{"id":"W4404749486","doi":"10.1061/jhyeff.heeng-6280","title":"Data-Driven Gray Box Modeling for Predicting Basin-Scale Groundwater Variations in Central Taiwan","year":2024,"lang":"en","type":"article","venue":"Journal of Hydrologic Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Smiths Detection (Canada)","funders":"","keywords":"Gray (unit); Structural basin; Scale (ratio); Groundwater; Hydrological modelling; Hydrology (agriculture); Geology; Environmental science; Cartography; Geomorphology; Climatology; Geography; Geotechnical 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":[0.001017988,0.0001590087,0.0002482166,0.0001254461,0.00006904777,0.00008803689,0.0004402311,0.0001069158,0.00008820066],"category_scores_gemma":[0.0002541162,0.0001228304,0.00009597357,0.0002480459,0.00003006412,0.0005457817,0.0001941422,0.000438796,0.00001008171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002394603,"about_ca_system_score_gemma":0.00001728984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003708769,"about_ca_topic_score_gemma":0.00002373159,"domain_scores_codex":[0.9984368,0.00003398139,0.0005460351,0.0002804103,0.0002431958,0.0004595782],"domain_scores_gemma":[0.9994621,0.0001391498,0.00008597223,0.0001919478,0.00001024323,0.0001106034],"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":[0.00001153385,0.00003883969,0.006431433,0.00002263031,0.00001988315,0.00005282587,0.0002495019,0.9892323,0.003357756,0.00003019047,0.0001027683,0.0004503169],"study_design_scores_gemma":[0.0001987271,0.0001603236,0.0007824572,0.00009368139,0.00003708482,0.0001332578,0.000008590774,0.9963935,0.0000643687,0.0005231883,0.001476925,0.0001279225],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7217405,0.00008761566,0.2767992,0.0005471822,0.0005210076,0.0001095673,0.0000137432,0.00006978567,0.0001113195],"genre_scores_gemma":[0.9651179,0.00001040762,0.03449218,0.00006191939,0.0002621746,0.00000518695,0.00001070452,0.00002278854,0.00001671334],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2433774,"threshold_uncertainty_score":0.5008876,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02526293117507837,"score_gpt":0.2436626313162373,"score_spread":0.2183997001411589,"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."}}