{"id":"W4390125374","doi":"10.1007/s10040-023-02740-4","title":"Groundwater level monitoring using exploited domestic wells: outlier removal and imputation of missing values","year":2023,"lang":"en","type":"article","venue":"Hydrogeology Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Outlier; Imputation (statistics); Missing data; Hydrogeology; Groundwater; Interpolation (computer graphics); Kalman filter; Data mining; Computer science; Geology; Statistics; Mathematics; Artificial intelligence; Geotechnical engineering","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":[0.003771914,0.0004122151,0.0009172278,0.0008875576,0.0004929916,0.001042219,0.001428689,0.0008095372,0.0009096286],"category_scores_gemma":[0.01100332,0.000337322,0.0007951107,0.003297938,0.0003683494,0.0009676255,0.000685622,0.0007176884,0.000283661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003542046,"about_ca_system_score_gemma":0.001119788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007521782,"about_ca_topic_score_gemma":0.008791146,"domain_scores_codex":[0.9980676,0.0007070655,0.0002784622,0.0004505026,0.0002852169,0.0002113122],"domain_scores_gemma":[0.9926339,0.001740073,0.001100503,0.003010134,0.001399133,0.0001162487],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001226265,0.0006431861,0.478816,0.0002248123,0.0008372057,0.0004447379,0.0006376266,0.1878691,0.01020081,0.005814269,0.005353614,0.3079323],"study_design_scores_gemma":[0.00006762438,0.000220932,0.1073391,0.00004103582,0.000209797,0.0002046846,0.0003659379,0.8680213,0.01250561,0.007154427,0.003808987,0.00006062793],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6490393,0.000184697,0.3445703,0.000245335,0.00005657631,0.00005898442,0.0033131,0.001037221,0.001494495],"genre_scores_gemma":[0.9281303,0.0000502961,0.06814089,0.0000218483,0.00001646278,0.00004314128,0.0029324,0.00003555581,0.000629149],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.007521782,"threshold_uncertainty_score":0.01994807,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07544844101826664,"score_gpt":0.3085105044475969,"score_spread":0.2330620634293303,"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."}}