{"id":"W4385618269","doi":"10.2139/ssrn.4534117","title":"Leveraging Machine Learning in Discrete Fracture Network Modeling to Optimize Geothermal Well Placement in Utah Forge, USA","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Drilling and Well Engineering","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Forge; Geothermal gradient; Fracture (geology); Mining engineering; Computer science; Engineering; Geology; Geotechnical engineering; Mechanical engineering; Geophysics","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":[0.000563613,0.0005339389,0.0005888775,0.000573369,0.0006376669,0.0009627614,0.0007510125,0.00133672,0.001060725],"category_scores_gemma":[0.002092333,0.0006559426,0.0004722344,0.0006030966,0.0003900418,0.0008486912,0.0004256654,0.000736591,0.0001718484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001528156,"about_ca_system_score_gemma":0.001907445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1013356,"about_ca_topic_score_gemma":0.181872,"domain_scores_codex":[0.9998662,0.0000397767,0.000006344777,0.00004381342,0.00002334842,0.00002046143],"domain_scores_gemma":[0.9993419,0.0004027935,0.0000611397,0.00004645115,0.0001115038,0.00003624253],"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":[0.00001909962,0.0000229651,0.002301568,0.000007036665,0.000008962986,0.00001632243,0.000007808148,0.9930878,0.000187278,0.0002856588,0.0002761064,0.003779314],"study_design_scores_gemma":[0.000001799106,0.000004047151,0.000349799,7.902554e-7,0.000001933907,0.000001192218,0.000005182243,0.9992692,0.000111449,0.0002009515,0.00005226573,0.000001310175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9207996,0.0003008398,0.07152786,0.0009766457,0.00005198495,0.00004835845,0.0008830545,0.0006784329,0.004733225],"genre_scores_gemma":[0.9869673,0.00003618681,0.01162956,0.00002414954,0.000007028385,0.00001444419,0.0003289781,0.00003997428,0.0009524262],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1013356,"threshold_uncertainty_score":0.2014915,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.010304828597841,"score_gpt":0.220536707547351,"score_spread":0.21023187894951,"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."}}