{"id":"W2974397275","doi":"10.2118/196096-ms","title":"Formation Lithology Classification: Insights into Machine Learning Methods","year":2019,"lang":"en","type":"article","venue":"SPE Annual Technical Conference and Exhibition","topic":"Hydrocarbon exploration and reservoir analysis","field":"Engineering","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"Apache (Canada)","funders":"","keywords":"Machine learning; Artificial intelligence; Computer science; Artificial neural network; Feature selection; Statistical classification; Algorithm; Supervised learning; Classifier (UML); Unsupervised learning; Data mining","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":[0.0002010109,0.0001182634,0.0001825061,0.0001465331,0.00007408545,0.0000459394,0.00007483344,0.0001607556,0.0001522705],"category_scores_gemma":[0.00003460037,0.0001032132,0.00004561412,0.0002363173,0.00004661641,0.0004888152,0.00003374114,0.0002789183,0.0001323522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003302779,"about_ca_system_score_gemma":0.000009256784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000112988,"about_ca_topic_score_gemma":0.00004828904,"domain_scores_codex":[0.99923,0.00009875053,0.0002482101,0.0001787265,0.0001132893,0.0001310648],"domain_scores_gemma":[0.9996189,0.00003863058,0.00003989609,0.0001471879,0.00008695885,0.00006841501],"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":[0.00006859421,0.00009810199,0.001298452,0.0003700174,0.00008033877,0.000009371296,0.005514428,0.007123866,0.8119083,0.06089003,0.001444805,0.1111937],"study_design_scores_gemma":[0.0005483891,0.0002679962,0.002566285,0.00007191636,0.00004563639,0.00002263103,0.001797563,0.9157374,0.02143348,0.01764462,0.039394,0.0004701198],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3436823,0.0008358532,0.6233558,0.001592219,0.0001730587,0.0003483377,0.000005202583,0.0009610312,0.02904614],"genre_scores_gemma":[0.9952554,0.0008661084,0.003448739,0.00006749274,0.00003700651,0.00001964592,0.0001329503,0.00001144579,0.0001612376],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9086135,"threshold_uncertainty_score":0.4208911,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02516340085357922,"score_gpt":0.2916107581385323,"score_spread":0.2664473572849531,"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."}}