{"id":"W4225741268","doi":"10.5750/ijme.v160ia4.1073","title":"AN APPLICATION OF MACHINE LEARNING TO SHIPPING EMISSION INVENTORY","year":2021,"lang":"en","type":"article","venue":"The International Journal of Maritime Engineering","topic":"Maritime Transport Emissions and Efficiency","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"International Association of Maritime Universities","keywords":"Set (abstract data type); Emission inventory; Computer science; Model selection; Data set; Quality (philosophy); Environmental science; Operations research; Machine learning; Meteorology; Artificial intelligence; Engineering; Air quality index; Geography","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0004842962,0.00006616581,0.00009525669,0.00005435206,0.00003880623,0.00001960019,0.0004106032,0.00002532268,0.0008957754],"category_scores_gemma":[0.000105956,0.00005260783,0.0000577843,0.0001377723,0.00001593927,0.0001334214,0.00008016724,0.0001869391,0.000009126053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007531345,"about_ca_system_score_gemma":0.00001822305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006967586,"about_ca_topic_score_gemma":0.000006312623,"domain_scores_codex":[0.9990872,0.00002228833,0.0002907359,0.00008778934,0.0004189388,0.00009308378],"domain_scores_gemma":[0.9995865,0.00004564356,0.0001051255,0.0001045652,0.00006302384,0.00009516994],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003377197,0.0001104637,0.0347142,0.000009480527,0.00002810546,0.00003476037,0.000467998,0.5164837,0.4275483,0.0001756981,0.0001264389,0.02026709],"study_design_scores_gemma":[0.0006513572,0.000184709,0.06895506,0.0003111868,0.00004540233,0.0004121053,0.000288974,0.7961914,0.08010425,0.0002642432,0.05226945,0.0003218764],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9244684,0.0001341105,0.0729875,0.0008517217,0.0002174791,0.0000506249,0.000002820845,0.00001553907,0.001271789],"genre_scores_gemma":[0.9962462,0.00001922683,0.003366872,0.00006924489,0.00008611479,0.000001254138,0.000005576041,0.00000891367,0.0001966336],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.347444,"threshold_uncertainty_score":0.9808112,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005417148154557534,"score_gpt":0.2194420612640964,"score_spread":0.2140249131095389,"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."}}