{"id":"W4234974331","doi":"10.5194/hess-2020-540","title":"Rainfall–Runoff Prediction at Multiple Timescales with a SingleLong Short-Term Memory Network","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":95,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Global Water Futures; Horizon 2020 Framework Programme; Österreichische Forschungsförderungsgesellschaft; Bundesministerium für Bildung, Wissenschaft und Forschung; Google; Compute Canada; Janssen Pharmaceuticals; Canada First Research Excellence Fund; Nvidia","keywords":"Benchmark (surveying); Computer science; Temporal resolution; Process (computing); Term (time); Deep learning; Flood myth; Artificial intelligence; Machine learning; Geology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004704512,0.0006185922,0.0003766393,0.0003018855,0.0002369123,0.0005435047,0.0006606646,0.0006570165,0.001299996],"category_scores_gemma":[0.001364947,0.000274656,0.0003614213,0.0004058277,0.000258421,0.001232458,0.0004724471,0.000909809,0.0002263202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006307984,"about_ca_system_score_gemma":0.0008170825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01649931,"about_ca_topic_score_gemma":0.01939403,"domain_scores_codex":[0.9998674,0.00002210614,0.000006771369,0.00005837588,0.00002184101,0.00002339546],"domain_scores_gemma":[0.9996859,0.0001406059,0.00004412383,0.0000329945,0.00007434122,0.00002203768],"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":[0.0001516269,0.0000819114,0.004419103,0.00002402284,0.00005988469,0.00005115872,0.00002811063,0.9342024,0.002321615,0.0008805906,0.0014799,0.0562997],"study_design_scores_gemma":[0.000004569439,0.000006560706,0.0003060973,0.000001344734,0.000003436848,0.000001838191,0.000002726539,0.998755,0.0003091569,0.0005348389,0.00007285211,0.000001492864],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7495719,0.0009746678,0.2409699,0.001519334,0.0002279326,0.0000350011,0.0008934174,0.001839052,0.003968749],"genre_scores_gemma":[0.9754017,0.0001241722,0.02246143,0.00009282606,0.00003932336,0.00002409313,0.0004537274,0.00002388018,0.001378855],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01649931,"threshold_uncertainty_score":0.03280658,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01693444763136312,"score_gpt":0.2072249257976239,"score_spread":0.1902904781662608,"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."}}