{"id":"W4417231053","doi":"10.1021/acs.analchem.5c04463","title":"Surface-Enhanced Raman Spectroscopy–Machine Learning for Multiplex Naphthenic Acid Profiling in Water","year":2025,"lang":"en","type":"article","venue":"Analytical Chemistry","topic":"Petroleum Processing and Analysis","field":"Chemistry","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Natural Resources Canada; University of Alberta","funders":"Alberta Innovates; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Naphthenic acid; Convolutional neural network; Principal component analysis; Chemometrics; Artificial neural network; Deep learning; Multiplex; Pattern recognition (psychology); Support vector machine","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":[0.00141285,0.0008426307,0.0004626816,0.0006383811,0.0002218073,0.0004542345,0.0004070227,0.0006514572,0.0005349811],"category_scores_gemma":[0.001716327,0.0002933071,0.0004903446,0.0005686482,0.000338614,0.0007083427,0.0004414755,0.0009501359,0.0003933327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004576467,"about_ca_system_score_gemma":0.0005251103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00152755,"about_ca_topic_score_gemma":0.00292679,"domain_scores_codex":[0.9995635,0.0001205629,0.00002505055,0.000126612,0.0001294643,0.00003484474],"domain_scores_gemma":[0.9995769,0.0002084022,0.00007466227,0.000042634,0.00008285257,0.00001457552],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000354813,0.0005174397,0.008622448,0.0003354562,0.0002008779,0.0001723342,0.0001522979,0.2271013,0.369779,0.003935828,0.001351225,0.3874771],"study_design_scores_gemma":[0.000005223643,0.0001042754,0.001228176,0.000007254718,0.00001060233,0.00003726889,0.00001573179,0.9491985,0.04764055,0.001075919,0.0006591077,0.00001744394],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1908715,0.001259205,0.8032316,0.000345888,0.00005970527,0.0001176287,0.0002733874,0.001843047,0.001998134],"genre_scores_gemma":[0.713553,0.0006932748,0.2836512,0.0001324083,0.00003207767,0.0001521716,0.000302134,0.00004976273,0.001434038],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00152755,"threshold_uncertainty_score":0.007471979,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0109584036066556,"score_gpt":0.2789709248372004,"score_spread":0.2680125212305448,"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."}}