{"id":"W4213159249","doi":"10.1016/j.jhazmat.2022.128491","title":"Application of machine learning methods for rapid fluorescence-based detection of naphthenic acids and phenol in natural surface waters","year":2022,"lang":"en","type":"article","venue":"Journal of Hazardous Materials","topic":"Petroleum Processing and Analysis","field":"Chemistry","cited_by":38,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Phenol; Naphthenic acid; Tailings; Convolutional neural network; Fluorescence; Oil sands; Environmental science; Chemistry; Surface water; Artificial intelligence; Environmental chemistry; Computer science; Environmental engineering; Organic chemistry; Materials science","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":[],"consensus_categories":[],"category_scores_codex":[0.001493008,0.00009803077,0.0004301881,0.0001412221,0.00008159225,0.00001983858,0.0001410191,0.00004252944,0.00005339349],"category_scores_gemma":[0.0001216679,0.00008325258,0.0001003238,0.0001257967,0.00003683388,0.00006460558,0.0000323624,0.0001613509,6.39001e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006855975,"about_ca_system_score_gemma":0.00004731166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005040693,"about_ca_topic_score_gemma":0.0000010929,"domain_scores_codex":[0.9987926,0.000177735,0.0006180499,0.0001146702,0.0001770425,0.0001198851],"domain_scores_gemma":[0.9987342,0.0001176438,0.0009253666,0.00008841774,0.0001079982,0.00002635877],"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":[0.0006618759,0.00004776298,0.0007307905,0.0002900711,0.00005657029,9.882161e-7,0.0001622873,0.002717876,0.9536031,8.876561e-7,7.582193e-7,0.041727],"study_design_scores_gemma":[0.001024485,0.0001284396,0.0001011573,0.00005004336,0.00008897138,0.00002572303,0.0002249726,0.01180285,0.9860486,0.00005215516,0.0003751841,0.00007737337],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9925838,0.0008960954,0.006320767,0.0000594593,0.00008150181,0.0000199804,0.00002114086,0.000007609595,0.000009650669],"genre_scores_gemma":[0.991009,0.00003683751,0.008826988,0.000005556866,0.00003619549,0.00000567803,0.00001096575,0.0000140997,0.00005470331],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04164962,"threshold_uncertainty_score":0.3394941,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009021813661369208,"score_gpt":0.2734539518774898,"score_spread":0.2644321382161205,"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."}}