{"id":"W2998342770","doi":"10.3390/rs12010002","title":"Comparing Deep Learning and Shallow Learning for Large-Scale Wetland Classification in Alberta, Canada","year":2019,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Flood Risk Assessment and Management","field":"Environmental Science","cited_by":183,"is_retracted":false,"has_abstract":true,"ca_institutions":"Government of Alberta; University of Alberta; Natural Resources Canada; Centre For Cold Ocean Resources Engineering; Memorial University of Newfoundland; Alberta Biodiversity Monitoring Institute","funders":"Alberta Environment and Parks; Alberta Biodiversity Monitoring Institute","keywords":"Wetland; Convolutional neural network; Remote sensing; Scale (ratio); Artificial intelligence; Computer science; Deep learning; Random forest; Machine learning; Cartography; Geography; Ecology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000241404,0.00009908886,0.0001405361,0.00003079175,0.0001396356,0.00003931358,0.00004600153,0.00003429969,0.00002941651],"category_scores_gemma":[0.00002390741,0.0001024923,0.00001826494,0.00009438921,0.00001248258,0.00009667566,0.00009294631,0.0001558342,0.00001709188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002152782,"about_ca_system_score_gemma":0.00001091067,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.3013768,"about_ca_topic_score_gemma":0.9153587,"domain_scores_codex":[0.9991028,0.00004605169,0.0001452821,0.0002762795,0.0001513761,0.0002781908],"domain_scores_gemma":[0.9997137,0.00008844546,0.00007013528,0.00008238567,0.00000451949,0.00004084431],"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":[0.0000246277,0.00001184962,0.8572477,0.00004951421,0.00001220975,0.000004200276,0.0008396388,0.04897598,0.007305115,0.00004145853,0.00008751517,0.08540025],"study_design_scores_gemma":[0.0004125291,0.00001714545,0.131824,0.00003000055,0.000007744369,0.000001731711,0.0007833721,0.8384128,0.00006635958,0.00002468776,0.02830027,0.00011939],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9772317,0.00002052206,0.009603841,0.0002197841,0.00009396418,0.0002691434,7.714122e-8,0.00001644162,0.01254454],"genre_scores_gemma":[0.9920956,0.00002740311,0.005366807,0.00005535029,0.00001798224,6.965594e-8,0.00001228821,0.00001440353,0.002410107],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7894368,"threshold_uncertainty_score":0.7032753,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009168292116597407,"score_gpt":0.2232973588163133,"score_spread":0.2141290666997159,"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."}}