{"id":"W4411245323","doi":"10.1007/s11004-025-10194-5","title":"Graph Neural Network Framework for Spatiotemporal Groundwater Level Forecasting","year":2025,"lang":"en","type":"article","venue":"Mathematical Geosciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal; Université du Québec à Chicoutimi; Institut National de la Recherche Scientifique","funders":"Natural Resources Canada","keywords":"Hydrogeology; Groundwater; Graph; Artificial neural network; Computer science; Geology; Data mining; Artificial intelligence; Theoretical computer science; Geotechnical engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004521266,0.0005233839,0.0006780322,0.00086417,0.0002709802,0.0007377919,0.001149943,0.0008746431,0.00270384],"category_scores_gemma":[0.001777078,0.000259075,0.0004264475,0.001333501,0.0004535996,0.001192902,0.0005211036,0.001012556,0.0004423751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009297003,"about_ca_system_score_gemma":0.0008454521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03106816,"about_ca_topic_score_gemma":0.02079473,"domain_scores_codex":[0.9998536,0.00005427427,0.000007167207,0.00003885556,0.00002934614,0.0000168091],"domain_scores_gemma":[0.9994965,0.0003086455,0.00004146226,0.00003120041,0.0001000009,0.0000222282],"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":[0.00001605123,0.00001312392,0.0002209316,0.00002229966,0.00002233243,0.00002369398,0.00001031689,0.9519029,0.0002142995,0.0301835,0.001375605,0.01599501],"study_design_scores_gemma":[8.513735e-7,0.000001407345,0.00002070346,0.000001047978,0.000001765196,0.000001194703,0.000001001905,0.9903393,0.00001805595,0.009466407,0.0001472795,9.282796e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01194021,0.0007545212,0.9827439,0.0005956466,0.00009884859,0.00001512739,0.0004629855,0.0003762703,0.003012374],"genre_scores_gemma":[0.8030502,0.002136944,0.1794342,0.0002579289,0.0002540487,0.0001364155,0.001250626,0.000134975,0.01334466],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03106816,"threshold_uncertainty_score":0.06177461,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07875439601610788,"score_gpt":0.2945342704497974,"score_spread":0.2157798744336895,"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."}}