{"id":"W4282840164","doi":"10.3390/en15124288","title":"Applying Machine Learning to Predict the Rate of Penetration for Geothermal Drilling Located in the Utah FORGE Site","year":2022,"lang":"en","type":"article","venue":"Energies","topic":"Drilling and Well Engineering","field":"Engineering","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Drilling; Rate of penetration; Artificial neural network; Random forest; Geothermal gradient; Machine learning; Hyperparameter; Preprocessor; Data pre-processing; Computer science; Penetration rate; Artificial intelligence; Data mining; Engineering; Petroleum engineering; Geology; Mechanical 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006188926,0.0001014564,0.0001086346,0.00008714197,0.000168434,0.00002636401,0.0001755733,0.00001945223,0.00001015604],"category_scores_gemma":[0.00003446485,0.00007470955,0.00004286511,0.000256634,0.00000786996,0.00005127466,0.00003320906,0.000188382,8.418526e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002868308,"about_ca_system_score_gemma":0.000006447064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001099451,"about_ca_topic_score_gemma":0.00005679588,"domain_scores_codex":[0.9993733,0.00004806497,0.0001837165,0.0000964558,0.0001101288,0.0001883955],"domain_scores_gemma":[0.9996219,0.0001975317,0.00002688775,0.0001270917,0.00001261455,0.00001400298],"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":[0.00001074512,0.00000429692,0.0005574928,0.00003981747,0.00001321569,5.897585e-7,0.002163881,0.9806204,0.01480417,0.0002966249,0.00003380657,0.001454909],"study_design_scores_gemma":[0.0001745357,0.00004116119,0.0008735182,0.00001848506,0.000008949268,0.000002077399,0.000788862,0.9776443,0.005373608,0.00003101432,0.0149473,0.0000961542],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.965614,0.0004700924,0.03278448,0.000070496,0.0002242577,0.0003946501,0.00001788299,0.0001585111,0.0002656119],"genre_scores_gemma":[0.9989874,0.00003175113,0.0002209483,0.00003587174,0.00007168746,0.0004971065,0.00003835544,0.00003299053,0.00008390546],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03337336,"threshold_uncertainty_score":0.3046567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007606805115766618,"score_gpt":0.1908804147961874,"score_spread":0.1832736096804208,"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."}}