{"id":"W1997245789","doi":"10.1016/s1093-0191(01)00095-8","title":"The automated extraction of environmentally relevant features from digital imagery using Bayesian multi-resolution analysis","year":2001,"lang":"en","type":"article","venue":"Advances in Environmental Research","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph; University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Bayesian probability; Pixel; Pattern recognition (psychology); Ambiguity; Mixture model; Parameterized complexity; Bayesian network; Gaussian; Interpretability; Data mining; Aerial imagery; Posterior probability; Machine learning; Algorithm","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":[0.0009460966,0.0008422843,0.001216821,0.002968452,0.0004696527,0.001300297,0.001122391,0.001050742,0.001015841],"category_scores_gemma":[0.003374402,0.001093761,0.001179164,0.002088677,0.0006356388,0.001684707,0.001228278,0.001283466,0.00102157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003812019,"about_ca_system_score_gemma":0.0008989453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00520813,"about_ca_topic_score_gemma":0.007742136,"domain_scores_codex":[0.999388,0.0001300621,0.00003803601,0.0001291293,0.0002586934,0.00005618089],"domain_scores_gemma":[0.9984924,0.0007736093,0.0001846293,0.0002284098,0.00028467,0.00003624804],"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":[0.0001290682,0.0001658625,0.003210505,0.0003482183,0.0001442156,0.0001724891,0.0001506906,0.134948,0.05810377,0.007041902,0.004388023,0.7911972],"study_design_scores_gemma":[0.00002259545,0.00002217436,0.006187495,0.0000318954,0.00007698629,0.0001531403,0.00003805305,0.9562434,0.01791772,0.01453524,0.004716714,0.00005448821],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01108173,0.0003857993,0.9865492,0.0001083659,0.0000123402,0.00002661175,0.0002906717,0.001000091,0.0005451412],"genre_scores_gemma":[0.1186868,0.0005574368,0.8783822,0.00006756146,0.00002905411,0.00008013548,0.001071931,0.0001949144,0.0009299003],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00520813,"threshold_uncertainty_score":0.01035565,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03417393581106833,"score_gpt":0.3579830410221154,"score_spread":0.3238091052110471,"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."}}