{"id":"W4362607122","doi":"10.21203/rs.3.rs-2770415/v1","title":"Ensemble learning of decomposition-based machine learning and deep learning models for multi-time step ahead streamflow forecasting in an arid region","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Deep belief network; Artificial intelligence; Streamflow; Computer science; Ensemble forecasting; Hilbert–Huang transform; Machine learning; Deep learning; Ensemble learning; Noise (video); White noise; Geography","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002705075,0.0002995371,0.0004837109,0.000466433,0.0007988526,0.00007375383,0.0002956046,0.0002761038,0.00004482023],"category_scores_gemma":[0.0005420534,0.0003061231,0.0001045324,0.0003213091,0.0003177581,0.0002099904,0.001399494,0.001776296,0.0000239808],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002389326,"about_ca_system_score_gemma":0.00002271873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001789926,"about_ca_topic_score_gemma":0.001688999,"domain_scores_codex":[0.9962899,0.001058005,0.0004260308,0.0009067372,0.0005225961,0.0007967257],"domain_scores_gemma":[0.9984289,0.0009309535,0.0002049756,0.0002356676,0.00007253826,0.0001269414],"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":[0.0001886813,0.0001005952,0.2375448,0.0005249233,0.00003213067,0.00003343834,0.001190886,0.7502493,0.0003616912,0.00001260399,0.00001273509,0.00974824],"study_design_scores_gemma":[0.0009013919,0.000639968,0.008247979,0.0004712102,0.00002150664,0.000001328255,0.0006895495,0.987743,0.0001577845,0.0007482116,0.0001157904,0.0002623202],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9028513,0.0003078364,0.09390313,0.0003409765,0.00005251456,0.001867387,0.00001261128,0.0001814552,0.0004828341],"genre_scores_gemma":[0.9907361,0.0002439554,0.007257696,0.000008094343,0.00003205682,0.0003357851,0.0003317045,0.00006694914,0.0009876388],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2374936,"threshold_uncertainty_score":0.9999391,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1241298736235243,"score_gpt":0.3665813308912837,"score_spread":0.2424514572677594,"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."}}