{"id":"W3108249908","doi":"10.1016/j.rse.2020.112206","title":"Assessment of machine learning classifiers for global lake ice cover mapping from MODIS TOA reflectance data","year":2020,"lang":"en","type":"article","venue":"Remote Sensing of Environment","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":84,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo; Communitech","funders":"Natural Sciences and Engineering Research Council of Canada; European Space Agency","keywords":"Cloud cover; Environmental science; Remote sensing; Moderate-resolution imaging spectroradiometer; Solar zenith angle; Land cover; Cryosphere; Climatology; Satellite; Physical geography; Sea ice; Geology; Cloud computing; Geography; Computer science","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":[0.0001938085,0.0001350166,0.0002665107,0.00001274952,0.00009057527,0.00001131583,0.0002127991,0.00005605429,0.0001792491],"category_scores_gemma":[0.00006838061,0.0001272801,0.00005885277,0.00007146892,0.0001059719,0.00009683193,0.00006827725,0.0001387037,0.00000823477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001996975,"about_ca_system_score_gemma":0.00004148668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007736149,"about_ca_topic_score_gemma":0.0002413619,"domain_scores_codex":[0.9987648,0.00006232545,0.0003062805,0.0003585482,0.0002997408,0.0002082833],"domain_scores_gemma":[0.9991885,0.0001705299,0.0002420799,0.0002933428,0.00001001037,0.00009552499],"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":[0.0003090361,0.00005301976,0.1878781,0.0003167675,0.0004074245,0.00003366372,0.001049447,0.3202871,0.006569852,0.00007116201,0.0002725692,0.4827518],"study_design_scores_gemma":[0.0003160264,0.0001122867,0.059908,0.00004995166,0.00005027806,0.000002428482,0.0002311091,0.9301146,0.00003453425,0.0001961437,0.008859117,0.0001255202],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3361588,0.0001855412,0.6570754,0.001293142,0.0001523576,0.000269237,0.001448089,0.00002356783,0.003393836],"genre_scores_gemma":[0.8389382,0.0001757333,0.1596627,0.0002381995,0.0000612884,9.127943e-9,0.0008849215,0.000004706451,0.00003416559],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6098275,"threshold_uncertainty_score":0.5190333,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04216562124770647,"score_gpt":0.2531099171291437,"score_spread":0.2109442958814372,"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."}}