{"id":"W2952629512","doi":"10.1371/journal.pone.0218165","title":"Large-scale probabilistic identification of boreal peatlands using Google Earth Engine, open-access satellite data, and machine learning","year":2019,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Peatlands and Wetlands Ecology","field":"Environmental Science","cited_by":80,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Biodiversity Monitoring Institute; University of Calgary; University of Alberta","funders":"Government of Alberta; Alberta Environment and Parks; Alberta Biodiversity Monitoring Institute","keywords":"Peat; Boreal; Remote sensing; Satellite imagery; Environmental science; Wetland; Permafrost; Land cover; Satellite; Computer science; Geography; Land use; Geology; Ecology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006092309,0.0004638203,0.0001924874,0.001781023,0.0003735796,0.0007749404,0.0005026011,0.0002659236,0.0006122668],"category_scores_gemma":[0.001628368,0.0002095448,0.0004790099,0.001436552,0.0003208414,0.0006969108,0.0006891018,0.0002599563,0.0002498221],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001236756,"about_ca_system_score_gemma":0.001561044,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.3013987,"about_ca_topic_score_gemma":0.5725985,"domain_scores_codex":[0.9997938,0.00003282118,0.00001052447,0.00005701043,0.00007780892,0.00002801904],"domain_scores_gemma":[0.9995304,0.0001579597,0.00009273493,0.00006850351,0.0001098425,0.00004053129],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002765927,0.0002118763,0.3840881,0.0002540799,0.0003158222,0.0004984158,0.0004117397,0.347276,0.009941674,0.004583281,0.009543017,0.2425994],"study_design_scores_gemma":[0.00001556763,0.00002184665,0.1825751,0.00003272921,0.00003503044,0.00009847051,0.0003658733,0.80509,0.002998239,0.004766546,0.003962683,0.00003793637],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8072495,0.0007146301,0.1627514,0.000605418,0.00004864811,0.0001764803,0.0148629,0.006717744,0.006873277],"genre_scores_gemma":[0.9286384,0.0001723901,0.05880535,0.00003011002,0.00001368702,0.00003020459,0.01133751,0.00009796867,0.0008743434],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3013987,"threshold_uncertainty_score":0.5992888,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05275894777722909,"score_gpt":0.2747272665893495,"score_spread":0.2219683188121205,"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."}}