{"id":"W4293831714","doi":"10.2139/ssrn.4205046","title":"Optimization of Machine Learning Approaches for Shale Gas Production Forecast","year":2022,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Shale gas; Production (economics); Oil shale; Petroleum engineering; Environmental science; Computer science; Artificial intelligence; Engineering; Waste management; Economics","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":[0.001474011,0.00008685931,0.0001215735,0.0001361036,0.0001835319,0.0000124849,0.000103935,0.00002480615,0.00002335837],"category_scores_gemma":[0.00008840517,0.00009146127,0.00007279134,0.0001900026,0.000007123009,0.00009972954,0.0000155496,0.000831283,2.045684e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003439847,"about_ca_system_score_gemma":0.00009308585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002802971,"about_ca_topic_score_gemma":0.000004454287,"domain_scores_codex":[0.9989231,0.00006214916,0.0002068967,0.00009204413,0.0001511139,0.0005647275],"domain_scores_gemma":[0.9997627,0.00003594408,0.00006315343,0.00007691621,0.00003602255,0.0000252398],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002606283,0.00001278321,0.0002016469,0.00002681678,0.00005450641,8.838938e-8,0.0001234036,0.9868356,0.0001908453,0.001862886,0.00001238086,0.010653],"study_design_scores_gemma":[0.0003375374,0.0001587919,0.000009296343,0.000003723007,0.00001513758,0.00008169898,0.0003869867,0.9936313,0.0003080836,0.004102479,0.0008766176,0.00008834773],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1089527,0.00159068,0.8887831,0.00006610037,0.0002404789,0.0001403225,0.000002776842,0.0000792849,0.0001446109],"genre_scores_gemma":[0.9816975,0.0004571503,0.01695521,0.000001097307,0.0001571134,0.00003389167,0.00002980248,0.00004137547,0.0006268751],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8727448,"threshold_uncertainty_score":0.3729682,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02312327762030254,"score_gpt":0.2345424834093351,"score_spread":0.2114192057890326,"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."}}