{"id":"W2813913090","doi":"10.1109/i2mtc.2018.8409517","title":"What can machine learning do for geomagnetic data processing? A reconstruction application","year":2018,"lang":"en","type":"article","venue":"","topic":"Geophysical and Geoelectrical Methods","field":"Earth and Planetary Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Earth's magnetic field; Computer science; Support vector machine; Machine learning; Artificial intelligence; Interpolation (computer graphics); Hyperplane; Unexploded ordnance; Field (mathematics); Boosting (machine learning); Random forest; Relation (database); Data mining; Mathematics; Geology; Remote sensing; Magnetic field","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":[0.002905272,0.0008112388,0.0008006709,0.0008079523,0.0004480701,0.001749576,0.0008140191,0.002005165,0.002082737],"category_scores_gemma":[0.01286455,0.0003277608,0.000579799,0.0008445281,0.001010414,0.002845984,0.0006781801,0.001573144,0.001077016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004735247,"about_ca_system_score_gemma":0.0006512738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002013467,"about_ca_topic_score_gemma":0.001521239,"domain_scores_codex":[0.9992537,0.0003345496,0.0000387543,0.0001344477,0.000184994,0.00005353635],"domain_scores_gemma":[0.9973133,0.001726558,0.000128828,0.0002690128,0.0004628073,0.00009931615],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002442047,0.0001689463,0.009089672,0.0005029512,0.0001634723,0.0002033356,0.0002267749,0.07995483,0.005058552,0.02690893,0.01310839,0.86437],"study_design_scores_gemma":[0.00003836264,0.0001825924,0.002899965,0.0003380457,0.00005297181,0.0002038813,0.0003265791,0.8678372,0.004987211,0.1033238,0.01975868,0.00005078702],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03273016,0.01399503,0.9219477,0.02163054,0.0006648659,0.00007458857,0.0002228622,0.001349105,0.007385085],"genre_scores_gemma":[0.4747829,0.01181937,0.504133,0.002007189,0.001049575,0.0001368996,0.000331689,0.0001567366,0.005582771],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002905272,"threshold_uncertainty_score":0.01536471,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0259444393033963,"score_gpt":0.2704768649855894,"score_spread":0.2445324256821931,"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."}}