{"id":"W4389044751","doi":"10.1016/j.geoen.2023.212529","title":"Identification of quartz cement in sandstone through deep learning segmentation of electron microscopy images","year":2023,"lang":"en","type":"article","venue":"Geoenergy Science and Engineering","topic":"Drilling and Well Engineering","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Azrieli Foundation","keywords":"Quartz; Cementation (geology); Geology; Petrophysics; Cement; Mineralogy; Petrography; Scanning electron microscope; Porosity; Convolutional neural network; Artificial intelligence; Materials science; Composite material; Geotechnical engineering; Computer science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004540144,0.00009912617,0.0001356998,0.0003434996,0.00003730431,0.0000207937,0.00009887816,0.00002990487,0.00000142872],"category_scores_gemma":[0.00003969318,0.0001111754,0.00001755849,0.001083709,0.00004703543,0.0002899786,0.000021796,0.00008331696,0.000001741235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005417006,"about_ca_system_score_gemma":0.00001145313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003919659,"about_ca_topic_score_gemma":0.00000350508,"domain_scores_codex":[0.999087,0.000004323463,0.0002785485,0.0001490322,0.0002073011,0.000273756],"domain_scores_gemma":[0.9997723,0.00002598911,0.00003515205,0.0000951335,0.00004103768,0.00003035136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[6.886006e-7,0.000002028939,0.0001249265,0.00006107717,0.000002755731,3.102754e-7,0.0003372205,0.5239726,0.4744599,0.00008872625,0.000002815684,0.0009469468],"study_design_scores_gemma":[0.0000919352,0.00001609366,0.003023861,0.00003730992,0.000002772683,8.194137e-7,0.0001329409,0.4720154,0.524529,0.00001318894,0.00006494642,0.00007174868],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9593279,0.0005244336,0.03967587,0.000007822116,0.0001812635,0.00005019821,0.000001040342,0.0001471306,0.00008432725],"genre_scores_gemma":[0.9984403,0.0007691752,0.0007200153,0.000001172699,0.00001569472,0.00001132131,0.000005437949,0.00001483014,0.00002204833],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05195724,"threshold_uncertainty_score":0.4533601,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00439717401407726,"score_gpt":0.2277545058852002,"score_spread":0.2233573318711229,"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."}}