{"id":"W4416337428","doi":"10.5194/bg-23-2959-2026","title":"PeatDepth-ML: A Global Map of Peat Depth Predicted using Machine Learning","year":2025,"lang":"en","type":"article","venue":"Biogeosciences","topic":"Peatlands and Wetlands Ecology","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal; University of Victoria; Environment and Climate Change Canada","funders":"","keywords":"Peat; Bootstrapping (finance); Metric (unit); Climate change; Sampling (signal processing); Mean squared error; Training (meteorology); Global change","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":[0.00084101,0.0007676457,0.0003428262,0.001790627,0.0001690825,0.0005280597,0.0004952937,0.0005313081,0.002609508],"category_scores_gemma":[0.001567244,0.0001798415,0.0006607862,0.001152671,0.0002032806,0.0006680924,0.0006059186,0.0004720533,0.0008180607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005310461,"about_ca_system_score_gemma":0.0006614408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01916873,"about_ca_topic_score_gemma":0.01848533,"domain_scores_codex":[0.9998416,0.00003191683,0.000007647769,0.00005693682,0.00003708849,0.0000248481],"domain_scores_gemma":[0.9995074,0.0001705902,0.00006762527,0.00006057533,0.0001537829,0.00003987095],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005411196,0.0002050679,0.1251795,0.0004782104,0.000399805,0.0005611277,0.0001902374,0.7311817,0.009955561,0.001758931,0.02137177,0.1081769],"study_design_scores_gemma":[0.00005758638,0.00009198399,0.06758016,0.00009629797,0.0000580304,0.00008966128,0.0001141473,0.9151554,0.005318348,0.001603137,0.009774577,0.00006068996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8005155,0.001073511,0.08392803,0.0006088341,0.0002209006,0.0001167191,0.08556369,0.01911139,0.008861472],"genre_scores_gemma":[0.9106929,0.0002141309,0.05261079,0.00005946064,0.00003637891,0.00008467559,0.03482492,0.0004035669,0.001073215],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01916873,"threshold_uncertainty_score":0.03811431,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01240940890521946,"score_gpt":0.253794289120823,"score_spread":0.2413848802156036,"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."}}