Tiered prediction models for port vessel emissions inventories

Albeit its importance, a large number of port authorities do not provide continuous or publicly available air emissions inventories (EIs) and thereby obscure the emissions contribution of ports. This is caused by, e.g., the economic effort generated by obtaining data. Therefore, the performance of abatement measures is not monitored and projected, which is specifically disadvantageous concerning top contributors such as container ships. To mitigate this issue, in this paper we propose port vessel EI prediction models by exploring the combination of different machine-learning algorithms, data from the one-off application of an activity-based bottom-up methodology and vessel-characteristics data. The results for this specific case show that prediction models enable acceptable trade-offs between the prediction performance and data requirements, promoting the creation of EIs.

Automated summary

Despite its importance, many port authorities do not provide continuous or publicly available air emissions inventories, which obscures the emissions contribution of ports. In this paper, we propose port vessel emissions prediction models using machine learning algorithms and vessel data to enable accurate prediction and creation of emissions inventories.