{"id":"W4383506396","doi":"10.1016/j.oceaneng.2023.115271","title":"Fuel consumption prediction for a passenger ferry using machine learning and in-service data: A comparative study","year":2023,"lang":"en","type":"article","venue":"Ocean Engineering","topic":"Maritime Transport Emissions and Efficiency","field":"Environmental Science","cited_by":40,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada; Simon Fraser University","funders":"National Research Council Canada","keywords":"Multicollinearity; Decision tree; Artificial neural network; Computer science; Energy consumption; Data mining; Boosting (machine learning); Machine learning; Ensemble forecasting; Regression analysis; Process (computing); Ensemble learning; Predictive modelling; Tree (set theory); Domain (mathematical analysis); Linear regression; Fuel efficiency; Engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002982299,0.00008951689,0.0001069208,0.00006191646,0.00007876161,0.00001741963,0.00007988836,0.00002603867,0.00006335117],"category_scores_gemma":[0.00001383033,0.00008928083,0.000008824516,0.0002769207,0.00001185258,0.0001786674,0.00009389196,0.0001070567,0.00000890766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003628924,"about_ca_system_score_gemma":0.000002935622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000109514,"about_ca_topic_score_gemma":0.000128391,"domain_scores_codex":[0.9993358,0.00001188714,0.0001370602,0.0002469154,0.00009989953,0.000168489],"domain_scores_gemma":[0.9997754,0.00004318653,0.00002073672,0.0001086609,0.000003708279,0.00004827683],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000192963,0.00007699811,0.6357452,0.00008207605,0.000009289512,0.000007667418,0.001756528,0.3559665,0.006058392,0.000003144207,0.00003363038,0.0002412554],"study_design_scores_gemma":[0.0002949908,0.00002373831,0.2465255,0.00002086713,0.00001056457,0.000002297251,0.0002797823,0.7519758,0.00001249975,0.000001758306,0.0007808223,0.00007146791],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9975778,0.00004345828,0.001847006,0.00001961997,0.00004746314,0.0002941437,0.00002405384,0.00009615146,0.00005032391],"genre_scores_gemma":[0.9988746,0.00001809928,0.00096426,0.000004049115,0.00001503443,0.000005778994,0.00005933588,0.00001113581,0.00004768919],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3960093,"threshold_uncertainty_score":0.3640767,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05992183769075371,"score_gpt":0.2894238771981307,"score_spread":0.229502039507377,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}