{"id":"W4415515968","doi":"10.1016/j.pce.2025.104159","title":"Machine learning-driven porosity prediction: A case study from the Cretaceous Mata Series, Canterbury Basin, New Zealand","year":2025,"lang":"en","type":"article","venue":"Physics and Chemistry of the Earth Parts A/B/C","topic":"Hydrocarbon exploration and reservoir analysis","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Government of Northwest Territories","funders":"China University of Petroleum, Beijing","keywords":"Porosity; Artificial neural network; Linear regression; Mean squared error; Series (stratigraphy); Submarine pipeline; Correlation coefficient; Effective porosity","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":[0.00005412404,0.0001240301,0.0001765027,0.00000530984,0.0001705905,0.00004572626,0.0001410323,0.00003538394,0.00003923821],"category_scores_gemma":[0.00001068215,0.00008031327,0.00006943395,0.0001426697,0.00005156728,0.00005410257,0.00008804831,0.0001706217,7.933532e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007718565,"about_ca_system_score_gemma":0.00002782731,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00102121,"about_ca_topic_score_gemma":0.000517555,"domain_scores_codex":[0.9994397,0.00003253133,0.0001640502,0.0001390493,0.0001219076,0.0001027707],"domain_scores_gemma":[0.9995227,0.00002965795,0.00004696551,0.0003259427,0.0000247276,0.0000500427],"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":[0.0001163267,0.0004591376,0.5358533,0.0002819902,0.002949705,0.000236167,0.01283064,0.3977678,0.02270182,0.00002042894,0.02121402,0.005568682],"study_design_scores_gemma":[0.003993121,0.0001487828,0.02071041,0.0004030025,0.001820105,0.0002643714,0.007025193,0.699641,0.1048694,0.001355431,0.1587803,0.0009888372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9975253,0.0006549706,0.0002344471,0.0005881921,0.00009425412,0.0001186044,0.0000714266,0.00005698083,0.0006557974],"genre_scores_gemma":[0.9952647,0.0001315439,0.000009520379,0.0000257645,0.0001266381,0.000005257271,0.00002632089,0.00000927664,0.004400995],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5151429,"threshold_uncertainty_score":0.327508,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008203776193655265,"score_gpt":0.1999341790197307,"score_spread":0.1917304028260754,"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."}}