{"id":"W4411725984","doi":"10.1109/tgrs.2025.3583970","title":"Toward Understanding the Benefits of Neural Network Parameterizations in Geophysical Inversions: A Study With Neural Fields","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial neural network; Geophysics; Computer science; Geology; Remote sensing; Artificial intelligence","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":[0.0001793891,0.00009327101,0.000123507,0.0001463896,0.0004171263,0.00004934656,0.0001012126,0.00003388434,0.000004907605],"category_scores_gemma":[0.000006063767,0.00005972107,0.00002868875,0.0008149764,0.0002503019,0.0001403489,0.000001592916,0.000206932,5.396197e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007684815,"about_ca_system_score_gemma":0.00003306888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005706629,"about_ca_topic_score_gemma":0.0009526319,"domain_scores_codex":[0.9992172,0.00008190843,0.0001457538,0.0002090262,0.0001550756,0.0001910804],"domain_scores_gemma":[0.9995601,0.0002126714,0.00003908283,0.000134599,0.00002035699,0.00003325132],"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":[0.0001574018,0.00005731488,0.003005585,0.00001898137,0.00002100064,0.0000124745,0.002381046,0.2113271,0.00002177947,0.00003240411,0.00006328598,0.7829016],"study_design_scores_gemma":[0.0002206299,0.0002969659,0.009426928,0.0001197906,0.00002404293,0.00001553591,0.003564517,0.9854025,0.0001743313,0.0006571875,0.00001077353,0.00008679963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6655955,0.00002713953,0.3326986,0.001048579,0.0002270718,0.0001854956,0.000003456939,0.00002807475,0.0001861023],"genre_scores_gemma":[0.9967844,0.00003533752,0.002314318,0.0008092464,0.000009693432,6.770943e-8,6.966467e-7,0.00000156029,0.00004465804],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7828148,"threshold_uncertainty_score":0.8626754,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03325416144474953,"score_gpt":0.2364053160777461,"score_spread":0.2031511546329966,"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."}}