{"id":"W3217073048","doi":"10.1007/s10596-021-10104-8","title":"Latent-space inversion (LSI): a deep learning framework for inverse mapping of subsurface flow data","year":2021,"lang":"en","type":"article","venue":"Computational Geosciences","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Energi Simulation","keywords":"Computer science; Hydrogeology; Curse of dimensionality; Data mapping; Redundancy (engineering); Dimensionality reduction; Data redundancy; Data mining; Data modeling; Synthetic data; Artificial intelligence; Machine learning; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004242423,0.00009254469,0.0001414548,0.00008850211,0.0001114287,0.0000475668,0.0002759337,0.0000578956,0.0000279462],"category_scores_gemma":[0.0006569218,0.00009770441,0.00004010547,0.0005407144,0.00004962651,0.0002367931,0.00009599882,0.0001249831,0.000004786635],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001981893,"about_ca_system_score_gemma":0.00004620993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004527779,"about_ca_topic_score_gemma":0.000002826874,"domain_scores_codex":[0.9991012,0.00004547107,0.0001938263,0.0002286609,0.0002638457,0.000166988],"domain_scores_gemma":[0.9988391,0.0007353023,0.00004326759,0.0001828293,0.0001380203,0.00006142607],"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":[0.000001997761,0.000006482862,0.001618318,0.00008031705,0.00001269553,0.000001260134,0.000353008,0.9938138,0.0003435609,0.0009073851,0.00008554807,0.002775702],"study_design_scores_gemma":[0.000165984,0.00001080859,0.002319693,0.00005539076,0.000005541641,0.000001723078,0.0002695103,0.9899133,0.0002743046,0.004804221,0.002070734,0.0001087305],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2102769,0.0003612331,0.7887031,0.00008839442,0.0003478085,0.00005641647,0.00001467276,0.0000843091,0.00006721263],"genre_scores_gemma":[0.3498733,0.00002977113,0.6498789,0.00001292337,0.00003479482,0.000002211561,0.00009255651,0.000008250703,0.00006723742],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1395965,"threshold_uncertainty_score":0.398427,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0564275407084321,"score_gpt":0.3019684970313588,"score_spread":0.2455409563229267,"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."}}