{"id":"W4405079415","doi":"10.1007/s12145-024-01623-w","title":"Application of machine learning and deep learning for predicting groundwater levels in the West Coast Aquifer System, South Africa","year":2024,"lang":"en","type":"article","venue":"Earth Science Informatics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"University of the Western Cape","keywords":"Groundwater recharge; Groundwater; Aquifer; Support vector machine; Machine learning; Artificial intelligence; Mean squared error; Random forest; Artificial neural network; Deep learning; Computer science; Hydrology (agriculture); Data mining; Geology; Statistics; Geotechnical engineering; Mathematics","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":[0.00265482,0.000100171,0.0001160275,0.00008531312,0.0003811034,0.0001936444,0.0002689672,0.00004268525,0.00001789485],"category_scores_gemma":[0.0002885215,0.0000637835,0.00002477644,0.0006561604,0.0004720018,0.0005115934,0.0001723594,0.0002628908,0.00004177764],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004366269,"about_ca_system_score_gemma":0.000013773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006019217,"about_ca_topic_score_gemma":0.00003534773,"domain_scores_codex":[0.9986873,0.00004015512,0.0003761,0.0001559485,0.0004307992,0.0003096729],"domain_scores_gemma":[0.999486,0.0002159274,0.0001256746,0.0001086181,0.0000141552,0.00004967798],"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":[0.00001694854,0.0000428236,0.2892197,0.000628042,0.000008252158,0.000003199753,0.1816892,0.4488385,0.004253997,0.001054485,0.00000694431,0.07423787],"study_design_scores_gemma":[0.00008494502,0.0001204474,0.01153397,0.00006635372,0.000006770862,0.00001993112,0.002414166,0.9833689,0.0001184484,0.00004500319,0.002141051,0.0000799959],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9389868,0.00003671909,0.05818629,0.00004913536,0.00005888547,0.0003280785,0.000002916835,0.00007545767,0.002275764],"genre_scores_gemma":[0.9949976,0.000001400392,0.004880846,0.00002410592,0.00001683287,0.00002171257,0.000002779564,0.000005843006,0.00004889659],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5345304,"threshold_uncertainty_score":0.2931178,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01793613378738637,"score_gpt":0.2353386898731987,"score_spread":0.2174025560858124,"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."}}