{"id":"W4401281272","doi":"10.1016/j.jhydrol.2024.131767","title":"Two-stage meta-ensembling machine learning model for enhanced water quality forecasting","year":2024,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":28,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec en Abitibi-Témiscamingue","funders":"","keywords":"Computer science; Boosting (machine learning); Artificial intelligence; Benchmark (surveying); Machine learning; Multilayer perceptron; Gradient boosting; Hyperparameter; Genetic algorithm; Extreme learning machine; Principal component analysis; Data pre-processing; Multi-objective optimization; Preprocessor; Data mining; Artificial neural network; Random forest","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003390669,0.0002223184,0.0005915356,0.0001126537,0.0002079636,0.00006240749,0.0002870475,0.0001291195,0.0009224685],"category_scores_gemma":[0.0005294452,0.000134418,0.0004578382,0.0001292694,0.0001500055,0.000278571,0.0001810843,0.0006967342,0.0000625985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001209693,"about_ca_system_score_gemma":0.00001804602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005346596,"about_ca_topic_score_gemma":0.00004930875,"domain_scores_codex":[0.9977417,0.000237938,0.0008154252,0.0003377648,0.0003100498,0.0005571396],"domain_scores_gemma":[0.9989229,0.0005013458,0.000272475,0.00013728,0.00003128502,0.0001346839],"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":[0.0001182446,0.00002843753,0.0001342709,0.00002474285,0.0002004951,0.00005182655,0.0005912254,0.8569132,0.1395308,0.00008240533,0.00004728338,0.002277034],"study_design_scores_gemma":[0.0004147959,0.0003898711,0.00000552543,0.00001294498,0.0003205595,0.0001960641,0.000006735899,0.9770242,0.01233385,0.005513261,0.003618167,0.0001640484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8424653,0.0002842311,0.1546654,0.001003755,0.0002908742,0.0001108507,0.000005561685,0.00005811124,0.001115874],"genre_scores_gemma":[0.9820811,0.0000116159,0.01587848,0.0003990168,0.0001521414,0.000009086818,0.000004381129,0.00003408838,0.001430087],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1396158,"threshold_uncertainty_score":0.9999908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1337372837568062,"score_gpt":0.3398877619549514,"score_spread":0.2061504781981452,"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."}}