{"id":"W4213263318","doi":"10.1016/j.scitotenv.2022.153903","title":"Automatic quantification and classification of microplastics in scanning electron micrographs via deep learning","year":2022,"lang":"en","type":"article","venue":"The Science of The Total Environment","topic":"Microplastics and Plastic Pollution","field":"Environmental Science","cited_by":157,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Microplastics; Artificial intelligence; Segmentation; Pattern recognition (psychology); Computer science; Environmental science; Computer vision; Biological system; Chemistry; Environmental chemistry; Biology","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":[0.001020604,0.00008501919,0.00009552437,0.00006331513,0.0004507377,0.00001198677,0.0003718948,0.00001662875,0.0002026892],"category_scores_gemma":[0.00005393699,0.00005985185,0.00003135896,0.0004681524,0.00113213,0.00007009244,0.0004617622,0.0001827247,0.000009253398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002239185,"about_ca_system_score_gemma":0.0000159374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001014363,"about_ca_topic_score_gemma":0.000004448447,"domain_scores_codex":[0.9987097,0.0001226037,0.0002635345,0.0002197804,0.0004721644,0.0002122008],"domain_scores_gemma":[0.999364,0.00008500718,0.0002732677,0.0002448249,0.000002725631,0.00003019547],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00000765841,0.00004616499,0.001440886,0.000004035965,0.000002038887,7.377174e-8,0.0005417204,0.2010922,0.7938175,0.0001228862,0.000004358681,0.002920398],"study_design_scores_gemma":[0.0001490136,0.0001152812,0.5184896,0.00001041247,0.00002102596,0.00002018902,0.0003644346,0.4335205,0.0468557,0.0003065072,0.00005395981,0.00009339133],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9984396,0.00006927739,0.0009281877,0.0001537684,0.00007985382,0.0001955246,0.000003522633,0.000004469961,0.0001257636],"genre_scores_gemma":[0.9994823,0.00002195673,0.0004093147,0.000003832245,0.000003070179,0.00001212833,0.000001275137,0.000005350205,0.00006072039],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7469618,"threshold_uncertainty_score":0.417138,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00746206696528267,"score_gpt":0.1986147713552712,"score_spread":0.1911527043899885,"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."}}