{"id":"W3042922613","doi":"10.5194/egusphere-egu2020-4233","title":"Using a boundary-corrected wavelet transform coupled with machine learning and hybrid deep learning approaches for multi-step water level forecasting in Lakes Michigan and Ontario","year":2020,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; McGill University","funders":"","keywords":"Artificial intelligence; Discrete wavelet transform; Support vector machine; Wavelet; Convolutional neural network; Computer science; Deep learning; Machine learning; Wavelet transform","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004232732,0.0003104158,0.0003701353,0.00004633055,0.0004917627,0.0001329234,0.0001011874,0.00008429792,0.0001793718],"category_scores_gemma":[0.0001228897,0.0002132162,0.00003960107,0.000136469,0.0002668269,0.0002356672,0.0001365367,0.0005571565,0.000003243992],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001089118,"about_ca_system_score_gemma":0.00001601013,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01008105,"about_ca_topic_score_gemma":0.1531592,"domain_scores_codex":[0.9981812,0.00007045952,0.0003188442,0.0006455846,0.0001908469,0.000593028],"domain_scores_gemma":[0.9995583,0.0001038618,0.00007687099,0.00006133878,0.000009176943,0.0001904147],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001120936,0.0001736961,0.583922,0.0001847098,0.00008196571,0.00009717218,0.04235788,0.2879892,0.01986557,0.000006707338,0.000002212794,0.06419799],"study_design_scores_gemma":[0.001853216,0.0004732724,0.003992709,0.00003696241,0.00003446212,0.0001237795,0.000318976,0.9911997,0.001043843,0.00001991329,0.0005457188,0.0003574089],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9079143,0.00002558454,0.09099176,0.0002033663,0.00001490586,0.0004966621,0.000003256007,0.00009670094,0.0002534573],"genre_scores_gemma":[0.9039667,0.000002033635,0.09549464,0.0001327475,0.00001530698,0.00001777064,0.00003881722,0.00004126259,0.0002906907],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7032106,"threshold_uncertainty_score":0.9965109,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1196018800088413,"score_gpt":0.2415624210213082,"score_spread":0.1219605410124669,"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."}}