{"id":"W4323981323","doi":"10.1016/j.geoen.2023.211660","title":"Lost circulation monitoring using bi-directional LSTM and data augmentation","year":2023,"lang":"en","type":"article","venue":"Geoenergy Science and Engineering","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":29,"is_retracted":false,"has_abstract":false,"ca_institutions":"Memorial University of Newfoundland","funders":"National Natural Science Foundation of China","keywords":"Computer science; Circulation (fluid dynamics); Field (mathematics); Artificial intelligence; Lost circulation; Volume (thermodynamics); Dither; Pattern recognition (psychology); Data mining; Machine learning; Computer vision; Mathematics; 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":[0.0003115049,0.0001142118,0.00008342856,0.0002979461,0.0001901663,0.0001128248,0.0001369827,0.00003646731,0.000001945272],"category_scores_gemma":[0.000048774,0.000121437,0.00000753476,0.0007352404,0.00005270159,0.0008630188,0.0001238226,0.00008132176,0.000002936068],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000085713,"about_ca_system_score_gemma":0.0000225835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003681957,"about_ca_topic_score_gemma":0.000001585949,"domain_scores_codex":[0.9990658,0.000002415655,0.0001204433,0.0002542914,0.0002427351,0.0003143099],"domain_scores_gemma":[0.9996645,0.00002007604,0.00001415754,0.0001756719,0.0000454438,0.00008012747],"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":[8.182946e-7,7.234599e-7,0.004248556,0.00003325399,0.000008250731,0.00000349853,0.0001380819,0.7262236,0.258247,0.000138536,0.00002395462,0.01093366],"study_design_scores_gemma":[0.00009097223,0.000003812627,0.1058763,0.00005195814,0.000007128519,0.00002331462,0.0001179327,0.8845103,0.008384635,0.00003781324,0.0007433026,0.0001524821],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.988901,0.0001864361,0.008903116,0.00001390562,0.001559682,0.0000417854,0.000004396011,0.0002799701,0.0001097744],"genre_scores_gemma":[0.9959747,0.0001680805,0.003427383,0.000004007108,0.0003853964,0.000003119286,0.000008876301,0.00001722763,0.0000111983],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2498624,"threshold_uncertainty_score":0.4952055,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02605270098623,"score_gpt":0.2572780049117755,"score_spread":0.2312253039255456,"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."}}