{"id":"W4408435373","doi":"10.5194/egusphere-egu25-7468","title":"Empirical Evidence of the Importance of Data Recency in LSTM-Based Rainfall-Runoff Modeling ","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Context (archaeology); Surface runoff; Computer science; Streamflow; Convergence (economics); Hydrological modelling; Range (aeronautics); Environmental science; Scale (ratio); Climatology; Geography; Drainage basin; Cartography","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":[0.009600285,0.001045918,0.0004191767,0.001134053,0.0005885905,0.001897696,0.001468679,0.00212587,0.006777338],"category_scores_gemma":[0.05079227,0.0007392883,0.0007886498,0.001933356,0.002258806,0.005001141,0.00175436,0.003342221,0.001548006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001284928,"about_ca_system_score_gemma":0.0008594958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01068789,"about_ca_topic_score_gemma":0.01287197,"domain_scores_codex":[0.9978241,0.0004386598,0.0001957942,0.0008561485,0.0005729816,0.0001123882],"domain_scores_gemma":[0.903808,0.07694162,0.006759209,0.00480472,0.006906571,0.0007798934],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001605066,0.0007280087,0.2781619,0.003518108,0.000977763,0.0007681795,0.001353545,0.09309374,0.01286181,0.02982441,0.01712794,0.5599795],"study_design_scores_gemma":[0.0001868187,0.001010076,0.492536,0.00226732,0.0007314619,0.001325466,0.001801782,0.305069,0.02231072,0.1062366,0.06624886,0.000275927],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6914501,0.03873742,0.1756909,0.02646825,0.001007667,0.0002071081,0.00606724,0.0008582012,0.05951311],"genre_scores_gemma":[0.9569434,0.008590431,0.02532777,0.002197356,0.000623479,0.00008279553,0.00273676,0.0002160352,0.003281946],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01068789,"threshold_uncertainty_score":0.05077177,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1788848221231224,"score_gpt":0.3657689902683189,"score_spread":0.1868841681451965,"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."}}