{"id":"W2748163690","doi":"10.1016/j.coldregions.2017.08.009","title":"Combining k-nearest-neighbor models for annual peak breakup flow forecasting","year":2017,"lang":"en","type":"article","venue":"Cold Regions Science and Technology","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"Alberta Environment and Protected Areas","funders":"Alberta Environment and Parks","keywords":"Breakup; Mahalanobis distance; k-nearest neighbors algorithm; Computer science; Streamflow; Standardization; Data mining; Meteorology; Artificial intelligence; Geography; Drainage basin; Cartography","routes":{"ca_aff":true,"ca_fund":true,"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":["sts"],"consensus_categories":["sts"],"category_scores_codex":[0.0005115871,0.0001256857,0.0001720626,0.0002397549,0.003338246,0.0001823705,0.0008274093,0.0001220398,0.00001254227],"category_scores_gemma":[0.0005085348,0.0001051158,0.00002923366,0.0003160485,0.002802631,0.0007980241,0.0001225077,0.0001646719,0.000006941839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009032676,"about_ca_system_score_gemma":0.0002293641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002331533,"about_ca_topic_score_gemma":0.0004309038,"domain_scores_codex":[0.9986944,0.000007032535,0.0001516543,0.0004123575,0.0002107703,0.000523758],"domain_scores_gemma":[0.9988996,0.0001208778,0.000137716,0.0004591737,0.0002611163,0.0001215034],"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":[0.00006048352,0.00006576598,0.1391229,0.00007886882,0.00003586556,0.0000786469,0.001432735,0.002566465,0.0002947769,0.32593,0.001578639,0.5287548],"study_design_scores_gemma":[0.0004632909,0.0002767168,0.006310224,0.00005405223,0.00002103846,0.000167527,0.00228032,0.9331977,0.00005891592,0.05277836,0.004144179,0.0002476973],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9162073,0.0003469882,0.0371923,0.0214428,0.001249384,0.001126928,0.0002829084,0.000398229,0.02175323],"genre_scores_gemma":[0.9882073,0.00006011674,0.01126874,0.0001263932,0.00004950184,0.000006994593,0.000005982025,0.00000389914,0.000271027],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9306312,"threshold_uncertainty_score":0.9999112,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03038166154886282,"score_gpt":0.2377829148328805,"score_spread":0.2074012532840177,"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."}}