Predicting GHG Emissions in Shipping: A Case Study Of Canada
Bibliographic record
Abstract
Shipping remains a crucial element of global trade and commerce, facilitating over 90% of international trade by volume. The maritime industry’s advanced logistics chains are vital for the timely delivery of goods, supporting both economic growth and employment. However, it is also a significant source of pollution, accounting for approximately 3% of global greenhouse gas (GHG) emissions, and contributing 13% of nitrogen oxides (NOx) and 12% of sulfur oxides (SOx). Additionally, shipping emits harmful pollutants, including particulate matter (PM), black carbon (BC), and methane (CH4). These emissions not only impact the global climate but also pose severe health risks to communities near shorelines, contributing to asthma, respiratory and cardiovascular diseases, lung cancer, and premature death.The International Maritime Organization (IMO) is actively engaged in mitigating these environmental impacts as part of its support for the UN Sustainable Development Goal 13, which addresses climate change in alignment with the 2015 Paris Agreement. The IMO has implemented several regulations to curb GHG emissions from shipping, beginning with mandatory energy efficiency measures introduced on July 15, 2011. Subsequent regulations include the Initial IMO GHG Strategy (2018) and the updated Strategy on Reduction of GHG Emissions from Ships (2023). The 2023 strategy sets ambitious targets to achieve near-zero GHG emissions from international shipping by around 2050, with interim goals of reducing emissions by at least 20% by 2030 and 70-80% by 2040. It also aims to cut the carbon intensity of international shipping by at least 40% by 2030, measured as CO2 emissions per unit of transport work. As of January 1, 2023, ships are required to calculate their Energy Efficiency Existing Ship Index (EEXI) and establish an annual operational Carbon Intensity Indicator (CII), with ratings from A to E indicating energy efficiency (International Maritime Organization).In response to evolving regulations aimed at reducing GHG emissions, we propose a machine learning framework to improve emission predictions, with a particular focus on the Saint Lawrence River. Currently, emissions in the Canadian shipping sector are calculated a posteriori, with Environment and Climate Change Canada (ECCC) providing a national marine emissions inventory and a comprehensive visualization tool. This tool enables users to analyze shipping activities and emissions across Canada by filtering data through various parameters.Our proposed work is designed to predict GHG emissions for vessels navigating the Saint Lawrence River, with plans for broader application across Canada. By employing a bottom-up methodology, we create a detailed emissions inventory based on individual vessel activities, leveraging Automatic Identification System (AIS) data to capture the spatiotemporal dynamics of shipping (Spire). To enhance accuracy, we incorporate vessel-specific information from CLARKSONS, including engine type, fuel type, and power, along with meteorological data such as current speed to account for external factors affecting emissions. Machine learning models, particularly deep learning techniques, are employed in the prediction phase, enabling the model to continually improve with new data. This scalable approach not only enhances environmental monitoring but also supports national efforts to reduce GHG emissions from marine transportation across Canada.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.006 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".