{"id":"W4322009923","doi":"10.5194/egusphere-egu23-8297","title":"Scalable machine learning solution for commercial scale three dimensional geophysical inversions","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Geophysical and Geoelectrical Methods","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mount Allison University","funders":"","keywords":"Scalability; Computer science; Inversion (geology); Workflow; Artificial intelligence; Deep learning; Machine learning; Algorithm; Big data; Scale (ratio); Geophysics; Computational science; Data mining; Geology; Database; Geography; Cartography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0006754317,0.001044164,0.0008568648,0.0004798204,0.0006014672,0.001296565,0.001601974,0.001195387,0.008114578],"category_scores_gemma":[0.00296266,0.0004686556,0.0007647346,0.0007449083,0.0006316048,0.001106151,0.002365911,0.001995867,0.001856287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009567505,"about_ca_system_score_gemma":0.002124404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009233226,"about_ca_topic_score_gemma":0.01254676,"domain_scores_codex":[0.9995981,0.0000781905,0.00002015975,0.00007215341,0.0001546053,0.00007683972],"domain_scores_gemma":[0.9989228,0.0004823362,0.00006074526,0.0001477316,0.000307664,0.00007875871],"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":[0.0001542785,0.0001073176,0.001303921,0.0001340195,0.00004887234,0.0002406412,0.0001086555,0.8796411,0.006123357,0.01023441,0.01048527,0.09141817],"study_design_scores_gemma":[0.000009790891,0.00000633747,0.00006976502,0.000003360898,0.000001784656,0.000008600526,0.00001597279,0.9954287,0.0004325711,0.003164604,0.0008557553,0.000002845733],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0245603,0.0002769701,0.9622647,0.0007808892,0.00009379812,0.0001021075,0.0003684599,0.003856099,0.007696649],"genre_scores_gemma":[0.3633436,0.0002760552,0.6281597,0.0002763175,0.00009864381,0.0003791575,0.001496731,0.000715469,0.00525439],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009233226,"threshold_uncertainty_score":0.02714598,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04900015208375386,"score_gpt":0.2675679168717416,"score_spread":0.2185677647879877,"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."}}