{"id":"W4386575378","doi":"10.1016/j.jhydrol.2023.130138","title":"Bayesian extreme learning machines for hydrological prediction uncertainty","year":2023,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":22,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Ministry of Colleges and Universities; University of Waterloo","keywords":"Computer science; Extreme learning machine; Probabilistic logic; Streamflow; Monte Carlo method; Multilayer perceptron; Perceptron; Machine learning; Dropout (neural networks); Artificial intelligence; Artificial neural network; Evapotranspiration; Statistics; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.001528933,0.0001553145,0.0003283956,0.0001240483,0.0002243916,0.00001760411,0.0002971782,0.0002047907,0.0008750898],"category_scores_gemma":[0.000987826,0.0001131224,0.0001895282,0.0003386781,0.0002392574,0.0001276926,0.0001340693,0.000464198,0.0001541893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009738865,"about_ca_system_score_gemma":0.00001285995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001986165,"about_ca_topic_score_gemma":0.00001288947,"domain_scores_codex":[0.9982612,0.0002156909,0.0005282364,0.0002525849,0.0002819963,0.0004602787],"domain_scores_gemma":[0.9989474,0.0004041964,0.0003586109,0.0001176952,0.00002368216,0.0001483452],"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":[0.0002449087,0.00005927908,0.04549221,0.000005168253,0.00002792192,0.00008481096,0.0001319629,0.9308286,0.01095986,0.00005017285,0.004430971,0.007684188],"study_design_scores_gemma":[0.0008479755,0.002372141,0.01160311,0.000009878358,0.00004751332,0.000507824,0.00000770282,0.9232177,0.0001074885,0.02352958,0.03760386,0.0001452846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9898298,0.00002184662,0.005286804,0.00253121,0.0004811666,0.000127183,0.000004174426,0.0001178877,0.00159988],"genre_scores_gemma":[0.997242,0.0000161837,0.001569531,0.0003885872,0.0003057345,0.000008248059,0.000008664227,0.00001765152,0.0004434015],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03388909,"threshold_uncertainty_score":0.958162,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03409063600264407,"score_gpt":0.2652666191260667,"score_spread":0.2311759831234226,"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."}}