Maritime activity is known to increase pollutant concentration levels in neighboring cities. In major touristic destinations, the singular need of cruise liners to keep supplying energy to on-board services and amenities while docked, has raised concerns about this industry contribution to pollutant emissions. To estimate the impact of port activities and that exclusively due to cruises, classical approaches would rely on atmospheric dispersion models. Although these tools retain the underlying physics, lack of details on background flow state and emission inventories limits their predictive capabilities. Using historical data on pollutant concentration, meteorology and traffic intensity at specific locations across the city of Barcelona, it was found that predictions of local pollutant concentration by the present Machine Learning tool are more accurate than those provided by the CALIOPE-Urban-v1.0 in our test cases. Estimated air quality impact due to cruise ships is shown to be limited in comparison to overall Port effects.

众所周知，海上活动会增加邻近城市的污染物浓度水平。在主要的旅游目的地，邮轮在停靠时不断为船上服务和设施提供能量的独特需求引起了人们对该行业对污染物排放的贡献的担忧。为了估算港口活动的影响以及仅因航行而产生的影响，经典方法将依赖于大气扩散模型。尽管这些工具保留了基本的物理原理，但缺乏有关背景流状态和排放清单的详细信息限制了其预测能力。利用有关巴塞罗那市特定位置的污染物浓度，气象学和交通强度的历史数据，我们发现，在我们的测试案例中，当前的机器学习工具对本地污染物浓度的预测比CALIOPE-Urban-v1.0提供的预测更为准确。与总体港口影响相比，游轮对空气质量的影响估计有限。