{"id":"W4414338273","doi":"10.1016/j.jappgeo.2025.105955","title":"Machine learning-driven velocity–resistivity modeling: A novel explicit framework for near-surface characterization","year":2025,"lang":"en","type":"article","venue":"Journal of Applied Geophysics","topic":"Geophysical and Geoelectrical Methods","field":"Earth and Planetary Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University Canada West; University of British Columbia","funders":"Institute of Postgraduate Studies, Universiti Sains Malaysia; Helmholtz-Zentrum Potsdam - Deutsches GeoForschungsZentrum GFZ; Ministry of Higher Education, Malaysia; Adekunle Ajasin University; Tertiary Education Trust Fund; Universiti Sains Malaysia","keywords":"Electrical resistivity tomography; Cluster analysis; Artificial neural network; Terrain; Support vector machine; Interpolation (computer graphics); Geophysical imaging; Stability (learning theory); Scalability; Decision tree","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0003433853,0.0001942633,0.0004438043,0.00004047616,0.0002798711,0.0001025767,0.0002765079,0.0001432042,0.00003541074],"category_scores_gemma":[0.0001681264,0.0001588669,0.0001906849,0.0005944817,0.00003559754,0.0001419857,0.00002096037,0.0006507263,0.00002032629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000104292,"about_ca_system_score_gemma":0.0001193509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005848621,"about_ca_topic_score_gemma":0.000005346572,"domain_scores_codex":[0.998703,0.00004549379,0.0004175954,0.0002256968,0.0002937209,0.0003145193],"domain_scores_gemma":[0.9987146,0.0004887457,0.0003430264,0.0001347281,0.0001947216,0.0001241495],"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":[0.001317078,0.0003999776,0.002023265,0.0001563563,0.0002236664,0.000003281827,0.0004008044,0.4754698,0.01355692,0.02901675,0.00002936773,0.4774027],"study_design_scores_gemma":[0.0005935584,0.0002911418,0.04416926,0.00004654259,0.00008619483,0.000001398659,0.00002671759,0.8462502,0.0008605536,0.1054845,0.001978905,0.0002109436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4514695,0.00003612872,0.5474299,0.0003022332,0.0001999553,0.00015718,0.00003257686,0.00001763326,0.0003549656],"genre_scores_gemma":[0.920047,0.00002949698,0.07910559,0.0003423044,0.0002941194,0.000001713904,0.00005130146,0.000006502413,0.0001219991],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4771917,"threshold_uncertainty_score":0.6478404,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01943737425224455,"score_gpt":0.2522558215212814,"score_spread":0.2328184472690368,"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."}}