{"id":"W4415989033","doi":"10.2139/ssrn.5714989","title":"An Explainable Optimization-Driven Framework for Accurate and Interpretable Groundwater-Level Prediction Toward Sustainable Management","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval; University of Ottawa","funders":"","keywords":"Groundwater recharge; Mean squared error; Groundwater; Baseline (sea); Bayesian probability; Precipitation; Hydrogeology; Hyperparameter; Sustainable management","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000865113,0.000656559,0.0005847243,0.0005169733,0.0003096292,0.001142479,0.001333087,0.001053512,0.002564044],"category_scores_gemma":[0.003220476,0.000482121,0.0007488378,0.0005922734,0.0007434403,0.0009940597,0.001161041,0.001458557,0.0003026002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007164713,"about_ca_system_score_gemma":0.001252597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00831861,"about_ca_topic_score_gemma":0.007801381,"domain_scores_codex":[0.9997258,0.000109432,0.00001545706,0.0000602832,0.00006403193,0.00002498585],"domain_scores_gemma":[0.9991248,0.0005425863,0.00009137721,0.0000737528,0.0001320285,0.00003545711],"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":[0.00002186008,0.00002178784,0.000300007,0.00002986036,0.00002956631,0.00004402469,0.00003306505,0.9498596,0.00117771,0.03503074,0.0006015486,0.01285029],"study_design_scores_gemma":[0.000001599781,0.000003000362,0.00002583175,0.000001239419,0.000001583482,0.000001620299,0.000001302549,0.9906866,0.00008428952,0.009028035,0.0001631392,0.000001703736],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005703692,0.00008458818,0.9925418,0.0002605648,0.00002426848,0.00001438172,0.0001165398,0.0002541042,0.001000031],"genre_scores_gemma":[0.5723839,0.0003238936,0.4230341,0.0002186101,0.0001554164,0.0001898723,0.0005235053,0.0002372415,0.002933447],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00831861,"threshold_uncertainty_score":0.01654035,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02005282082196004,"score_gpt":0.2744041750805372,"score_spread":0.2543513542585771,"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."}}