{"id":"W4411349001","doi":"10.5194/egusphere-2025-2517","title":"Improving Terrestrial Carbon Flux Simulations With Machine Learning and Global Earth Observations","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Atmospheric and Environmental Gas Dynamics","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Alliance de recherche numérique du Canada; Queen's University; Australian Government","keywords":"Earth (classical element); Flux (metallurgy); Carbon flux; Earth system science; Astrobiology; Carbon cycle; Carbon fibers; Environmental science; Earth science; Geology; Computer science; Physics; Materials science; Oceanography; Ecosystem; Astronomy; Biology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001165549,0.0008748786,0.0006417325,0.0004667533,0.0003841212,0.0007623527,0.0006865636,0.001180961,0.001019621],"category_scores_gemma":[0.003307949,0.0003774202,0.0009680225,0.0005830025,0.0004391761,0.001105211,0.000479384,0.001033864,0.0002035575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008999003,"about_ca_system_score_gemma":0.0008188308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0192032,"about_ca_topic_score_gemma":0.01234217,"domain_scores_codex":[0.9997627,0.0001112298,0.00001518758,0.0000581044,0.00002707158,0.00002571911],"domain_scores_gemma":[0.9987509,0.0008304743,0.0001155503,0.0001183508,0.0001383783,0.00004623859],"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":[0.00002015396,0.00003939028,0.002532663,0.00001328514,0.00002997552,0.000008247632,0.000005822658,0.993342,0.0002120896,0.0001702662,0.0001669977,0.003459185],"study_design_scores_gemma":[0.000009417868,0.000007109576,0.0005576548,0.000002653366,0.000004818964,0.000001088168,0.000003066707,0.9989096,0.0002099043,0.0002060551,0.00008597122,0.000002708693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9320011,0.0003981126,0.05920322,0.0008013249,0.0001175939,0.00006550807,0.001133671,0.001121051,0.005158546],"genre_scores_gemma":[0.9807196,0.00006873059,0.01776772,0.0001039849,0.00002440705,0.00004817077,0.000854966,0.0000640521,0.0003483055],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0192032,"threshold_uncertainty_score":0.0381828,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01019924276573738,"score_gpt":0.2178109826133127,"score_spread":0.2076117398475753,"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."}}