{"id":"W4409349159","doi":"10.1016/j.advwatres.2025.104955","title":"Tackling water table depth modeling via machine learning: From proxy observations to verifiability","year":2025,"lang":"en","type":"article","venue":"Advances in Water Resources","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Environment and Climate Change Canada","keywords":"Proxy (statistics); Water table; Computer science; Table (database); Hydrology (agriculture); Machine learning; Data mining; Geology; Groundwater; Geotechnical engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003306107,0.0001702858,0.0002017478,0.00006990665,0.00035005,0.00003221068,0.0002974284,0.00005356278,0.0001960753],"category_scores_gemma":[0.00003424897,0.0001094245,0.00003206894,0.0001725714,0.0001073752,0.0004321886,0.0006620841,0.0001951684,0.0001861517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008223365,"about_ca_system_score_gemma":9.793348e-7,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001651791,"about_ca_topic_score_gemma":0.00167187,"domain_scores_codex":[0.9985377,0.00009146338,0.0002798487,0.000493991,0.0001473904,0.0004496005],"domain_scores_gemma":[0.999658,0.00003683243,0.00001954356,0.0002375613,0.000007095407,0.00004091528],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005066968,0.00003475912,0.4076522,0.000009338283,0.00001174818,0.000002711003,0.003071015,0.5855642,0.002981418,0.000004884089,0.00001565921,0.000601395],"study_design_scores_gemma":[0.0007505541,0.0001208884,0.012468,0.00006317803,0.0000489037,3.925326e-7,0.0005071298,0.385758,0.0384888,0.01817333,0.5430625,0.0005582646],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9822406,0.0002859269,0.01075108,0.001529548,0.0001321303,0.0003064772,0.000001656487,0.00007663109,0.004676014],"genre_scores_gemma":[0.995487,0.00007115095,0.001743996,0.0005654733,0.00002006121,0.00009874017,0.00003397459,0.00001022507,0.001969416],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5430469,"threshold_uncertainty_score":0.44622,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01209878178312852,"score_gpt":0.2370961120783292,"score_spread":0.2249973302952007,"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."}}