{"id":"W2467110827","doi":"10.1007/s10489-016-0815-x","title":"A hierarchical selective ensemble randomized neural network hybridized with heuristic feature selection for estimation of sea-ice thickness","year":2016,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial neural network; Radiometer; Feature (linguistics); Heuristic; Remote sensing; Feature selection; Sea ice; Brightness temperature; Brightness; Artificial intelligence; Microwave; Geology; Telecommunications; Climatology; Optics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0005993322,0.0001986826,0.0004373674,0.00005145958,0.0002097399,0.00002415914,0.000176478,0.00009371856,0.00009706354],"category_scores_gemma":[0.0002252902,0.0001160156,0.00008631564,0.0003287236,0.0003158655,0.0001266648,0.00001007447,0.0001818957,0.00001918369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001311842,"about_ca_system_score_gemma":0.0001062374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002341389,"about_ca_topic_score_gemma":0.0002655223,"domain_scores_codex":[0.9986155,0.0001080758,0.0002996171,0.000343511,0.0002574332,0.0003758766],"domain_scores_gemma":[0.9969687,0.002453957,0.0002139509,0.0001323797,0.0001421862,0.00008877074],"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":[0.1216618,0.0001107223,0.01132322,0.0002101282,0.0003365593,0.000005799537,0.001052977,0.2872399,0.000587723,0.02518719,0.0006344208,0.5516495],"study_design_scores_gemma":[0.01055034,0.0004283943,0.002284522,0.0001288269,0.0001612279,0.0001099454,0.0001164488,0.9248309,0.003542954,0.05731333,0.0001175494,0.0004155911],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1200047,0.00003688597,0.8773273,0.000339419,0.000125707,0.0009658753,0.00002689096,0.00005674913,0.001116473],"genre_scores_gemma":[0.9547617,0.00005257286,0.0447119,0.0001433354,0.0001159624,0.00003264368,0.00005356039,0.000008822467,0.0001194836],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.834757,"threshold_uncertainty_score":0.4730978,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008014361352737089,"score_gpt":0.2194283204342499,"score_spread":0.2114139590815128,"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."}}