{"id":"W4414947999","doi":"10.5194/hess-29-5005-2025","title":"How well do process-based and data-driven hydrological models learn from limited discharge data?","year":2025,"lang":"en","type":"article","venue":"Hydrology and earth system sciences","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of Calgary","funders":"Universität Potsdam; Deutsche Forschungsgemeinschaft","keywords":"Entropy (arrow of time); Multivariate statistics; Regression; Model selection; Predictive modelling; Training (meteorology); Regression analysis; Selection (genetic algorithm)","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":[0.008306994,0.0006896553,0.0008126221,0.001004765,0.0002231877,0.00190826,0.001057204,0.001621689,0.0006297832],"category_scores_gemma":[0.02910311,0.0005176715,0.000999216,0.0008867786,0.0008440844,0.004517502,0.0009875073,0.0009869952,0.0002833963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00110635,"about_ca_system_score_gemma":0.0007933907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005674461,"about_ca_topic_score_gemma":0.004236559,"domain_scores_codex":[0.9983626,0.000856984,0.0001053888,0.0003738864,0.0001851738,0.0001158963],"domain_scores_gemma":[0.9889332,0.007799932,0.001025605,0.001222979,0.000753326,0.0002648966],"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":[0.0001809137,0.0001054981,0.04416053,0.00009667815,0.0004202019,0.00006579185,0.0001160612,0.9290926,0.001026217,0.002156135,0.0005148721,0.02206451],"study_design_scores_gemma":[0.00001755811,0.00004759067,0.01226753,0.0000251742,0.00002903502,0.0000178527,0.00004080285,0.9819052,0.0008177152,0.004587752,0.0002190867,0.00002473084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9098557,0.000634038,0.08420954,0.001720604,0.0000697671,0.00006688016,0.0008478817,0.0003865494,0.002208925],"genre_scores_gemma":[0.9953053,0.00007589856,0.003903874,0.00009872394,0.00001464118,0.00001736241,0.000398118,0.00002701022,0.0001591029],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008306994,"threshold_uncertainty_score":0.04393214,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03847088177710778,"score_gpt":0.2613924243780638,"score_spread":0.222921542600956,"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."}}