{"id":"W4389430802","doi":"10.1080/02626667.2023.2273402","title":"Comparing three machine learning algorithms with existing methods for natural streamflow estimation","year":2023,"lang":"en","type":"article","venue":"Hydrological Sciences Journal","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Power Generation; Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Streamflow; Computer science; Estimation; Natural (archaeology); Algorithm; Machine learning; Artificial intelligence; Engineering; Geology; Geography; Cartography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007101745,0.001277772,0.00110118,0.003940358,0.0006041215,0.001119408,0.00114587,0.001144528,0.0007807863],"category_scores_gemma":[0.01207036,0.0001965697,0.001136966,0.001935984,0.0004280201,0.001591488,0.0008220902,0.0009638173,0.0002472581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009768077,"about_ca_system_score_gemma":0.001300306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008722872,"about_ca_topic_score_gemma":0.008963626,"domain_scores_codex":[0.9968201,0.001131214,0.0003774987,0.0005806339,0.0008958734,0.0001946381],"domain_scores_gemma":[0.9920567,0.005182568,0.0003600891,0.0006697815,0.001606378,0.0001245223],"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":[0.0005199597,0.0005447782,0.03793117,0.0003353051,0.001080776,0.00007311958,0.00009537181,0.3979645,0.002024158,0.002204237,0.001646496,0.5555801],"study_design_scores_gemma":[0.0000371508,0.0001876204,0.006754791,0.00002485487,0.00009311998,0.00003986061,0.00005837901,0.9889759,0.001941293,0.001098062,0.000771453,0.00001755306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3806503,0.005515047,0.6048169,0.0006651871,0.000327119,0.0002736357,0.0007069423,0.002459028,0.004585873],"genre_scores_gemma":[0.7214835,0.001078401,0.2746033,0.0001694305,0.0001409491,0.0002060956,0.001257814,0.00009586738,0.0009646641],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008722872,"threshold_uncertainty_score":0.03755808,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08181002430665128,"score_gpt":0.3516079070020364,"score_spread":0.2697978826953851,"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."}}