{"id":"W1990829950","doi":"10.1109/igarss.2014.6947537","title":"Classification of land cover based on deep belief networks using polarimetric RADARSAT-2 data","year":2014,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Natural Science Foundation of China","keywords":"Deep belief network; Computer science; Land cover; Artificial intelligence; Support vector machine; Remote sensing; Deep learning; Pattern recognition (psychology); Geography; Land use; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0004273978,0.0007179162,0.0003906729,0.001164656,0.0002046177,0.0006607736,0.0005261191,0.0004840608,0.0006495317],"category_scores_gemma":[0.0009247027,0.0002302214,0.0004377265,0.0007012309,0.0002487134,0.0008693459,0.0005129862,0.0005984962,0.000224182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006361724,"about_ca_system_score_gemma":0.000322007,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009760003,"about_ca_topic_score_gemma":0.01281539,"domain_scores_codex":[0.9998245,0.00003290643,0.00001016021,0.00005129299,0.00003842734,0.00004284406],"domain_scores_gemma":[0.9996234,0.000153945,0.00005793597,0.00003463823,0.0001008384,0.00002922458],"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":[0.0003466732,0.0003263194,0.0217634,0.00006953414,0.0001434264,0.000142066,0.00009769428,0.6615548,0.007848825,0.001395136,0.002101259,0.3042108],"study_design_scores_gemma":[0.000002530624,0.00001166805,0.001313475,0.000002709325,0.000005748072,0.000005258805,0.000012329,0.9974498,0.000749924,0.0003682855,0.00007525907,0.00000293646],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6480049,0.0004503006,0.3467959,0.0003794751,0.00006494109,0.00007187474,0.0009929925,0.0009709293,0.002268597],"genre_scores_gemma":[0.9708996,0.0001033501,0.02703188,0.00004411805,0.00001705981,0.00002592666,0.0009044101,0.00001434975,0.0009592113],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009760003,"threshold_uncertainty_score":0.01940638,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04207195488702933,"score_gpt":0.2535840156259814,"score_spread":0.211512060738952,"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."}}