{"id":"W4233166168","doi":"10.5194/bg-2015-661-rc1","title":"Predicting carbon dioxide and energy fluxes across global FLUXNET sites with regression algorithms","year":2016,"lang":"en","type":"peer-review","venue":"","topic":"Atmospheric and Environmental Gas Dynamics","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Lawrence Berkeley National Laboratory; U.S. Department of Energy; Japan Aerospace Exploration Agency; European Commission; European Regional Development Fund; National Aeronautics and Space Administration; Natural Resources Canada; Horizon 2020 Framework Programme; Natural Sciences and Engineering Research Council of Canada; Oak Ridge National Laboratory; Biological and Environmental Research; Canadian Foundation for Climate and Atmospheric Sciences; Microsoft Research; National Science Foundation","keywords":"FluxNet; Carbon dioxide; Environmental science; Energy (signal processing); Regression; Algorithm; Atmospheric sciences; Computer science; Mathematics; Chemistry; Geology; Statistics; Ecosystem; Ecology; Biology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00334473,0.001389834,0.0005997133,0.001148319,0.0002727029,0.0006782567,0.0007152788,0.0008628376,0.000566924],"category_scores_gemma":[0.004844196,0.0005775217,0.0008107716,0.001303607,0.000294443,0.001126242,0.0004415588,0.0006488585,0.0002091085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001019902,"about_ca_system_score_gemma":0.0006226609,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02813846,"about_ca_topic_score_gemma":0.02776493,"domain_scores_codex":[0.9993166,0.0003055311,0.00004305727,0.0002027157,0.00006890448,0.00006331781],"domain_scores_gemma":[0.9984208,0.0009374586,0.0001827341,0.0001614078,0.0002538793,0.00004376243],"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":[0.0002222007,0.0002909075,0.04675344,0.0000371591,0.0001945178,0.00003431079,0.00004490095,0.9158913,0.003156662,0.000226394,0.0004919877,0.03265619],"study_design_scores_gemma":[0.00002195102,0.00003558505,0.01247692,0.000003198855,0.00001306474,0.000004845125,0.00001351959,0.9862781,0.0008517688,0.0002049336,0.00008731315,0.000008803577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"other","genre_scores_codex":[0.9714829,0.0001019952,0.02614425,0.00006719138,0.00001874671,0.0000366678,0.0007072882,0.000901369,0.0005395358],"genre_scores_gemma":[0.9559307,0.00004515759,0.04149113,0.00002152603,0.00001176413,0.00009910439,0.001970883,0.00006583442,0.0003638898],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.02813846,"threshold_uncertainty_score":0.05594933,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007954323972853838,"score_gpt":0.2425191657164889,"score_spread":0.2345648417436351,"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."}}