex, geospatial domains. Overall, SWR-Viz demonstrates how lightweight AI forecasting can be effectively fused with visual analytics to support rapid, informed routing decisions under changing ocean conditions.
Abstract
Efficient and sustainable maritime transport increasingly depends on reliable forecasting and adaptive routing, yet operational adoption remains difficult due to forecast latencies and the need for human judgment in rapid decision-making under changing ocean conditions. We introduce SWR-Viz, an AI-assisted visual analytics framework that combines a physics-informed Fourier Neural Operator wave forecast model with SIMROUTE-based routing and interactive emissions analytics. The framework generates near-term forecasts directly from current conditions, supports data assimilation with sparse observations, and enables rapid exploration of what-if routing scenarios. We evaluate the forecast models and SWR-Viz framework along key shipping corridors in the Japan Coast and Gulf of Mexico, showing both improved forecast stability and realistic routing outcomes comparable to ground-truth reanalysis wave products. Expert feedback highlights the usability of SWR-Viz, its ability to isolate voyage segments with high emission reduction potential, and its value as a practical decision-support system. More broadly, this work illustrates how lightweight AI forecasting can be integrated with interactive visual analytics to support human-centered decision-making in complex geospatial and environmental domains.