{"id":"W2344030229","doi":"10.1016/j.chemosphere.2016.04.061","title":"Combining parallel factor analysis and machine learning for the classification of dissolved organic matter according to source using fluorescence signatures","year":2016,"lang":"en","type":"article","venue":"Chemosphere","topic":"Water Quality Monitoring and Analysis","field":"Environmental Science","cited_by":39,"is_retracted":false,"has_abstract":false,"ca_institutions":"Trent University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Support vector machine; Leachate; Dissolved organic carbon; Artificial intelligence; Colored dissolved organic matter; Random forest; Fractionation; Multilayer perceptron; Environmental science; Pattern recognition (psychology); Environmental chemistry; Computer science; Chemistry; Artificial neural network; Chromatography","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":[0.0001824065,0.0001071465,0.0001818955,0.00001412596,0.00019552,0.00003699205,0.0001815274,0.00004463815,0.0003202048],"category_scores_gemma":[0.00008078372,0.00006168948,0.00008548801,0.0003342199,0.00007589267,0.00008810087,0.0001153185,0.00006729,0.00001225072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005349898,"about_ca_system_score_gemma":0.000002825237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000246783,"about_ca_topic_score_gemma":0.00002076064,"domain_scores_codex":[0.9991987,0.00003907044,0.000182801,0.0002576204,0.0001520418,0.0001697942],"domain_scores_gemma":[0.9993911,0.0002179766,0.0001194416,0.0002014465,0.00001318041,0.00005685837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00001032408,0.000007553049,0.458147,0.000005967402,0.00006635931,4.840802e-8,0.0003088927,0.001505333,0.5353745,8.226359e-7,0.00001402458,0.004559217],"study_design_scores_gemma":[0.0004095068,0.00003630541,0.6841894,0.00006529489,0.0005638621,5.829483e-7,0.00144789,0.06008207,0.2524469,0.00004941643,0.0003954598,0.000313349],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8674244,0.00003475189,0.1319373,0.0004692734,0.00001618097,0.00008600461,0.000004060506,0.00001556518,0.00001236627],"genre_scores_gemma":[0.9961944,0.000005944019,0.003081163,0.00002187367,0.00002326853,0.000006833275,0.000002738964,0.00001261399,0.0006512054],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2829276,"threshold_uncertainty_score":0.3506018,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03073987588059009,"score_gpt":0.2584529909392067,"score_spread":0.2277131150586166,"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."}}