{"id":"W4406498735","doi":"10.1021/acs.analchem.4c05197","title":"Integrating C–H Information to Improve Machine Learning Classification Models for Microplastic Identification from Raman Spectra","year":2025,"lang":"en","type":"article","venue":"Analytical Chemistry","topic":"Microplastics and Plastic Pollution","field":"Environmental Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Environment and Climate Change Canada","keywords":"Chemistry; Identification (biology); Raman spectroscopy; Artificial intelligence; Machine learning; Pattern recognition (psychology); Botany; Optics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003163768,0.001369558,0.0008958622,0.001486948,0.0006835844,0.001198051,0.001245771,0.001252869,0.001468199],"category_scores_gemma":[0.008564442,0.0003955422,0.0009155217,0.001205748,0.0005351201,0.002033825,0.0007104019,0.001992597,0.001017379],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008535848,"about_ca_system_score_gemma":0.001148159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009314663,"about_ca_topic_score_gemma":0.01024986,"domain_scores_codex":[0.9993526,0.0001731175,0.00005047374,0.0001821277,0.0001877048,0.00005385327],"domain_scores_gemma":[0.9960355,0.002478576,0.0002895576,0.0004016864,0.0007241396,0.00007041158],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002229413,0.0005397702,0.008495488,0.0001681364,0.0002050373,0.00009232888,0.0001107277,0.6095459,0.01772587,0.00346985,0.002245398,0.3571785],"study_design_scores_gemma":[0.000003566681,0.00002720417,0.0006498706,0.000005971142,0.00001236979,0.000008692255,0.000007147258,0.9950398,0.002581809,0.001341768,0.0003074109,0.00001448215],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1044409,0.001324304,0.8877078,0.0007374182,0.0001383714,0.0001866173,0.0003918646,0.002421177,0.002651602],"genre_scores_gemma":[0.5566113,0.0006926904,0.4388549,0.0003213504,0.000150961,0.0001878552,0.0008984243,0.0001542808,0.002128303],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009314663,"threshold_uncertainty_score":0.01852089,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008143890954492198,"score_gpt":0.2278374596083205,"score_spread":0.2196935686538283,"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."}}