{"id":"W4396809200","doi":"10.1016/j.geoen.2024.212909","title":"An intelligent lithology recognition system for continental shale by using digital coring images and convolutional neural networks","year":2024,"lang":"en","type":"article","venue":"Geoenergy Science and Engineering","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Coring; Convolutional neural network; Oil shale; Lithology; Geology; Computer science; Artificial intelligence; Geochemistry; Paleontology; Drilling; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002010308,0.0007502561,0.0005419042,0.0009348886,0.0003273242,0.0004941527,0.0007979018,0.0005729236,0.002477506],"category_scores_gemma":[0.0002393685,0.0002940157,0.0004944444,0.0005556602,0.0001505658,0.0005217576,0.0005570671,0.0004119288,0.001160524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005097419,"about_ca_system_score_gemma":0.000903541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0156761,"about_ca_topic_score_gemma":0.03160746,"domain_scores_codex":[0.9998875,0.000003886053,0.000006456235,0.00004228269,0.00003464506,0.00002521186],"domain_scores_gemma":[0.9998655,0.00001267878,0.00001364668,0.000016881,0.00007417369,0.0000171725],"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":[0.0003905604,0.0002799382,0.006822513,0.0001268606,0.0001720531,0.0002289472,0.00005276498,0.02049189,0.1364756,0.0005234066,0.009814113,0.8246214],"study_design_scores_gemma":[0.00005530707,0.0001915404,0.01380508,0.00002047539,0.0001352436,0.0001486192,0.00004860306,0.8919086,0.08654717,0.0007411142,0.006348357,0.0000497529],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3677961,0.001402271,0.5856776,0.0004809937,0.0005715499,0.0003035293,0.002464448,0.033482,0.007821558],"genre_scores_gemma":[0.7759824,0.0004906862,0.2035667,0.00041175,0.0001053626,0.0001481,0.003564999,0.0001987784,0.01553132],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0156761,"threshold_uncertainty_score":0.03116971,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01254165926271084,"score_gpt":0.20979623237608,"score_spread":0.1972545731133692,"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."}}