{"id":"W4389333596","doi":"10.1016/j.jwpe.2023.104633","title":"Single and ensemble explainable machine learning-based prediction of membrane flux in the reverse osmosis process","year":2023,"lang":"en","type":"article","venue":"Journal of Water Process Engineering","topic":"Membrane Separation Technologies","field":"Environmental Science","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia, Okanagan Campus","funders":"Qatar National Research Fund; Fonds National de la Recherche Luxembourg","keywords":"Reverse osmosis; Machine learning; Artificial intelligence; Ensemble forecasting; Ensemble learning; Desalination; Computer science; Boosting (machine learning); Process (computing); Process engineering; Engineering; Membrane; Chemistry","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":[0.0006608861,0.00009497282,0.0001537392,0.0001750199,0.00004416046,0.00002155661,0.0001946275,0.00005127058,0.00004931328],"category_scores_gemma":[0.0001488314,0.00005979642,0.00002645957,0.0004140869,0.00003614338,0.0003373085,0.00003152797,0.0002181606,0.000006396026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003849652,"about_ca_system_score_gemma":0.000006947505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001075706,"about_ca_topic_score_gemma":0.000003499392,"domain_scores_codex":[0.9990875,0.00002193451,0.0003075616,0.000102978,0.0003046858,0.0001754016],"domain_scores_gemma":[0.9997128,0.00004290833,0.0001127582,0.00008135758,0.00002432621,0.0000258014],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002114684,0.00003547994,0.004819783,0.0002132865,0.000006091499,0.00001648651,0.002188366,0.7584994,0.2338842,0.000001133966,0.00005152279,0.0002631366],"study_design_scores_gemma":[0.000450113,0.0002071338,0.001820256,0.00009541411,0.00001395099,0.00004202164,0.0008271305,0.108532,0.887229,0.00007394357,0.0006253686,0.00008359172],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9985591,0.00003675064,0.0007704622,0.0003363454,0.00004021806,0.0001013082,0.000001189737,0.00005141147,0.0001031852],"genre_scores_gemma":[0.999617,0.00002258538,0.0002145652,0.00001379774,0.00001344864,0.000009802615,0.00000338333,0.00001112446,0.00009422532],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6533449,"threshold_uncertainty_score":0.2438427,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01327406019135729,"score_gpt":0.2132485228341595,"score_spread":0.1999744626428022,"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."}}