{"id":"W4367693472","doi":"10.1016/j.eti.2023.103179","title":"Tracking the sources of dissolved organic matter under bio- and photo-transformation conditions using fluorescence spectrum-based machine learning techniques","year":2023,"lang":"en","type":"article","venue":"Environmental Technology & Innovation","topic":"Water Quality Monitoring and Analysis","field":"Environmental Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Trent University","funders":"Korea Institute of Marine Science and Technology promotion; Korea Environmental Industry and Technology Institute; Ministry of Oceans and Fisheries; Ministry of Environment","keywords":"Dissolved organic carbon; Compost; Colored dissolved organic matter; Mixing (physics); Transformation (genetics); Support vector machine; Biogeochemical cycle; Environmental science; Chemistry; Biological system; Environmental chemistry; Machine learning; Computer science; Ecology","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":[0.0009733114,0.000485596,0.0003510707,0.0005339361,0.0001672255,0.0004891507,0.0004089444,0.0005038365,0.0002863347],"category_scores_gemma":[0.001502803,0.0001785743,0.0005046737,0.0004883542,0.0002400381,0.0007835873,0.0003670062,0.0006373409,0.0001401304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004029306,"about_ca_system_score_gemma":0.0003863056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001304049,"about_ca_topic_score_gemma":0.001817976,"domain_scores_codex":[0.9997109,0.0000645527,0.00001769194,0.0001060539,0.00007843714,0.00002239942],"domain_scores_gemma":[0.9994503,0.000282419,0.0001092072,0.00003366121,0.0001095529,0.00001474082],"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":[0.0003777031,0.0003734327,0.02804188,0.0002938176,0.0001263781,0.000121026,0.0002053826,0.287203,0.458966,0.00218356,0.0003994157,0.2217083],"study_design_scores_gemma":[0.000004765127,0.00008756311,0.003455935,0.000007010666,0.00001429558,0.00002456142,0.0000263175,0.9128861,0.082373,0.0007406787,0.0003602664,0.00001942345],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4893231,0.0004475638,0.5080448,0.0001584984,0.0000231602,0.00004800461,0.0002514914,0.0006795217,0.001023698],"genre_scores_gemma":[0.8051953,0.000257834,0.1935825,0.00004815345,0.000009805552,0.000061797,0.0002110528,0.00003658587,0.0005970389],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001304049,"threshold_uncertainty_score":0.005147457,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01552628938658035,"score_gpt":0.2464717783748141,"score_spread":0.2309454889882337,"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."}}