{"id":"W4285098376","doi":"10.1016/j.memsci.2022.120817","title":"Membrane fouling prediction and uncertainty analysis using machine learning: A wastewater treatment plant case study","year":2022,"lang":"en","type":"article","venue":"Journal of Membrane Science","topic":"Membrane Separation Technologies","field":"Environmental Science","cited_by":111,"is_retracted":false,"has_abstract":false,"ca_institutions":"Suez (Canada); McMaster University","funders":"","keywords":"Membrane fouling; Mean squared error; Random forest; Fouling; Artificial neural network; Ultrafiltration (renal); Hyperparameter; Computer science; Environmental science; Artificial intelligence; Machine learning; Process engineering; Engineering; Membrane; Mathematics; Statistics; Chemistry; Chromatography","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002520712,0.0001920074,0.0003876923,0.0006539082,0.001263634,0.0001081712,0.000414457,0.00002992637,0.0006530641],"category_scores_gemma":[0.0001232668,0.0001436032,0.0001134133,0.002112309,0.0003987422,0.0005732496,0.0004082942,0.0003550239,0.00000259148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006960855,"about_ca_system_score_gemma":0.00007806494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001568039,"about_ca_topic_score_gemma":0.0003036213,"domain_scores_codex":[0.9972301,0.0002416263,0.0005901604,0.0004212431,0.001189557,0.0003273673],"domain_scores_gemma":[0.9989167,0.00009388815,0.0005158762,0.0002779754,0.00003069696,0.0001648071],"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":[0.00008764985,0.0002737526,0.05550171,0.000004125481,0.0001161745,0.001372628,0.003416133,0.7631426,0.1754254,0.000002670007,0.000002349755,0.0006547486],"study_design_scores_gemma":[0.002090795,0.003329227,0.002558444,0.000008682697,0.0009541976,0.01833217,0.02698248,0.884926,0.05981401,0.00001981539,0.0006508809,0.0003332715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9991704,0.00005211225,0.00007454196,0.0001291013,0.0001690307,0.0002719183,0.00001705523,0.00003822992,0.0000776655],"genre_scores_gemma":[0.9988953,0.00004246538,0.0008834532,0.00001943742,0.00002336095,0.000008390252,0.000002259505,0.000008771442,0.000116592],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1217834,"threshold_uncertainty_score":0.9718982,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02894644718359843,"score_gpt":0.2750552278110729,"score_spread":0.2461087806274745,"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."}}