{"id":"W4411868158","doi":"10.2139/ssrn.5335437","title":"How Much Historical Data Do We Need? The Role of Data Recency and Training Period Length in Lstm-Based Rainfall-Runoff Modeling","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Period (music); Training (meteorology); Surface runoff; Computer science; Meteorology; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007868115,0.0006590261,0.001483765,0.0005936103,0.0006050273,0.002970887,0.00184088,0.002069204,0.004466039],"category_scores_gemma":[0.06831352,0.0009048273,0.0004405632,0.001600816,0.00139164,0.01977985,0.00163833,0.003436111,0.001235667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008950321,"about_ca_system_score_gemma":0.001718071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009215659,"about_ca_topic_score_gemma":0.01280643,"domain_scores_codex":[0.9985904,0.0006205493,0.0001503576,0.0003541179,0.0001753308,0.0001091592],"domain_scores_gemma":[0.9753028,0.01811463,0.001454259,0.002418316,0.001977842,0.0007321644],"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":[0.001187168,0.0004028319,0.07878805,0.002344738,0.0005527657,0.0003745136,0.0007729701,0.2387934,0.007563183,0.01807288,0.0229165,0.628231],"study_design_scores_gemma":[0.0002363748,0.0003171897,0.0411677,0.001841106,0.0004936947,0.000383574,0.001351719,0.8035872,0.009027174,0.1100426,0.0313035,0.000248168],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.43928,0.03348915,0.3961903,0.1063677,0.002397861,0.0001482934,0.00915991,0.00165264,0.01131421],"genre_scores_gemma":[0.8825095,0.01161467,0.09436961,0.004111693,0.001740843,0.0001353195,0.003060923,0.0008358263,0.001621703],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009215659,"threshold_uncertainty_score":0.04161108,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03944593123635301,"score_gpt":0.258421134032215,"score_spread":0.218975202795862,"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."}}