{"id":"W2783616714","doi":"10.1080/01431161.2018.1425564","title":"MSMD: maximum separability and minimum dependency feature selection for cropland classification from optical and radar data","year":2018,"lang":"en","type":"article","venue":"International Journal of Remote Sensing","topic":"Synthetic Aperture Radar (SAR) Applications and Techniques","field":"Engineering","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"National Oceanic and Atmospheric Administration; National Aeronautics and Space Administration","keywords":"Feature selection; Classifier (UML); Synthetic aperture radar; Computer science; Radar; Remote sensing; Filter (signal processing); Dependency (UML); Artificial intelligence; Feature (linguistics); Random forest; Data mining; Selection (genetic algorithm); Pattern recognition (psychology); Geography; Computer vision","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008438907,0.0008355464,0.0008535498,0.001895899,0.0004137166,0.0004773544,0.0006130756,0.000409727,0.000866752],"category_scores_gemma":[0.00127761,0.0002803488,0.001194754,0.001210327,0.0003047428,0.0004710661,0.0006908933,0.0004359818,0.0003768358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003245683,"about_ca_system_score_gemma":0.0007522717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002609402,"about_ca_topic_score_gemma":0.002022829,"domain_scores_codex":[0.999357,0.0001135008,0.00005420987,0.0001255798,0.0002787109,0.00007085926],"domain_scores_gemma":[0.9995661,0.0001854479,0.0000656833,0.00003823498,0.0001153248,0.00002912378],"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":[0.0004117853,0.0002616334,0.006218155,0.0001739133,0.000179017,0.0003083127,0.0001061549,0.05619653,0.06097456,0.001134161,0.003306834,0.870729],"study_design_scores_gemma":[0.00005071711,0.0002541269,0.01395415,0.00001822313,0.00008454549,0.0003367874,0.00006524775,0.9504583,0.02951888,0.001327994,0.003888841,0.00004218493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1151862,0.0005367996,0.8817444,0.0001008823,0.00004593984,0.0001175674,0.0003674285,0.001038484,0.0008621812],"genre_scores_gemma":[0.5612814,0.0004060336,0.4323481,0.0000821874,0.00007575964,0.0003264988,0.002653067,0.0000988387,0.002728043],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002609402,"threshold_uncertainty_score":0.005188346,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02295756072932985,"score_gpt":0.2890158317423346,"score_spread":0.2660582710130047,"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."}}