{"id":"W4413794448","doi":"10.5194/egusphere-2025-3968","title":"High-resolution remote sensing and machine-learning-based upscaling of methane fluxes: a case study in the Western Canadian tundra","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Cryospheric studies and observations","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"HORIZON EUROPE European Research Council; Natural Sciences and Engineering Research Council of Canada; Bundesministerium für Forschung und Technologie; TED; HORIZON EUROPE Climate, Energy and Mobility; Academy of Finland; H2020 European Research Council; E.B. Eddy Endowment Fund; European Space Agency; Networks of Centres of Excellence of Canada; Canada First Research Excellence Fund; Gordon and Betty Moore Foundation","keywords":"Tundra; Random forest; Environmental science; Arctic; Gradient boosting; Support vector machine; Flux (metallurgy); Atmospheric sciences; Terrain; Remote sensing; Geography; Cartography; Machine learning; Geology; Computer science; Chemistry","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":[0.001458021,0.0007966988,0.000406513,0.001065678,0.002190598,0.001480214,0.001357741,0.0006796498,0.0005592718],"category_scores_gemma":[0.002601842,0.000290606,0.0006763016,0.002716683,0.0009278759,0.0005275357,0.0005729751,0.0006031153,0.0001229928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01052869,"about_ca_system_score_gemma":0.007496355,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9707257,"about_ca_topic_score_gemma":0.9778869,"domain_scores_codex":[0.9994024,0.00008836127,0.00002906668,0.0001388647,0.0001827082,0.0001585461],"domain_scores_gemma":[0.999038,0.0002006077,0.00006434851,0.0001050211,0.0005067986,0.00008541589],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009616934,0.001009735,0.4274941,0.0004465389,0.0005457207,0.003435814,0.001821048,0.3999012,0.02202601,0.001947909,0.004596689,0.1358136],"study_design_scores_gemma":[0.0001580083,0.0002069045,0.3987665,0.0000779355,0.000211151,0.0003161473,0.002665253,0.5803354,0.009986212,0.0005239236,0.006605716,0.0001468553],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9934624,0.0002938889,0.002896097,0.0002391822,0.00001532988,0.00007334432,0.0006862758,0.0002213097,0.002112216],"genre_scores_gemma":[0.9898956,0.0001271347,0.008889814,0.00004691434,0.00000688859,0.00001754288,0.0005459446,0.00003315171,0.0004370298],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02927428,"threshold_uncertainty_score":0.07639128,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04125215315562142,"score_gpt":0.2567752294028076,"score_spread":0.2155230762471861,"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."}}