{"id":"W4281711948","doi":"10.1016/j.jhazmat.2022.129282","title":"Evaluation of machine learning techniques to select marine oil spill response methods under small-sized dataset conditions","year":2022,"lang":"en","type":"article","venue":"Journal of Hazardous Materials","topic":"Oil Spill Detection and Mitigation","field":"Environmental Science","cited_by":29,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Northern British Columbia; Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Fisheries and Oceans Canada","keywords":"Kriging; Support vector machine; Artificial neural network; Subarctic climate; Machine learning; Computer science; Oil spill; Regression; Regression analysis; Feature selection; Arctic; Environmental science; Artificial intelligence; Data mining; Statistics; Ecology; Mathematics; Environmental 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008465388,0.002256853,0.001177464,0.002005506,0.000848059,0.001609339,0.001651716,0.001939494,0.00162204],"category_scores_gemma":[0.01956998,0.0003332861,0.00149579,0.001282229,0.0005692195,0.00163762,0.001098435,0.001458601,0.0006785376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009504501,"about_ca_system_score_gemma":0.001685581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01236549,"about_ca_topic_score_gemma":0.01273478,"domain_scores_codex":[0.9962327,0.001529217,0.0005085888,0.0008797571,0.0006114566,0.000238336],"domain_scores_gemma":[0.984272,0.01145373,0.0005372361,0.001014445,0.002428456,0.0002939959],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.006126346,0.003974164,0.04801132,0.0016906,0.002622019,0.0003286187,0.0002460098,0.4122365,0.01864504,0.0009250409,0.02018662,0.4850077],"study_design_scores_gemma":[0.0003282254,0.0009735553,0.010828,0.00007663644,0.0003067604,0.00008948691,0.0001910742,0.9755063,0.009706912,0.0004334659,0.00152768,0.00003186102],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9183049,0.00666992,0.06034565,0.001231713,0.0008030886,0.0005573196,0.004982137,0.003724943,0.003380337],"genre_scores_gemma":[0.8946108,0.001002202,0.08255405,0.0004054937,0.0002261062,0.0003386254,0.01801703,0.000286345,0.002559402],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01236549,"threshold_uncertainty_score":0.04476982,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03464809265568988,"score_gpt":0.347328762334056,"score_spread":0.3126806696783661,"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."}}