{"id":"W2769340760","doi":"10.1002/2017gl075661","title":"Predicting the Geothermal Heat Flux in Greenland: A Machine Learning Approach","year":2017,"lang":"en","type":"article","venue":"Geophysical Research Letters","topic":"Cryospheric studies and observations","field":"Earth and Planetary Sciences","cited_by":104,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Science Foundation of Sri Lanka","keywords":"Greenland ice sheet; Geology; Glacier; Geothermal gradient; Ice core; Groenlandia; Volcano; Plume; Glaciology; Climatology; Ice stream; Flux (metallurgy); Ice sheet; Geophysics; Geomorphology; Oceanography; Paleontology; Tectonics; Volcanism; Cryosphere; Meteorology; Sea ice","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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0008543994,0.000099742,0.000139351,0.00002924285,0.001896199,0.0002438884,0.0005996277,0.00002904759,0.000226284],"category_scores_gemma":[0.0004287775,0.00006232676,0.00005768281,0.0001838011,0.0003938631,0.0001846085,0.0001129404,0.0007858645,0.0001357512],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009038875,"about_ca_system_score_gemma":0.0000220699,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.07638658,"about_ca_topic_score_gemma":0.004586624,"domain_scores_codex":[0.9982236,0.0002177261,0.0001312635,0.0002668067,0.0005581055,0.0006025161],"domain_scores_gemma":[0.9989569,0.000538078,0.00003183616,0.0003573377,0.00003196104,0.00008388092],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003651508,0.00002094531,0.9788124,0.000009014787,0.000015845,0.00001692393,0.0006662864,0.007365337,0.0001769862,0.00003941387,0.0008005638,0.01203975],"study_design_scores_gemma":[0.0001952829,0.00004262001,0.8344829,0.000009289346,0.00000214443,0.000001154045,0.0002629381,0.1610063,0.000003524156,0.00007281943,0.003856148,0.00006491321],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9862951,0.0001661445,0.00004791436,0.008914136,0.00007819067,0.0002077758,0.00001232487,0.00001938207,0.004259015],"genre_scores_gemma":[0.9984545,0.00003018767,0.0001138213,0.0004142576,0.0004041592,0.000009525781,0.00003061394,0.000004587024,0.0005384219],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1536409,"threshold_uncertainty_score":0.9994032,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05481715894739209,"score_gpt":0.2888828573782011,"score_spread":0.234065698430809,"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."}}