{"id":"W2900519402","doi":"10.1109/igarss.2018.8519171","title":"Toward the Use of Deep Learning for Topographic Feature Extraction from High Resolution Optical Satellite Imagery","year":2018,"lang":"en","type":"article","venue":"","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Natural Resources Canada","funders":"Public Safety Canada","keywords":"Artificial intelligence; Computer science; Convolutional neural network; RGB color model; Deep learning; Feature extraction; Satellite imagery; Pixel; Remote sensing; Satellite; Confusion matrix; Feature (linguistics); Cohen's kappa; Pattern recognition (psychology); Artificial neural network; High resolution; Scale (ratio); Computer vision; Geology; Geography; Cartography; Machine learning; Engineering","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":[0.0006196107,0.0005247396,0.0002133201,0.0005889149,0.0001801698,0.0007479246,0.0005389657,0.0003392481,0.0006477165],"category_scores_gemma":[0.001202737,0.0002412546,0.0002882981,0.000614399,0.0003089595,0.0009722581,0.0005859176,0.0006188393,0.0003462624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006700522,"about_ca_system_score_gemma":0.0006901234,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0131525,"about_ca_topic_score_gemma":0.0227982,"domain_scores_codex":[0.9998403,0.00002941445,0.000007941898,0.00003766459,0.0000622235,0.00002243276],"domain_scores_gemma":[0.999689,0.00009003159,0.0000294306,0.00005470784,0.0001240874,0.00001285191],"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":[0.00009992811,0.0001644607,0.009957699,0.00009973065,0.0001197544,0.0001472961,0.000120772,0.2792186,0.0455123,0.007796873,0.003138144,0.6536245],"study_design_scores_gemma":[0.000002587512,0.00002283716,0.001517181,0.00001154214,0.000008697563,0.00002802538,0.00002452628,0.9811364,0.01280541,0.002673008,0.001763279,0.000006523362],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1054942,0.0006544859,0.8883383,0.0004573837,0.00003142176,0.00004596181,0.0003359292,0.001443416,0.003198928],"genre_scores_gemma":[0.5890334,0.000685157,0.4053683,0.0001387356,0.00002249193,0.00004346375,0.0008926023,0.00007034989,0.003745624],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0131525,"threshold_uncertainty_score":0.0261519,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02495116974718405,"score_gpt":0.2417965853086747,"score_spread":0.2168454155614906,"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."}}