{"id":"W4396900897","doi":"10.5194/hess-2024-111","title":"Data-driven modeling of hydraulic head time series: results and lessons learned from the 2022 groundwater modeling challenge","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Horizon 2020; Canada First Research Excellence Fund","keywords":"Groundwater; Series (stratigraphy); Head (geology); Hydraulic head; Groundwater model; Computer science; Hydrology (agriculture); Environmental science; Engineering; Geology; Groundwater flow; Geotechnical engineering; Aquifer; Geomorphology","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.001067337,0.0003980282,0.0004980622,0.00003560231,0.000196364,0.0001601142,0.001356606,0.0003663878,0.0006860326],"category_scores_gemma":[0.0001652071,0.0002578094,0.00009685987,0.0001209351,0.0002899097,0.0001790942,0.01307055,0.001176133,0.0004332185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001057305,"about_ca_system_score_gemma":0.0000297817,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01061946,"about_ca_topic_score_gemma":0.001484228,"domain_scores_codex":[0.9966072,0.0001976808,0.0006639066,0.001587236,0.000528884,0.000415116],"domain_scores_gemma":[0.9978346,0.0001695189,0.0001434581,0.001725811,0.00001357031,0.0001130657],"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":[0.00006801271,0.00004727226,0.0000075289,0.00002904983,0.00006174133,0.00001018244,0.001223171,0.9941116,0.0003526153,0.00003916406,0.0005253438,0.00352433],"study_design_scores_gemma":[0.0001582083,0.00005828375,0.000005502792,0.0002038586,0.00008507963,0.000004131561,0.00006216013,0.9594705,0.00001245166,0.03870185,0.0009467889,0.0002912179],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9463615,0.000640691,0.00524616,0.03124727,0.0002867537,0.0004860106,0.00111417,0.0002843316,0.01433308],"genre_scores_gemma":[0.9920083,0.0005463591,0.005196864,0.0002022698,0.0001386825,0.00001776946,0.00061971,0.00005486669,0.001215157],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04564678,"threshold_uncertainty_score":0.9999874,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1703569354296154,"score_gpt":0.3172107073941534,"score_spread":0.1468537719645379,"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."}}