{"id":"W4392595534","doi":"10.5194/egusphere-egu24-128","title":"Numeraical twins and deep neural network to predict groundwater flow ","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ministère des Ressources naturelles et des Forêts (Québec); Université du Québec à Chicoutimi","funders":"","keywords":"Groundwater; Artificial neural network; Flow (mathematics); Environmental science; Groundwater flow; Hydrology (agriculture); Computer science; Geology; Water resource management; Artificial intelligence; Geotechnical engineering; Mechanics; Aquifer; Physics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0002539638,0.0005927156,0.0003259258,0.000461823,0.0001821435,0.0004269724,0.0005736639,0.0006099859,0.001045224],"category_scores_gemma":[0.0008429624,0.0002916507,0.0003721284,0.0004072492,0.0003035019,0.0005411632,0.0004840871,0.000602378,0.0002063432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007656257,"about_ca_system_score_gemma":0.0005888467,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03211512,"about_ca_topic_score_gemma":0.0334766,"domain_scores_codex":[0.9999204,0.00001573938,0.000004305386,0.00002585376,0.00001828663,0.00001555073],"domain_scores_gemma":[0.9998596,0.00005521005,0.00001797657,0.00001318908,0.0000383855,0.00001568206],"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":[0.00003942035,0.0000338233,0.001732231,0.000007881627,0.00002482143,0.00002053824,0.000009316455,0.9752344,0.001047253,0.0007049317,0.0004803756,0.02066496],"study_design_scores_gemma":[5.031323e-7,0.0000033286,0.00009622236,4.338116e-7,0.000001158237,8.96814e-7,0.000001070232,0.9995463,0.0001290719,0.0001775265,0.00004272342,7.08216e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5441525,0.000625834,0.445999,0.0006540003,0.0001938135,0.0000539753,0.0007137427,0.002033112,0.005574116],"genre_scores_gemma":[0.9375574,0.0001090165,0.05791212,0.00007020024,0.00002743829,0.00003181881,0.000708538,0.00004654418,0.003536926],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03211512,"threshold_uncertainty_score":0.06385636,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01862872823071409,"score_gpt":0.232566155016577,"score_spread":0.2139374267858629,"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."}}