{"id":"W4392833544","doi":"10.5194/egusphere-egu24-13400","title":"Interpolation vs. Extrapolation in Flood Forecasting: Exploring the Predictive Capability of Conceptual and Machine Learning Tools in Non-Stationary Scenarios","year":2024,"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 Manitoba","funders":"","keywords":"Flood forecasting; Computer science; Streamflow; Extrapolation; Hydrological modelling; Flood myth; Storm; Data assimilation; Hindcast; Benchmark (surveying); Meteorology; Climatology; Machine learning; Environmental science; Drainage basin; Geology; Mathematics; Statistics; Cartography; 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":[0.00373763,0.0005767401,0.0003631058,0.0009508111,0.0002919766,0.0006164391,0.0007629475,0.0008191008,0.0005047539],"category_scores_gemma":[0.0114528,0.0002391563,0.0004941918,0.001065406,0.0008432347,0.002009946,0.0007841229,0.001124901,0.00008212793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006166767,"about_ca_system_score_gemma":0.0005049485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005153699,"about_ca_topic_score_gemma":0.003151036,"domain_scores_codex":[0.9994493,0.0003399944,0.00002904965,0.00007852117,0.00006469294,0.00003841493],"domain_scores_gemma":[0.9917458,0.00726941,0.000327181,0.0003449807,0.0002417364,0.00007092128],"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":[0.00016771,0.0001246604,0.008936061,0.00007903964,0.00003497369,0.00004544881,0.00008130829,0.9577537,0.0006935188,0.004437115,0.0001478784,0.02749871],"study_design_scores_gemma":[0.000007390238,0.00006604151,0.0009662981,0.000007643737,0.000005047068,0.000005793383,0.00002090312,0.9957689,0.0006784931,0.002384499,0.00008311465,0.000005893647],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8598001,0.0009017516,0.135275,0.0007039988,0.00005005507,0.00008290423,0.0002743983,0.000305439,0.002606411],"genre_scores_gemma":[0.984979,0.0001993815,0.01457777,0.00002338653,0.00001397386,0.00002164991,0.00009520411,0.00000955827,0.00008011732],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005153699,"threshold_uncertainty_score":0.01976669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05614548094519204,"score_gpt":0.247388339693573,"score_spread":0.191242858748381,"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."}}