{"id":"W4229058842","doi":"10.1016/j.ecoinf.2022.101658","title":"Estimating boreal forest ground cover vegetation composition from nadir photographs using deep convolutional neural networks","year":2022,"lang":"en","type":"article","venue":"Ecological Informatics","topic":"Fire effects on ecosystems","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Nadir; Convolutional neural network; Segmentation; Computer science; Robustness (evolution); Remote sensing; Artificial intelligence; Vegetation (pathology); Image segmentation; Environmental science; Land cover; Pattern recognition (psychology); Computer vision; Geology; Ecology; Land use; Satellite","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"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":[0.0003013193,0.0005427548,0.0001711701,0.0008313571,0.0001649693,0.0004052876,0.0003806094,0.0002474918,0.0006667192],"category_scores_gemma":[0.0007368515,0.0002131935,0.0002974992,0.0005095626,0.0001227505,0.0003850016,0.0002465676,0.000267246,0.0003223621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000505913,"about_ca_system_score_gemma":0.0002697236,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02836094,"about_ca_topic_score_gemma":0.06605896,"domain_scores_codex":[0.9998661,0.00001688326,0.000005542907,0.00005712363,0.0000277477,0.00002648633],"domain_scores_gemma":[0.9997932,0.00005978025,0.00003137706,0.00002934163,0.0000728513,0.00001354162],"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":[0.0004909904,0.0004782847,0.2006031,0.0001953365,0.0002622245,0.0002801878,0.0002333464,0.3193115,0.0385938,0.0004929699,0.004169023,0.4348891],"study_design_scores_gemma":[0.00001000322,0.00004404676,0.09707346,0.00002094784,0.00003290627,0.00006598036,0.0001319522,0.8936139,0.007800949,0.0003337667,0.0008558793,0.00001623632],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.95898,0.0003175304,0.03598378,0.00006313312,0.00003823973,0.0000396528,0.001554252,0.0008982843,0.002125247],"genre_scores_gemma":[0.9601933,0.0001163111,0.03624066,0.00002966273,0.00001141295,0.00001686528,0.002397764,0.00003317851,0.0009608605],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02836094,"threshold_uncertainty_score":0.05639172,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01149053206700128,"score_gpt":0.2185038198708857,"score_spread":0.2070132878038844,"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."}}