{"id":"W4396897549","doi":"10.5194/hess-28-2107-2024","title":"Enhancing long short-term memory (LSTM)-based streamflow prediction with a spatially distributed approach","year":2024,"lang":"en","type":"article","venue":"Hydrology and earth system sciences","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Power Generation; University of Waterloo","funders":"Global Water Futures; Canada First Research Excellence Fund; Environment and Climate Change Canada","keywords":"Streamflow; Long short term memory; Term (time); Computer science; Artificial intelligence; Artificial neural network; Recurrent neural network; Cartography; Geography","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000804228,0.0001799907,0.0002043357,0.00008718074,0.0006402914,0.00008320583,0.0001668717,0.00009683465,0.00006084325],"category_scores_gemma":[0.000005596316,0.000121975,0.00003365411,0.0003231218,0.001095276,0.0003143118,0.0001060412,0.0001306592,0.00006033646],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002577119,"about_ca_system_score_gemma":0.00001921491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001179411,"about_ca_topic_score_gemma":0.0004763869,"domain_scores_codex":[0.9983879,0.0001266943,0.0002106995,0.0006356006,0.0002484755,0.0003906641],"domain_scores_gemma":[0.9996697,0.00007137149,0.00003775601,0.0001405104,0.000004734125,0.00007587543],"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":[0.0001311829,0.0001067618,0.8467662,0.0006180824,0.000183196,0.0002945072,0.001441479,0.1457068,0.001130845,0.0005782841,0.0002998059,0.00274282],"study_design_scores_gemma":[0.0006260758,0.001372895,0.2066262,0.0003208507,0.0002547105,0.0002886988,0.0008557969,0.786405,0.002075717,0.00008030726,0.0005241796,0.000569642],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.959685,0.0002945896,0.03033217,0.0003611643,0.0002575457,0.0003079736,0.00001521054,0.0002162791,0.008530113],"genre_scores_gemma":[0.9991975,0.00001361471,0.0004622999,0.00007147015,0.00005050213,0.00005039124,0.00002176473,0.000006356366,0.0001260995],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6406982,"threshold_uncertainty_score":0.4973997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009328611598780163,"score_gpt":0.2017187926356492,"score_spread":0.1923901810368691,"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."}}