{"id":"W2884821113","doi":"10.3390/rs10071119","title":"Very Deep Convolutional Neural Networks for Complex Land Cover Mapping Using Multispectral Remote Sensing Imagery","year":2018,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":430,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick; Centre For Cold Ocean Resources Engineering; Memorial University of Newfoundland","funders":"Research and Development Corporation of Newfoundland and Labrador; Natural Sciences and Engineering Research Council of Canada; Department of Environment and Conservation, Government of Newfoundland and Labrador; Government of Canada","keywords":"Multispectral image; Convolutional neural network; Random forest; Computer science; Artificial intelligence; Support vector machine; Remote sensing; Deep learning; Pattern recognition (psychology); Satellite imagery; Contextual image classification; Image (mathematics); Geology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000389141,0.0007789388,0.0003070388,0.0008709681,0.0001638433,0.0005089646,0.0006143498,0.0003982535,0.001733881],"category_scores_gemma":[0.0008106863,0.0002212815,0.0005232645,0.000779258,0.0002322686,0.0009834948,0.0004659529,0.0006529462,0.0006073282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005618757,"about_ca_system_score_gemma":0.0005920895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01182693,"about_ca_topic_score_gemma":0.02044861,"domain_scores_codex":[0.9998242,0.000027282,0.00000963919,0.00004084334,0.00006545373,0.00003256116],"domain_scores_gemma":[0.999833,0.0000565169,0.00003132629,0.00002718871,0.00004185641,0.00001015343],"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":[0.000274531,0.0001998462,0.007827939,0.0002698277,0.0002447246,0.0002636957,0.00009689153,0.4088345,0.03039461,0.004003095,0.009070338,0.53852],"study_design_scores_gemma":[0.000007091313,0.00003794586,0.003204265,0.00002565313,0.00002848564,0.00005562186,0.00003327813,0.9824479,0.009055473,0.002562621,0.00252584,0.00001584567],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3669043,0.006320585,0.6033982,0.0008726172,0.0002707889,0.0001188901,0.002281541,0.007782587,0.01205058],"genre_scores_gemma":[0.86686,0.001493189,0.1229637,0.0002126501,0.00004545021,0.00005232425,0.003642224,0.0001502499,0.004580231],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01182693,"threshold_uncertainty_score":0.02351618,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04236704489195767,"score_gpt":0.2613133717486997,"score_spread":0.2189463268567421,"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."}}