{"id":"W4392760103","doi":"10.5194/egusphere-egu24-14815","title":"Quantifying the Effect of Additional Training Data When Using Machine Learning to Predict Streamflow in Ungauged Basins","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Streamflow; Training (meteorology); Artificial intelligence; Machine learning; Computer science; Geography; Drainage basin; Meteorology; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001979992,0.0003827914,0.0005613404,0.0004371256,0.0000542171,0.0001131514,0.000714429,0.0002276486,0.0005370225],"category_scores_gemma":[0.000877248,0.0002929827,0.0001204198,0.0003322215,0.00002309323,0.00008412608,0.001004866,0.001685899,0.000007712636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000118353,"about_ca_system_score_gemma":0.0000664664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001976483,"about_ca_topic_score_gemma":0.0002138162,"domain_scores_codex":[0.9979064,0.0003328079,0.0005760141,0.0004786773,0.0003841298,0.0003219931],"domain_scores_gemma":[0.9973673,0.001638525,0.00005468403,0.0008241592,0.00002792314,0.00008746515],"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":[0.00001526428,0.000003331502,0.001006489,0.0009063979,0.0001349763,0.000008119516,0.0007137855,0.9925614,0.0005898799,0.00002244621,0.0004010263,0.003636887],"study_design_scores_gemma":[0.0002431558,0.00003466658,0.0003749308,0.001278363,0.00006564555,0.000004801838,0.00006577169,0.9950748,0.0005061823,0.0001016172,0.001987441,0.0002626369],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8438455,0.001291409,0.1452876,0.0001031178,0.001362261,0.0008653594,0.005047165,0.0008558208,0.001341759],"genre_scores_gemma":[0.9094508,0.00002548735,0.08778204,0.000005859429,0.0002691518,0.00004785349,0.002183581,0.0001284127,0.0001067613],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06560536,"threshold_uncertainty_score":0.9999523,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1034141868070107,"score_gpt":0.3439858036957439,"score_spread":0.2405716168887332,"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."}}