{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004616235,0.000156297,0.0001209941,0.0000635961,0.0004811966,0.00007950502,0.0001482084,0.00006622525,0.0005426132],"category_scores_gemma":[0.0007150677,0.0001541634,0.00003811724,0.0001690126,0.0003965749,0.0001710818,0.0001347813,0.0003599564,0.0008740344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002237827,"about_ca_system_score_gemma":0.000005343354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004629604,"about_ca_topic_score_gemma":0.00001997704,"domain_scores_codex":[0.9981415,0.0001748993,0.0002427247,0.0005213534,0.0005029232,0.0004165971],"domain_scores_gemma":[0.9986852,0.0008678837,0.00007569058,0.000128606,0.000002601933,0.0002399614],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001396432,0.00004590071,0.02594442,0.00002166108,0.000012028,0.0000022175,0.0003302556,0.001894685,0.9620993,0.00003071962,0.0008616875,0.008617504],"study_design_scores_gemma":[0.0009293557,0.0005219748,0.2404416,0.000016362,0.00003310035,0.000009583563,0.0002117358,0.7050775,0.01656379,0.0001258802,0.03571702,0.0003521341],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7970032,0.00006783338,0.1992527,0.002922462,0.0001041052,0.0005051429,0.00003401135,0.00003718221,0.000073363],"genre_scores_gemma":[0.9985689,0.00006985725,0.000617834,0.0003735408,0.000101065,0.00007538697,0.00007452985,0.00002799488,0.00009088351],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9455355,"threshold_uncertainty_score":0.9999039,"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."}}