{"id":"W3144399036","doi":"10.1080/07038992.2021.1901562","title":"Wetland Mapping Using Multi-Spectral Satellite Imagery and Deep Convolutional Neural Networks: A Case Study in Newfoundland and Labrador, Canada","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre For Cold Ocean Resources Engineering; Memorial University of Newfoundland","funders":"","keywords":"Convolutional neural network; Artificial intelligence; Deep learning; Computer science; Pattern recognition (psychology); Satellite imagery; Feature (linguistics); Wetland; Machine learning; Remote sensing; Geography; Ecology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.0003888975,0.0006709075,0.0003936024,0.001514364,0.001746133,0.001197579,0.00114435,0.0006772094,0.001155309],"category_scores_gemma":[0.0008386964,0.0002429573,0.0005103664,0.003900172,0.0009581375,0.0005377483,0.0005610251,0.0005410381,0.000197998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01701004,"about_ca_system_score_gemma":0.01074457,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9864727,"about_ca_topic_score_gemma":0.9946265,"domain_scores_codex":[0.999542,0.0000424557,0.00001553115,0.00007011753,0.0001323907,0.0001975757],"domain_scores_gemma":[0.9995178,0.00009298581,0.00004193885,0.00003021442,0.000232579,0.0000845269],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009617285,0.001225332,0.5489046,0.001083475,0.0006415668,0.03190037,0.004438029,0.171093,0.01024827,0.006790936,0.03173243,0.1909802],"study_design_scores_gemma":[0.0001491825,0.0001515177,0.6990873,0.000198515,0.0003192612,0.001467227,0.01833224,0.2523959,0.006082156,0.0009392916,0.02067636,0.0002011623],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9835342,0.0007009865,0.00232141,0.0006739952,0.00002370227,0.0001476211,0.003616036,0.000179402,0.008802693],"genre_scores_gemma":[0.9875672,0.000613964,0.004271704,0.00008450605,0.000008226119,0.00002459266,0.002184914,0.00003335431,0.00521159],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01701004,"threshold_uncertainty_score":0.1234171,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01671937218146018,"score_gpt":0.2194686978796248,"score_spread":0.2027493256981646,"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."}}