{"id":"W4387013344","doi":"10.1016/j.envpol.2023.122548","title":"Leveraging deep learning for automatic recognition of microplastics (MPs) via focal plane array (FPA) micro-FT-IR imaging","year":2023,"lang":"en","type":"article","venue":"Environmental Pollution","topic":"Microplastics and Plastic Pollution","field":"Environmental Science","cited_by":39,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Pattern recognition (psychology); Confusion; Computer science; Convolutional neural network; Confusion matrix; Spectral line; Environmental science; Materials science; Biological system; Physics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003875296,0.0002809888,0.0002532131,0.000145308,0.0003682937,0.00002992431,0.0001568829,0.000112945,0.0009637477],"category_scores_gemma":[0.00008646074,0.0003061315,0.0001263845,0.0002341504,0.000263429,0.0002074396,0.0001220123,0.0002141586,0.001262904],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004289733,"about_ca_system_score_gemma":0.000009129025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006108881,"about_ca_topic_score_gemma":0.00001301375,"domain_scores_codex":[0.9980363,0.00008970674,0.0004885626,0.0004625309,0.0003521552,0.0005707332],"domain_scores_gemma":[0.9992168,0.0001945022,0.000279823,0.0001742206,0.000003552479,0.0001311047],"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":[0.00005079679,0.00008526852,0.006950277,0.00004352353,0.00002298035,0.000005653559,0.0004606948,0.01006641,0.9180729,0.000002704639,0.0005269601,0.06371183],"study_design_scores_gemma":[0.002679303,0.0004309567,0.2805717,0.000197333,0.0002460168,0.0001704063,0.001200686,0.4111975,0.2943498,0.001567808,0.006224265,0.001164292],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8060798,0.00005594424,0.1924389,0.00009063959,0.0004551023,0.000374087,0.0001507571,0.0001216047,0.0002331427],"genre_scores_gemma":[0.9936926,0.00006039966,0.005162088,0.00007352026,0.0001073997,0.00002974251,0.0005980617,0.00004791647,0.0002282208],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6237231,"threshold_uncertainty_score":0.9999495,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008795327414080407,"score_gpt":0.1956070959600578,"score_spread":0.1868117685459774,"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."}}