{"id":"W4406570018","doi":"10.22541/essoar.173724236.66537152/v1","title":"A novel model for forecasting geomagnetic indices using machine learning","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Earthquake Detection and Analysis","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Goddard Space Flight Center; British Geological Survey; U.S. Geological Survey; Danmarks Tekniske Universitet; Natural Resources Canada; Sveriges Geologiska Undersökning","keywords":"Earth's magnetic field; Artificial intelligence; Computer science; Machine learning; Physics","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003707778,0.0002481326,0.0003466961,0.0003479156,0.0003614918,0.0001819169,0.0002331771,0.000209338,0.0009409796],"category_scores_gemma":[0.0001291206,0.0002181165,0.0002646609,0.0002227116,0.00003241713,0.00007786148,0.00007266698,0.0004959652,0.000008561997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005909846,"about_ca_system_score_gemma":0.0001486296,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.009664493,"about_ca_topic_score_gemma":0.02250061,"domain_scores_codex":[0.9986087,0.00003443155,0.0003473988,0.000489965,0.0002008628,0.0003186479],"domain_scores_gemma":[0.999253,0.0001817611,0.0002205859,0.0001722344,0.00007908789,0.00009336851],"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":[0.00001488771,0.000007318375,0.0204993,0.0001400934,0.00005897179,7.153802e-7,0.0001069294,0.9490362,0.00003296106,0.00000734803,0.000007950005,0.03008735],"study_design_scores_gemma":[0.0002069329,0.00003477805,0.0007286947,0.00008387791,0.0001479971,0.000005510378,0.00006517915,0.9977541,0.00003773209,0.0004285788,0.0002529466,0.000253683],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2711138,0.001005773,0.7196398,0.0001167098,0.0003937162,0.0004607351,0.0006807683,0.0001920798,0.006396633],"genre_scores_gemma":[0.8933811,0.00004162448,0.09437028,0.0002054408,0.0001214451,0.000004277008,0.0005156558,0.00000604347,0.01135416],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6252695,"threshold_uncertainty_score":0.9999723,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0812001243797037,"score_gpt":0.2605231246282146,"score_spread":0.1793230002485109,"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."}}