Abstract This study presents an eXplainable Artificial Intelligence (XAI) framework to predict the performance of marine scrubbers used for sulfur dioxide (SO2) removal from marine diesel engine flue gases. Using an aggregated dataset from a roll-on/roll-off (Ro-Ro) cargo ship equipped with an open-loop scrubber, combined with satellite data, the study constructs and evaluates multiple artificial intelligence models, including ensemble models, which were benchmarked against each other using standard regression metrics such as the coefficient of determination (R2), mean absolute error (MAE), and mean squared error (MSE). Results achieve high accuracy R2>0.92 and offer insights for optimizing scrubber operations. Nevertheless, artificial intelligence models lack transparency. To overcome this problem, this research integrates post-hoc explainability techniques to elucidate the contributions of various features to model predictions, thereby enhancing interpretability and reliability. The integration of SHapley Additive exPlanations (SHAP) and Explain Like I’m 5 (ELI5) not only confirmed the consistency of feature importance rankings (e.g. seawater acidity level, SO2 inlet concentration, outlet temperature) but also aligned with the physical-chemical principles of SO2 absorption. Quantitative comparisons with theoretical expectations demonstrated the reliability of the XAI insights, enhancing both model transparency and interpretability. This can improve the current capability of designing scrubber units by defining more efficient and less expensive options for environmental regulation compliance. © 2025 The Authors
DOI Publisher Details Copy BibTeX Download .bib
{"key"=>"Di Bonito2025", "type"=>"Article", "bibtex"=>"@article{Di Bonito2025,\n author = {Di Bonito, Luigi Piero and Campanile, Lelio and Iacono, Mauro and Di Natale, Francesco},\n title = {An eXplainable Artificial Intelligence framework to predict marine scrubbers performances},\n year = {2025},\n journal = {Engineering Applications of Artificial Intelligence},\n volume = {160},\n doi = {10.1016/j.engappai.2025.111860}\n}\n", "author"=>"Di Bonito, Luigi Piero and Campanile, Lelio and Iacono, Mauro and Di Natale, Francesco", "author_array"=>[{"first"=>"Luigi Piero", "last"=>"Di Bonito", "prefix"=>"", "suffix"=>""}, {"first"=>"Lelio", "last"=>"Campanile", "prefix"=>"", "suffix"=>""}, {"first"=>"Mauro", "last"=>"Iacono", "prefix"=>"", "suffix"=>""}, {"first"=>"Francesco", "last"=>"Di Natale", "prefix"=>"", "suffix"=>""}], "author_0_first"=>"Luigi Piero", "author_0_last"=>"Di Bonito", "author_0_prefix"=>"", "author_0_suffix"=>"", "author_1_first"=>"Lelio", "author_1_last"=>"Campanile", "author_1_prefix"=>"", "author_1_suffix"=>"", "author_2_first"=>"Mauro", "author_2_last"=>"Iacono", "author_2_prefix"=>"", "author_2_suffix"=>"", "author_3_first"=>"Francesco", "author_3_last"=>"Di Natale", "author_3_prefix"=>"", "author_3_suffix"=>"", "title"=>"An eXplainable Artificial Intelligence framework to predict marine scrubbers performances", "year"=>"2025", "journal"=>"Engineering Applications of Artificial Intelligence", "volume"=>"160", "doi"=>"10.1016/j.engappai.2025.111860", "url"=>"https://www.scopus.com/inward/record.uri?eid=2-s2.0-105012411635&doi=10.1016%2fj.engappai.2025.111860&partnerID=40&md5=d72a3bfd4424ef830e7cbd0060404d28", "abstract"=>"This study presents an eXplainable Artificial Intelligence (XAI) framework to predict the performance of marine scrubbers used for sulfur dioxide (SO2) removal from marine diesel engine flue gases. Using an aggregated dataset from a roll-on/roll-off (Ro-Ro) cargo ship equipped with an open-loop scrubber, combined with satellite data, the study constructs and evaluates multiple artificial intelligence models, including ensemble models, which were benchmarked against each other using standard regression metrics such as the coefficient of determination (R2), mean absolute error (MAE), and mean squared error (MSE). Results achieve high accuracy R2>0.92 and offer insights for optimizing scrubber operations. Nevertheless, artificial intelligence models lack transparency. To overcome this problem, this research integrates post-hoc explainability techniques to elucidate the contributions of various features to model predictions, thereby enhancing interpretability and reliability. The integration of SHapley Additive exPlanations (SHAP) and Explain Like I’m 5 (ELI5) not only confirmed the consistency of feature importance rankings (e.g. seawater acidity level, SO2 inlet concentration, outlet temperature) but also aligned with the physical-chemical principles of SO2 absorption. Quantitative comparisons with theoretical expectations demonstrated the reliability of the XAI insights, enhancing both model transparency and interpretability. This can improve the current capability of designing scrubber units by defining more efficient and less expensive options for environmental regulation compliance. © 2025 The Authors", "author_keywords"=>"CatBoost regression model; Chemical engineering; Explainable Artificial Intelligence; Marine scrubbers; SHapley Additive Explanations method; Sulfur dioxide removal", "keywords"=>"Additives; Diesel engines; Marine engines; Regression analysis; Regulatory compliance; Ships; Sulfur dioxide; Transparency; Catboost regression model; Explainable artificial intelligence; Intelligence models; Marine scrubber; Performance; Regression modelling; Shapley; Shapley additive explanation method; SO 2; Sulphur dioxide removal; Mean square error; Scrubbers", "publication_stage"=>"Final", "source"=>"Scopus", "note"=>"Cited by: 0"}