{"id":"W4407964362","doi":"10.1016/j.marpolbul.2025.117740","title":"Identification of marine microplastics by a combined method of principal component analysis and random forest for fluorescence spectrum processing","year":2025,"lang":"en","type":"article","venue":"Marine Pollution Bulletin","topic":"Microplastics and Plastic Pollution","field":"Environmental Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"National Laboratory of Solid State Microstructures, Nanjing University; Natural Science Foundation of Shandong Province; Department of Education of Liaoning Province; National Natural Science Foundation of China; China Postdoctoral Science Foundation; Liaoning Provincial Department of Human Resources and Social Security","keywords":"Microplastics; Principal component analysis; Identification (biology); Environmental science; Random forest; Environmental chemistry; Chemistry; Ecology; Biology; Statistics; Computer science; Mathematics; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001101211,0.001061169,0.0008274635,0.002668397,0.000868163,0.0006952745,0.0005369687,0.0004746995,0.002029199],"category_scores_gemma":[0.001456778,0.0003459609,0.001181506,0.001660476,0.0002915523,0.0009636327,0.0004564923,0.0007369069,0.0009518865],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001797383,"about_ca_system_score_gemma":0.0008794424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003178282,"about_ca_topic_score_gemma":0.005276396,"domain_scores_codex":[0.9994778,0.00008874037,0.00003921191,0.0001672578,0.0001615568,0.00006541739],"domain_scores_gemma":[0.9992962,0.0002533238,0.00004513003,0.00005804014,0.0003191264,0.00002817655],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003340121,0.0002080682,0.00698758,0.0002773128,0.00009512671,0.00009195288,0.0001558993,0.004189334,0.5350323,0.0008011234,0.0009718104,0.4508555],"study_design_scores_gemma":[0.00006406283,0.0005053497,0.119381,0.00004156992,0.0004546833,0.0008760323,0.0002207538,0.4749532,0.3902034,0.002583113,0.01044808,0.0002686961],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08410334,0.0002738504,0.9121243,0.00004680469,0.00003783172,0.0001706191,0.0005651474,0.001851807,0.000826144],"genre_scores_gemma":[0.1276882,0.0002125576,0.8699777,0.00001544724,0.00002249192,0.0002150264,0.0007684737,0.0002420306,0.0008580034],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003178282,"threshold_uncertainty_score":0.006788373,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004348409652905448,"score_gpt":0.2234498087111708,"score_spread":0.2191013990582653,"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."}}