{"id":"W3103554233","doi":"10.1109/jstars.2020.3036802","title":"Evaluation of the Landsat-Based Canadian Wetland Inventory Map Using Multiple Sources: Challenges of Large-Scale Wetland Classification Using Remote Sensing","year":2020,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"Agriculture and Agri-Food Canada; University of New Brunswick; Dalhousie University; Agriculture Food and Rural Development; Ducks Unlimited Canada; Alberta Biodiversity Monitoring Institute; University of Alberta","funders":"Natural Resources Canada","keywords":"Remote sensing; Scale (ratio); Synthetic aperture radar; Computer science; Land cover; Environmental science; Wetland; Land use; Cartography; Geography","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":[0.001094098,0.0001681729,0.0003131907,0.0001237252,0.0002073635,0.00002825343,0.0001178729,0.0001776019,0.000003829155],"category_scores_gemma":[0.000244599,0.0001310489,0.00006634402,0.000701257,0.0001233764,0.00008892894,0.00002891449,0.0003762537,2.850218e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002775235,"about_ca_system_score_gemma":0.000325954,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005195369,"about_ca_topic_score_gemma":0.0638275,"domain_scores_codex":[0.9978472,0.0002662006,0.0006416406,0.0002237063,0.0007714942,0.000249751],"domain_scores_gemma":[0.9985157,0.00007531855,0.0007042894,0.0001885684,0.000398586,0.0001175126],"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":[0.00004601327,0.00002655586,0.009373043,0.0001055401,0.00005737432,0.000005028352,0.00369482,0.2181592,0.689918,0.00000602957,0.00003847806,0.07856987],"study_design_scores_gemma":[0.0008098247,0.00002275388,0.06295936,0.000290292,0.0001170761,0.00002604462,0.0005826641,0.9210403,0.01343128,0.0001537506,0.0004322415,0.0001344015],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9873648,0.0001456579,0.01060164,0.00120767,0.0001797178,0.000296299,0.000004959812,0.000007139995,0.0001921425],"genre_scores_gemma":[0.9209698,0.00004243859,0.07865932,0.0001453983,0.0001602127,5.49868e-9,0.000003426402,0.00001604214,0.000003359958],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7028811,"threshold_uncertainty_score":0.9532552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06857258130019128,"score_gpt":0.249800621356786,"score_spread":0.1812280400565947,"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."}}