{"id":"W4388976461","doi":"10.1007/s11356-023-30774-4","title":"Forecasting water quality variable using deep learning and weighted averaging ensemble models","year":2023,"lang":"en","type":"article","venue":"Environmental Science and Pollution Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":45,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec en Abitibi-Témiscamingue","funders":"","keywords":"Computer science; Recurrent neural network; Artificial intelligence; Convolutional neural network; Ensemble forecasting; Water quality; Artificial neural network; Genetic algorithm; Deep learning; Machine learning; Predictive modelling; Ecology; Biology","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.007203114,0.0001431629,0.0001402403,0.0001880195,0.002648947,0.0001817009,0.0002155364,0.00008021399,0.000557612],"category_scores_gemma":[0.000174104,0.0001112399,0.00001912573,0.0009733802,0.002189203,0.0007069159,0.00132684,0.0004018932,0.000194935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004540247,"about_ca_system_score_gemma":0.00001603346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006339842,"about_ca_topic_score_gemma":0.000009165026,"domain_scores_codex":[0.9963989,0.0002954229,0.0002279351,0.0006813617,0.001319569,0.00107684],"domain_scores_gemma":[0.999409,0.0001054322,0.00003988243,0.0001511917,0.000009016619,0.000285496],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000250657,0.00004159412,0.02068751,0.00001217027,0.000004522192,0.00001684865,0.001882896,0.09554172,0.8445765,0.0001674208,0.00003335241,0.03701036],"study_design_scores_gemma":[0.0001918711,0.00007611101,0.005800919,0.00001493777,0.000003409375,0.00003283462,0.0003611367,0.9800485,0.007340898,0.004649208,0.001291028,0.0001891425],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9943569,0.00003344647,0.001041245,0.0002454155,0.00004569821,0.0001838332,0.000002539021,0.00006623896,0.004024626],"genre_scores_gemma":[0.9971323,0.00005725431,0.002020658,0.00007526192,0.00002919641,0.000008679588,0.000005237999,0.00001313077,0.0006583089],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8845068,"threshold_uncertainty_score":0.9986495,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1166973988005425,"score_gpt":0.3441548242888416,"score_spread":0.2274574254882991,"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."}}