{"id":"W4388424342","doi":"10.1190/geo2023-0352.1","title":"Quantitative characterization of organic and inorganic pores in shale based on deep learning","year":2023,"lang":"en","type":"article","venue":"Geophysics","topic":"Hydrocarbon exploration and reservoir analysis","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Object Research Systems (Canada)","funders":"National Natural Science Foundation of China","keywords":"Oil shale; Focused ion beam; Materials science; Porosity; Artificial neural network; Scanning electron microscope; Segmentation; Geology; Artificial intelligence; Computer science; Mineralogy; Pattern recognition (psychology); Ion; Composite material; Chemistry","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":[0.00005696432,0.00006555401,0.0001161601,0.0001570961,0.00002090474,0.000009697246,0.00003698676,0.00003093916,0.00002009317],"category_scores_gemma":[0.00002529406,0.00006637153,0.00001955771,0.0007994286,0.00001265505,0.00007268614,0.00001094261,0.00008674988,0.00004706981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001275937,"about_ca_system_score_gemma":0.000006729028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005436528,"about_ca_topic_score_gemma":0.00002424854,"domain_scores_codex":[0.9995946,0.00002426268,0.0001172754,0.0000826945,0.00009160548,0.00008953712],"domain_scores_gemma":[0.999827,0.00003647472,0.00002583668,0.00007053204,0.00001968196,0.00002043502],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001404158,0.00003416317,0.01141568,0.0001177286,0.00003552596,0.000006154279,0.002551374,0.2490238,0.7346827,0.0003428825,0.000005239281,0.001770693],"study_design_scores_gemma":[0.0001599685,0.00004363298,0.06486759,0.00002035842,0.000007142932,5.553933e-8,0.0002250839,0.9257736,0.008679886,0.0001278366,0.00001589967,0.00007894883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9970759,0.000008667713,0.002545449,0.00003690978,0.00002847805,0.00004240857,0.000002110996,0.00009669134,0.0001634044],"genre_scores_gemma":[0.9997106,0.00007338233,0.0000256282,0.0000136853,0.00001311894,0.000004265325,0.0001015811,0.0000169123,0.00004084597],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7260028,"threshold_uncertainty_score":0.2706552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009315333828344232,"score_gpt":0.2110941462425932,"score_spread":0.2017788124142489,"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."}}