Back to search

Virginia Commonwealth University

An Integrated Data-Driven Framework for Arctic Shipping: Analyzing Vessel Speed, Environmental and Ecological Factors Through Innovative Statistical Spatio-Temporal Methods, Inverse Optimization and Machine Learning

Abstract

dc:description.abstract

This dissertation develops an integrated data-driven framework to analyze vessel navigation and ecological risk in the United States Arctic from 2010 to 2019. As environmental change and maritime activity increase in the region, understanding how vessels respond to dynamic conditions and how those responses interact with marine ecosystems has become increasingly important. A central theme of this dissertation is the treatment of vessel speed as both an observed outcome and a decision variable reflecting trade- offs among operational, environmental, and ecological factors. The first chapter develops a predictive framework for vessel speed over ground (SOG) using Gaussian Process Boosting (GPBoost), which combines gradient-boosted trees with grouped random effects to capture nonlinear relationships and structured heterogeneity across vessels, space, and time. Using more than 14 million Automatic Identification System (AIS) obser- vations, the model identifies key environmental and operational drivers of vessel speed, including sea ice concentration, wind conditions, and vessel characteristics. The second chapter develops a spatiotemporal framework for whale inten- sity using a Log-Gaussian Cox Process (LGCP). By integrating aerial survey data with environmental covariates, this approach produces high-resolution estimates of beluga and bowhead whale intensity across space and time, pro- viding a spatial measure of ecological exposure. Building on these results, the third chapter develops an inverse control constrained optimization framework to infer the latent trade-offs govern- ing vessel speed decisions. Observed vessel speeds are treated as solutions to an underlying risk-minimization problem that balances deviation from typical operating speed with exposure to ice-related navigational risk and whale-related ecological risk. The results reveal substantial heterogeneity across vessel groups and navigational statuses, with ice-related risk exerting a stronger and more consistent influence on vessel speed than whale-related risk. Overall, this dissertation integrates machine learning, spatial statistics, and inverse optimization to move beyond prediction toward interpretable inference in Arctic maritime systems.

Degree

thesis:*
Name thesis:degree_name
Doctor of Philosophy
Level thesis:degree_level
Dissertation
Discipline thesis:degree_discipline
Integrative Life Sciences

Author and committee

dc:creator, dc:contributor.*
Authors dc:creator
  • Pant, Mauli
  • 0000-0002-9666-8421
Contributors dc:contributor
  • Linda Fernandez
  • Indranil Sahoo
  • Paul Brooks
  • Cheng Ly
  • Johan Ren´e van Dorp

Subjects

dc:subject × 13

Rights

dc:rights
Statement dc:rights
  • © The Author

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
Virginia Commonwealth University
Base URL
scholarscompass.vcu.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Pant, Mauli; 0000-0002-9666-8421. An Integrated Data-Driven Framework for Arctic Shipping: Analyzing Vessel Speed, Environmental and Ecological Factors Through Innovative Statistical Spatio-Temporal Methods, Inverse Optimization and Machine Learning. Dissertation thesis, https://doi.org/10.25772/h7ke-qe74