{"id":"W3123670553","doi":"10.1190/geo2020-0312.1","title":"Physics-guided deep learning for seismic inversion with hybrid training and uncertainty analysis","year":2021,"lang":"en","type":"article","venue":"Geophysics","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":130,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Inversion (geology); Computer science; Artificial intelligence; Deep learning; Artificial neural network; Residual; Synthetic data; Set (abstract data type); Machine learning; Algorithm; Seismology; Geology","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0001255129,0.0001356208,0.0002397138,0.00005712569,0.0002820484,0.00007206979,0.00008159126,0.00002786148,0.00006734487],"category_scores_gemma":[0.00002561009,0.0001168831,0.00009622188,0.000455108,0.00007925845,0.0001811052,0.00001376041,0.0001393644,0.00001133945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006108921,"about_ca_system_score_gemma":0.0000570652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001342287,"about_ca_topic_score_gemma":0.00004124667,"domain_scores_codex":[0.9990909,0.00005036467,0.0001186119,0.0003195518,0.0001627814,0.0002577957],"domain_scores_gemma":[0.9994577,0.0001317795,0.0000794962,0.0001467125,0.0001026011,0.00008166955],"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":[0.00005123258,0.00002847281,0.04896295,0.00005957042,0.0004142451,0.00003129698,0.00158815,0.1518691,0.0001585021,0.0001202313,0.001684375,0.7950318],"study_design_scores_gemma":[0.0003480755,0.0001357593,0.003734659,0.00001958367,0.0002793362,0.00001083937,0.00116465,0.9796314,0.002040033,0.003956048,0.008447237,0.0002323573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9067956,0.0001879988,0.09082831,0.0003328609,0.000076137,0.000118756,0.00003332804,0.0001523167,0.001474688],"genre_scores_gemma":[0.9930249,0.00005329388,0.004779863,0.001166121,0.00009429501,0.00000174973,0.0005474614,0.000005443358,0.0003268192],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8277623,"threshold_uncertainty_score":0.4766354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01924395102055943,"score_gpt":0.2191049878074552,"score_spread":0.1998610367868958,"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."}}