{"id":"W4405718147","doi":"10.1109/access.2024.3521895","title":"Predicting Subsurface Layer Thickness and Seismic Wave Velocity Using Deep Learning: Knowledge Distillation Approach","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Seismic Waves and Analysis","field":"Earth and Planetary Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Seneca Polytechnic","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Layer (electronics); Geology; Computer science; Deep learning; Geophysics; Artificial intelligence; Materials science; Composite material","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":[0.0003677364,0.0001527435,0.0001818406,0.0001058007,0.0003067492,0.0005270776,0.0001459786,0.00009260143,0.0001295396],"category_scores_gemma":[0.00002970201,0.0001241721,0.00005894074,0.0004976387,0.00006569651,0.0005784049,0.00002506574,0.0002638226,0.0000238446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009908914,"about_ca_system_score_gemma":0.00003751744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002399715,"about_ca_topic_score_gemma":0.0002268123,"domain_scores_codex":[0.9988798,0.0001010977,0.0001939732,0.0003933579,0.0001777048,0.0002540011],"domain_scores_gemma":[0.999523,0.0001759385,0.00005711789,0.0001081518,0.00003930656,0.00009642787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001291581,0.00001420372,0.4790401,0.0002562721,0.0001099307,0.00002049929,0.00174983,0.4521414,0.0001068027,0.00002555606,0.00005592846,0.06646655],"study_design_scores_gemma":[0.00006298877,0.00001016454,0.09817915,0.00003748134,0.00007308996,0.00002553573,0.0003016061,0.900103,0.00004637248,0.0002526005,0.0007541451,0.0001538793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9621923,0.002261928,0.03155117,0.00004931813,0.0004424909,0.00008858959,0.00002036488,0.0001074001,0.003286434],"genre_scores_gemma":[0.9987586,0.0001272002,0.000441749,0.00003565784,0.0002897625,4.911781e-7,0.00006552407,0.000008156813,0.000272895],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4479616,"threshold_uncertainty_score":0.5082622,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05397369601468319,"score_gpt":0.2842391989934549,"score_spread":0.2302655029787717,"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."}}