{"id":"W2752508396","doi":"10.1109/lgrs.2017.2743339","title":"Sea Ice Classification Using Cryosat-2 Altimeter Data by Optimal Classifier–Feature Assembly","year":2017,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China; European Space Agency; National Key Research and Development Program of China; Alberta Agricultural Research Institute","keywords":"Support vector machine; Artificial intelligence; Random forest; Convolutional neural network; Naive Bayes classifier; Pattern recognition (psychology); Sea ice; Computer science; Bayesian network; k-nearest neighbors algorithm; Feature extraction; Feature (linguistics); Cross-validation; Arctic ice pack; Remote sensing; Geology; Climatology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0005713962,0.0002213098,0.0002056859,0.00006852631,0.001840678,0.0006443076,0.0007496774,0.0001255001,0.00001067275],"category_scores_gemma":[0.00009220963,0.0001819369,0.00004094339,0.0001099818,0.0008036326,0.001175194,0.00007920153,0.0003222495,0.00002351615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001264959,"about_ca_system_score_gemma":0.00006976214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005790638,"about_ca_topic_score_gemma":0.0003413869,"domain_scores_codex":[0.9980451,0.0000740387,0.0001957249,0.0007322126,0.0004081477,0.0005447569],"domain_scores_gemma":[0.9984108,0.0001013731,0.0002582884,0.0009987435,0.00004112999,0.0001896225],"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":[0.00007977898,0.00001881489,0.03279222,0.00006448669,0.00005839012,0.0001658048,0.0006225763,0.0005877468,0.155157,0.000004493349,0.01702543,0.7934233],"study_design_scores_gemma":[0.0001686698,0.00002410309,0.08551475,0.000057022,0.00004073912,0.0001588623,0.0001763857,0.9095672,0.0001405572,0.00001724895,0.003855538,0.0002789292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9130118,0.00005133013,0.07596549,0.009198747,0.001096812,0.0001198992,0.0001096217,0.00003724213,0.0004090426],"genre_scores_gemma":[0.8977039,0.00009193624,0.0978983,0.003510558,0.0003336994,8.961456e-9,0.0001475595,0.000009009752,0.0003050531],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9089794,"threshold_uncertainty_score":0.9994588,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04888486111882449,"score_gpt":0.2708843276749792,"score_spread":0.2219994665561547,"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."}}