{"id":"W4220974539","doi":"10.1029/2021gb007146","title":"Using Machine Learning to Predict Inland Aquatic CO<sub>2</sub> and CH<sub>4</sub> Concentrations and the Effects of Wildfires in the Yukon‐Kuskokwim Delta, Alaska","year":2022,"lang":"en","type":"article","venue":"Global Biogeochemical Cycles","topic":"Climate change and permafrost","field":"Earth and Planetary Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. Fish and Wildlife Service; Nuclear Safety and Security Commission; National Aeronautics and Space Administration; National Science Foundation","keywords":"Tundra; Environmental science; Permafrost; Dissolved organic carbon; Arctic; Aquatic ecosystem; Thermokarst; Total organic carbon; Surface water; Hydrology (agriculture); Ecosystem; Delta; Physical geography; Environmental chemistry; Atmospheric sciences; Ecology; Oceanography; Chemistry; Environmental engineering; Geology; Geography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004204854,0.0001693989,0.0002415033,0.000039275,0.0003674076,0.00007289945,0.0001992785,0.00005551843,0.00002467709],"category_scores_gemma":[0.0002048275,0.0001100262,0.00005067314,0.00033949,0.0003214263,0.00007622274,0.00007668576,0.0002230584,0.000003779794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000130387,"about_ca_system_score_gemma":0.00002733322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003742257,"about_ca_topic_score_gemma":0.003295384,"domain_scores_codex":[0.9985515,0.0003230103,0.0002462308,0.0002601305,0.0003102877,0.0003088548],"domain_scores_gemma":[0.9988221,0.000838829,0.00008910905,0.0001349314,0.00001182132,0.0001032301],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001689661,0.00002530741,0.9267134,0.00004559055,0.00001925995,0.00001246568,0.001146625,0.0002029995,0.068252,0.0000174193,0.0001556866,0.003240245],"study_design_scores_gemma":[0.003460179,0.0005136903,0.8267805,0.000183457,0.0002013929,0.0002542706,0.002607194,0.04235468,0.1201496,0.00232673,0.0006113626,0.000556981],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9927035,0.003739858,0.000003601395,0.0005629621,0.00007224537,0.0004338864,0.002379215,0.00001501428,0.00008974202],"genre_scores_gemma":[0.997847,0.000549946,0.00001807203,0.0005556684,0.00005528893,0.000009697707,0.0009607518,0.000003452257,1.844251e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09993295,"threshold_uncertainty_score":0.5657198,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01438288607798476,"score_gpt":0.232971058292181,"score_spread":0.2185881722141963,"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."}}