{"id":"W4411253423","doi":"10.5194/essd-17-2507-2025","title":"WetCH <sub>4</sub> : a machine-learning-based upscaling of methane fluxes of northern wetlands during 2016–2022","year":2025,"lang":"en","type":"article","venue":"Earth system science data","topic":"Atmospheric and Environmental Gas Dynamics","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; McGill University","funders":"European Commission","keywords":"Methane; Wetland; Environmental science; Hydrology (agriculture); Geology; Chemistry; Ecology","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":[0.000948038,0.0008310561,0.0004465485,0.0006105807,0.000354607,0.0004306104,0.000746244,0.0004158615,0.0009205083],"category_scores_gemma":[0.001044677,0.000280685,0.0009609835,0.0004363714,0.0002817884,0.0006100766,0.0003925814,0.0004836243,0.0002444609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008639181,"about_ca_system_score_gemma":0.001009773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.06647597,"about_ca_topic_score_gemma":0.06157005,"domain_scores_codex":[0.9998726,0.00002297045,0.000007409089,0.00004801949,0.0000246916,0.00002432184],"domain_scores_gemma":[0.9996779,0.00007690055,0.0000443296,0.0000536046,0.0001021842,0.0000451595],"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":[0.0004784367,0.0004329615,0.1162504,0.00009165979,0.0003720543,0.0001765835,0.0000596387,0.8291205,0.007246725,0.0002691286,0.003265196,0.04223669],"study_design_scores_gemma":[0.00002974046,0.00004019822,0.02240572,0.00000497398,0.00002412865,0.00000782693,0.00001506693,0.9754332,0.001602738,0.00008720657,0.0003361001,0.00001300316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.990844,0.00009168187,0.005047331,0.0001204251,0.00004213371,0.00002949762,0.001966625,0.001061933,0.0007964023],"genre_scores_gemma":[0.9878925,0.00002864533,0.007562986,0.00002490561,0.00002003414,0.00002789227,0.004086141,0.00004547363,0.0003113361],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06647597,"threshold_uncertainty_score":0.1321781,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006953849307034677,"score_gpt":0.2098464942852278,"score_spread":0.2028926449781931,"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."}}