{"id":"W2955270041","doi":"10.1016/j.jhydrol.2019.06.075","title":"Using bootstrap ELM and LSSVM models to estimate river ice thickness in the Mackenzie River Basin in the Northwest Territories, Canada","year":2019,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Climate change and permafrost","field":"Earth and Planetary Sciences","cited_by":59,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mean squared error; Drainage basin; Coefficient of determination; Mean absolute percentage error; Statistics; Mean absolute error; Extreme learning machine; Correlation coefficient; Snow; Environmental science; Hydrology (agriculture); Climatology; Mathematics; Geology; Meteorology; Geography; Artificial neural network; Computer science; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069288,0.0001080285,0.0002129445,0.00009065179,0.000071039,0.00003902796,0.0003346723,0.00006307836,0.0001781409],"category_scores_gemma":[0.00001240343,0.00006076959,0.00002585525,0.0001676446,0.00007381518,0.0002198685,0.00001385047,0.0003219611,0.000003435519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000147093,"about_ca_system_score_gemma":0.0001505584,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.8556746,"about_ca_topic_score_gemma":0.9896516,"domain_scores_codex":[0.9988923,0.0002069076,0.0002708626,0.0001166757,0.0002436363,0.0002696333],"domain_scores_gemma":[0.9993528,0.0003139301,0.0001168441,0.0001265657,0.00003070763,0.00005920088],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00009114787,0.00001164947,0.9630518,0.00001113813,0.000005933942,0.0003433302,0.005702557,0.03016705,0.00002766041,0.00001685634,0.0002474356,0.0003234291],"study_design_scores_gemma":[0.000459916,0.0001760073,0.9634678,0.00002947646,0.00001912385,0.001198652,0.0008722257,0.02795119,0.000003897822,0.0008027463,0.004907369,0.0001116463],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9957923,0.0003316649,0.000006329514,0.002769866,0.0004332955,0.0001204543,0.0003063437,0.000001012534,0.000238723],"genre_scores_gemma":[0.9965753,0.00006037903,0.0000788686,0.003078499,0.0001503773,2.940293e-7,0.00004867313,0.000002562917,0.00000503581],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.133977,"threshold_uncertainty_score":0.2478112,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0487281476295134,"score_gpt":0.2706032406568089,"score_spread":0.2218750930272955,"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."}}