{"id":"W4283159752","doi":"10.5194/gmd-15-4709-2022","title":"A map of global peatland extent created using machine learning (Peat-ML)","year":2022,"lang":"en","type":"article","venue":"Geoscientific model development","topic":"Peatlands and Wetlands Ecology","field":"Environmental Science","cited_by":79,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University; Environment and Climate Change Canada","funders":"","keywords":"Peat; Boreal; Environmental science; Mean squared error; Vegetation (pathology); Physical geography; Soil science; Hydrology (agriculture); Climatology; Geology; Statistics; Ecology; Mathematics; Geography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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":[0.0002909598,0.0002815239,0.0001657458,0.00235813,0.000239672,0.0006220108,0.000238866,0.0002384594,0.002711315],"category_scores_gemma":[0.0008882771,0.0001070296,0.0002905697,0.00190141,0.0002031835,0.0002760142,0.0004340361,0.000285506,0.0004666612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000871893,"about_ca_system_score_gemma":0.001356651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1656344,"about_ca_topic_score_gemma":0.271756,"domain_scores_codex":[0.9998893,0.0000112033,0.000004574123,0.00003359445,0.00003921784,0.00002223505],"domain_scores_gemma":[0.9996331,0.00009314049,0.00004043746,0.00003983598,0.0001636794,0.00002974991],"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":[0.000604089,0.0002283099,0.1949246,0.0008561274,0.0002888426,0.0009725826,0.001116054,0.3714222,0.02943817,0.003443409,0.02516818,0.3715374],"study_design_scores_gemma":[0.00008464629,0.00007333019,0.5136526,0.0001755009,0.00007411191,0.0002872716,0.0007073046,0.4384228,0.01066644,0.001387839,0.03438439,0.00008375713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8203018,0.0004434272,0.06596804,0.0002808069,0.0000831378,0.0002167362,0.08883592,0.007800609,0.01606955],"genre_scores_gemma":[0.9036668,0.000164739,0.07062704,0.00002771768,0.00001288664,0.00008598474,0.02315717,0.0002044138,0.002053265],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1656344,"threshold_uncertainty_score":0.3293407,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01825625136512427,"score_gpt":0.2247311004704992,"score_spread":0.2064748491053749,"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."}}