{"id":"W4310376514","doi":"10.1080/07038992.2022.2144179","title":"A New U-Net Based Convolutional Neural Network for Estimating Caribou Lichen Ground Cover from Field-Level RGB Images","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Forest Service; Government of Newfoundland and Labrador; University of Alberta; Natural Resources Canada","funders":"","keywords":"Ground truth; Workflow; Convolutional neural network; Geospatial analysis; Remote sensing; Computer science; Scalability; Field (mathematics); Software; Artificial neural network; RGB color model; Scale (ratio); Cartography; Data mining; Environmental science; Geography; Artificial intelligence; Database; Mathematics","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":[0.0004055001,0.0006292202,0.000303176,0.0006687472,0.0003271171,0.000505453,0.001019569,0.0005464241,0.00163508],"category_scores_gemma":[0.0009251275,0.0002403973,0.0003379574,0.0005458518,0.0002153737,0.0007075574,0.0005805605,0.0004654745,0.0004297422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001035682,"about_ca_system_score_gemma":0.001189515,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.06650583,"about_ca_topic_score_gemma":0.08899942,"domain_scores_codex":[0.9998609,0.0000124784,0.000006522342,0.00004776895,0.00003973099,0.00003265902],"domain_scores_gemma":[0.9997979,0.00004632619,0.00001938318,0.00002127592,0.0001003328,0.00001478241],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002475011,0.0002374192,0.01401588,0.00009315307,0.0001513463,0.0001534725,0.00007915938,0.4839065,0.01845341,0.002096975,0.005490044,0.4750752],"study_design_scores_gemma":[0.000003140345,0.00001636475,0.00123099,0.000005281741,0.00001217618,0.00001480037,0.000007046698,0.9953056,0.002672784,0.0002619086,0.0004642176,0.000005596642],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.27843,0.0007230922,0.7056831,0.0002929234,0.0001177086,0.0001370777,0.0009363498,0.007817066,0.005862777],"genre_scores_gemma":[0.7958183,0.0002928174,0.1903063,0.0002176224,0.00003090615,0.0001529009,0.002024212,0.0001469538,0.01101005],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.06650583,"threshold_uncertainty_score":0.1322375,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03586329542699808,"score_gpt":0.2393163798419746,"score_spread":0.2034530844149765,"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."}}