{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006583981,0.0001588923,0.0001946269,0.0002618212,0.0003233771,0.0001751618,0.0007425432,0.00008652511,0.0000204619],"category_scores_gemma":[0.00007084752,0.0001298466,0.00009948505,0.0007427685,0.0004723371,0.001525988,0.0003604939,0.0004109899,0.00002096001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003688796,"about_ca_system_score_gemma":0.00002673792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000220105,"about_ca_topic_score_gemma":0.0001411027,"domain_scores_codex":[0.9974786,0.0002514092,0.0003943584,0.0005273652,0.0008534227,0.0004948416],"domain_scores_gemma":[0.9986793,0.0004914922,0.0001300488,0.0005937504,0.00001143734,0.00009394351],"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":[0.0003338558,0.001522296,0.1367194,0.00001584345,0.000274143,0.0002007465,0.001004093,0.2900872,0.1441144,0.0007112171,0.00004108021,0.4249757],"study_design_scores_gemma":[0.0002492414,0.00006605177,0.08191112,0.00002492478,0.00001478129,0.00001107853,0.0003198982,0.913088,0.001990168,0.00174328,0.000425621,0.0001558714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3008362,0.004094708,0.6943779,0.0001162762,0.00007965689,0.0001833377,0.00002488244,0.00006044017,0.0002266093],"genre_scores_gemma":[0.9688107,0.004627966,0.02636855,0.00001002226,0.00002157873,0.00001513795,0.00002523108,0.00001129012,0.0001094633],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6680094,"threshold_uncertainty_score":0.529499,"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."}}