{"id":"W2995440822","doi":"10.1016/j.petrol.2019.106805","title":"Determination of an infill well placement using a data-driven multi-modal convolutional neural network","year":2019,"lang":"en","type":"article","venue":"Journal of Petroleum Science and Engineering","topic":"Drilling and Well Engineering","field":"Engineering","cited_by":55,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Korea Institute of Geoscience and Mineral Resources; Ministry of Trade, Industry and Energy; Ewha Womans University; Computer Modelling Group; National Research Foundation of Korea; Korea Gas Corporation; Ministry of Science and Technology","keywords":"Convolutional neural network; Computer science; Artificial neural network; Modal; Feed forward; Infill; Feature (linguistics); Artificial intelligence; Algorithm; Pattern recognition (psychology); Engineering; Structural engineering; Control engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002213653,0.0008940328,0.0005475797,0.0007667698,0.0003362122,0.000590539,0.0007145566,0.001147933,0.00156477],"category_scores_gemma":[0.0008756408,0.0005426275,0.0004296682,0.0004067001,0.0003130002,0.0006914476,0.0007726321,0.0007881126,0.0007236769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004799393,"about_ca_system_score_gemma":0.001259027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00663407,"about_ca_topic_score_gemma":0.01262036,"domain_scores_codex":[0.9998914,0.000009211179,0.000005119596,0.00003785002,0.00003308858,0.00002332308],"domain_scores_gemma":[0.9997404,0.00006483557,0.00003911583,0.00002055829,0.0001038634,0.00003125693],"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":[0.0003493911,0.0001604938,0.008786194,0.0001263484,0.00006038553,0.0003734479,0.00007536309,0.6789775,0.09021208,0.002150513,0.00231915,0.2164091],"study_design_scores_gemma":[0.000003109962,0.000009677459,0.0005199646,0.000003475606,0.00000398639,0.00001395002,0.000005407843,0.9953973,0.003628575,0.0002534501,0.0001565212,0.000004645458],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1656389,0.0001989879,0.8287886,0.0002004468,0.00006880524,0.00005435981,0.0002621002,0.002188153,0.002599576],"genre_scores_gemma":[0.8418703,0.00009130966,0.155321,0.00005957752,0.00002117575,0.00003309168,0.0003372182,0.0001010792,0.002165234],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00663407,"threshold_uncertainty_score":0.01319087,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01766097858687922,"score_gpt":0.2398608259998425,"score_spread":0.2221998474129633,"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."}}