{"id":"W2811244448","doi":"10.1109/jstars.2018.2846178","title":"Deep Convolutional Neural Network for Complex Wetland Classification Using Optical Remote Sensing Imagery","year":2018,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":241,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre For Cold Ocean Resources Engineering; Memorial University of Newfoundland; University of New Brunswick","funders":"Research and Development Corporation of Newfoundland and Labrador","keywords":"Convolutional neural network; Computer science; Remote sensing; Land cover; Random forest; Artificial intelligence; Deep learning; Satellite imagery; Contextual image classification; Thematic map; Pattern recognition (psychology); Feature extraction; Land use; Image (mathematics); Cartography","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005234441,0.000241348,0.0003940794,0.0002612153,0.0003170802,0.0001419512,0.00008575006,0.0002042513,0.000001691738],"category_scores_gemma":[0.0001905955,0.0002533105,0.00007071652,0.0007274834,0.0002084957,0.0001744378,0.00001510815,0.0004591457,9.48809e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001895184,"about_ca_system_score_gemma":0.0001228448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000187872,"about_ca_topic_score_gemma":0.0001470929,"domain_scores_codex":[0.9980839,0.00005972101,0.0008782325,0.0002460224,0.0003015517,0.0004306118],"domain_scores_gemma":[0.9981021,0.0002512501,0.0003117906,0.00021006,0.001021314,0.0001034433],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000893404,0.00001013848,0.00007599113,0.00007007422,0.00006925404,0.00001094311,0.000181347,0.07929461,0.6403949,0.0001525513,0.0003013915,0.2793494],"study_design_scores_gemma":[0.0006770323,0.00004028475,0.02241878,0.0001465705,0.00005832533,0.0003039692,0.00005066903,0.9697185,0.003752674,0.001301071,0.001288962,0.0002432028],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3571979,0.00006331892,0.6414006,0.0002693293,0.0005829542,0.0002135064,0.000002075936,0.00005178234,0.0002185747],"genre_scores_gemma":[0.4297324,0.00004313919,0.5686232,0.00009125554,0.001445581,1.503455e-8,0.00001609324,0.00003630629,0.00001199766],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8904238,"threshold_uncertainty_score":0.9999919,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06331301919100238,"score_gpt":0.2662183573009876,"score_spread":0.2029053381099852,"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."}}