{"id":"W3005619874","doi":"10.1007/s00477-020-01776-2","title":"Short-term water quality variable prediction using a hybrid CNN–LSTM deep learning model","year":2020,"lang":"en","type":"article","venue":"Stochastic Environmental Research and Risk Assessment","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":557,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Mean squared error; Water quality; Coefficient of determination; Artificial intelligence; Correlation coefficient; Convolutional neural network; Computer science; Statistics; Machine learning; Mathematics","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":[0.00021879,0.0006148123,0.0004652228,0.0002959402,0.0002033529,0.0004208969,0.0007558384,0.0006466623,0.001619779],"category_scores_gemma":[0.0004823345,0.0003016186,0.0004859387,0.0004270102,0.0001734264,0.0007152631,0.0004500259,0.0007800481,0.0004109052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005263915,"about_ca_system_score_gemma":0.0008041426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02217775,"about_ca_topic_score_gemma":0.02431514,"domain_scores_codex":[0.9999061,0.000005452659,0.000005283905,0.00003766096,0.00002124296,0.00002431487],"domain_scores_gemma":[0.9998671,0.00002727929,0.00001449999,0.00001396264,0.00006371465,0.00001336025],"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":[0.0002929205,0.0002420941,0.005991113,0.00007448762,0.0001642515,0.0001565608,0.00003310182,0.7437562,0.02375132,0.001263434,0.004121738,0.2201527],"study_design_scores_gemma":[0.000002425996,0.000009223101,0.0003774149,0.000001474249,0.000006981856,0.000004703992,0.000001199251,0.9984339,0.0009004836,0.0001698427,0.00008941362,0.000002915157],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3611546,0.001138291,0.6236462,0.0008991421,0.0006739406,0.00006286237,0.001438143,0.00332723,0.007659596],"genre_scores_gemma":[0.9752514,0.0001957226,0.01959147,0.000129651,0.00005588989,0.00002865519,0.0006000391,0.00002997905,0.004117236],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02217775,"threshold_uncertainty_score":0.0440973,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07775161905009657,"score_gpt":0.351285002543724,"score_spread":0.2735333834936274,"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."}}