{"id":"W4399130561","doi":"10.2166/hydro.2024.275","title":"Accelerating regional-scale groundwater flow simulations with a hybrid deep neural network model incorporating mixed input types: A case study of the northeast Qatar aquifer","year":2024,"lang":"en","type":"article","venue":"Journal of Hydroinformatics","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Sultan Qaboos University; Khalifa University of Science, Technology and Research; Hamad Bin Khalifa University","keywords":"Aquifer; Groundwater flow; Groundwater; Scale (ratio); Groundwater model; Hydrology (agriculture); Environmental science; Artificial neural network; Geology; Flow (mathematics); Geotechnical engineering; Geography; Computer science; Cartography; Mathematics; Machine learning","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":[0.0004577065,0.0001846775,0.0002928476,0.0001457473,0.0001371711,0.0001379507,0.0001918166,0.00004048641,0.00000452745],"category_scores_gemma":[0.00003234521,0.0001169411,0.0001039986,0.0003908986,0.00002431616,0.0006922128,0.00004660629,0.0004622297,8.556714e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006031579,"about_ca_system_score_gemma":0.000048672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007866629,"about_ca_topic_score_gemma":0.00008637166,"domain_scores_codex":[0.9983774,0.00005385089,0.0009144819,0.00006450145,0.0003978327,0.0001918804],"domain_scores_gemma":[0.999137,0.0002069085,0.0002029252,0.0002479852,0.000127233,0.00007790359],"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":[0.00001153945,0.00002915717,0.0008009346,0.0001536948,0.0001184041,0.0000976794,0.004000158,0.9940323,0.00001701866,0.000008487681,0.000062781,0.0006678987],"study_design_scores_gemma":[0.0004435148,0.0001324884,0.00007227078,0.0001702188,0.00009115909,0.001903706,0.0008393482,0.9960456,0.00002096446,0.000128537,0.00001787407,0.0001342605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8540759,0.00009798417,0.1452401,0.00002473271,0.0002432737,0.0001731759,0.00000352944,0.00004924178,0.00009212834],"genre_scores_gemma":[0.9387556,0.000002434597,0.06100208,0.00001487517,0.00017106,0.000002716064,0.000002783214,0.00003551269,0.00001297463],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08467968,"threshold_uncertainty_score":0.4768718,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02530332618753747,"score_gpt":0.2524863562469032,"score_spread":0.2271830300593657,"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."}}