{"id":"W4283575529","doi":"10.3389/frwa.2022.934709","title":"Interpreting Deep Machine Learning for Streamflow Modeling Across Glacial, Nival, and Pluvial Regimes in Southwestern Canada","year":2022,"lang":"en","type":"article","venue":"Frontiers in Water","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Streamflow; Flood forecasting; Precipitation; Pluvial; Climatology; Glacier; Environmental science; Climate change; Drainage basin; Geology; Meteorology; Geography; Geomorphology; Cartography; Oceanography","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003896137,0.0001218205,0.000173036,0.00004257936,0.0003843354,0.00001753947,0.0001493605,0.00002784956,0.00007044932],"category_scores_gemma":[0.00001503707,0.0001048028,0.00002135028,0.00005377474,0.00007095364,0.0001070022,0.0006582369,0.0002138824,0.000001316046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002504902,"about_ca_system_score_gemma":0.000004599548,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1032722,"about_ca_topic_score_gemma":0.2761838,"domain_scores_codex":[0.9988785,0.00008152602,0.0001833589,0.0003058611,0.0001238773,0.0004268828],"domain_scores_gemma":[0.9998475,0.00001510848,0.00002744746,0.00008020928,0.000001617899,0.00002815726],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001206309,0.00001294979,0.6561053,0.000009266957,0.00001399505,0.00001913998,0.009249476,0.3323069,0.00002944441,7.815964e-7,0.0005555149,0.001576606],"study_design_scores_gemma":[0.001150686,0.00008105274,0.002579626,0.00001082148,0.00001194519,0.000002518734,0.007426087,0.9774189,0.00009625235,0.0007181641,0.01022357,0.000280366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9935708,0.0000949178,0.004834656,0.0006184522,0.0004024053,0.0002118493,0.000005995769,0.0000142095,0.0002467047],"genre_scores_gemma":[0.998269,0.00001348732,0.0007217403,0.0002312413,0.00001510546,0.00007353893,0.00002287239,0.00001343631,0.0006395907],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6535257,"threshold_uncertainty_score":0.9026992,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005888411655057092,"score_gpt":0.2016918177831335,"score_spread":0.1958034061280764,"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."}}