{"id":"W3091414454","doi":"10.1088/1748-9326/abbd01","title":"Machine learning for aquatic plastic litter detection, classification and quantification (APLASTIC-Q)","year":2020,"lang":"en","type":"article","venue":"Environmental Research Letters","topic":"Microplastics and Plastic Pollution","field":"Environmental Science","cited_by":117,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Deutsche Gesellschaft für Internationale Zusammenarbeit; Bundesministerium für Wirtschaftliche Zusammenarbeit und Entwicklung; International Atomic Energy Agency; University of Toronto; World Bank Group; Deutsche Forschungsgemeinschaft; Niedersächsische Ministerium für Wissenschaft und Kultur; Volkswagen Foundation","keywords":"Litter; Plastic bag; Environmental science; Computer science; Machine learning; Artificial intelligence; Periphyton; Pixel; Marine debris; Remote sensing; Ecology; Waste management; Biology; Engineering; Meteorology; Geography","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009638807,0.0008245576,0.0003361172,0.0005401848,0.0002498232,0.0004664671,0.001011894,0.0007286821,0.003097738],"category_scores_gemma":[0.001725822,0.0002616779,0.0004177343,0.0003230642,0.0002660382,0.0005365298,0.0008369368,0.0006691505,0.0008036749],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001151936,"about_ca_system_score_gemma":0.001131313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01513931,"about_ca_topic_score_gemma":0.01758902,"domain_scores_codex":[0.9996638,0.00006608785,0.0000194218,0.0001309448,0.00006300562,0.00005664877],"domain_scores_gemma":[0.9994174,0.0001938269,0.00006255732,0.00006862078,0.0002274484,0.00003019967],"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":[0.0004086565,0.0003506942,0.01913363,0.0002999358,0.0002659806,0.0002340729,0.00007267475,0.2697087,0.02968539,0.002478375,0.02167556,0.6556864],"study_design_scores_gemma":[0.00001420944,0.00007278247,0.002324294,0.00001344509,0.00001320928,0.00002835227,0.00001391803,0.9885889,0.006644956,0.0006848678,0.001592457,0.000008604638],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.324462,0.001651651,0.6459993,0.001497781,0.0003651321,0.0005814841,0.003312862,0.01360652,0.008523243],"genre_scores_gemma":[0.816111,0.0002725402,0.1676874,0.0007147359,0.00006923614,0.0002821239,0.004228559,0.00008946776,0.0105449],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01513931,"threshold_uncertainty_score":0.03010237,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04550698208650344,"score_gpt":0.2686950186324235,"score_spread":0.2231880365459201,"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."}}