{"id":"W4280597605","doi":"10.1007/s10596-022-10151-9","title":"Application of machine learning to characterize gas hydrate reservoirs in Mackenzie Delta (Canada) and on the Alaska north slope (USA)","year":2022,"lang":"en","type":"article","venue":"Computational Geosciences","topic":"Methane Hydrates and Related Phenomena","field":"Environmental Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"National Energy Technology Laboratory; U.S. Department of Energy","keywords":"Permafrost; Geology; Well logging; Clathrate hydrate; Wireline; Hydrogeology; Drilling; Saturation (graph theory); Natural gas; Formation evaluation; Logging while drilling; Hydrate; Hydrology (agriculture); Mineralogy; Petroleum engineering; Geotechnical engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004801589,0.00007449673,0.00008515902,0.00004673455,0.0003558557,0.00001749541,0.000285079,0.000009494865,0.0004285644],"category_scores_gemma":[0.00004428755,0.00005423168,0.00001168908,0.0006763904,0.0001183332,0.0000575607,0.0002637274,0.0001596698,0.000008830148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007031718,"about_ca_system_score_gemma":0.00004227509,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.0807799,"about_ca_topic_score_gemma":0.1106349,"domain_scores_codex":[0.9987472,0.0001238172,0.000178796,0.0002504489,0.0005496892,0.0001500103],"domain_scores_gemma":[0.9995244,0.0001956389,0.000127972,0.00008473158,0.00000828439,0.0000589555],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.00001765558,0.00002533165,0.1645978,0.000002043165,0.000001797936,0.000001529948,0.0004054703,0.8299009,0.000346775,0.0002406666,0.00006843466,0.004391587],"study_design_scores_gemma":[0.00009696046,0.0001155332,0.615392,0.000003431544,0.000001788958,0.000002948581,0.0001391583,0.3778457,0.00004400262,0.001079799,0.005191651,0.00008693826],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9961213,0.00001849109,0.0003950864,0.002665412,0.00005235665,0.0001891425,0.0000427513,0.000004407193,0.0005110428],"genre_scores_gemma":[0.9987569,0.000006843019,0.0004074513,0.0005893002,0.000006287763,0.00003609983,0.00005493409,0.000003753099,0.0001383647],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4520552,"threshold_uncertainty_score":0.9253412,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01325838761214692,"score_gpt":0.212134017688651,"score_spread":0.1988756300765041,"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."}}