{"id":"W3000803710","doi":"10.1016/j.scitotenv.2020.136836","title":"Enhancing nitrate and strontium concentration prediction in groundwater by using new data mining algorithm","year":2020,"lang":"en","type":"article","venue":"The Science of The Total Environment","topic":"Groundwater flow and contamination studies","field":"Environmental Science","cited_by":85,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Groundwater; Random forest; Algorithm; Environmental science; Correlation coefficient; Water quality; Computer science; Data mining; Soil science; Hydrology (agriculture); Machine learning; Engineering; Geotechnical engineering; Ecology","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":[0.0004592401,0.00009390574,0.00009161758,0.000007969519,0.0002513842,0.000046471,0.0004594928,0.00001725508,0.00009314007],"category_scores_gemma":[0.00001548662,0.00005786418,0.00001427744,0.0001589148,0.0006981561,0.0005930667,0.0009334314,0.0000715632,0.00001096944],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001233549,"about_ca_system_score_gemma":0.00001494661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004277255,"about_ca_topic_score_gemma":0.000007810216,"domain_scores_codex":[0.9987881,0.00004797503,0.0002027184,0.0003174989,0.0004405424,0.0002031643],"domain_scores_gemma":[0.9995571,0.00001590371,0.00009073546,0.0002736249,0.00000184883,0.00006078983],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001364234,0.00004874792,0.003322041,0.000005138154,0.00001186485,5.687343e-7,0.006289511,0.02034,0.9421957,0.00000673026,0.00032906,0.02743703],"study_design_scores_gemma":[0.0008805984,0.0001813527,0.1330916,0.00003974407,0.00007268293,0.00001347709,0.003795304,0.7211434,0.1399747,0.00005868508,0.0004497155,0.0002987143],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9788015,0.0000693402,0.01965067,0.001083076,0.00008436212,0.0001981913,0.00001135755,0.000005755233,0.00009570743],"genre_scores_gemma":[0.9979771,0.00001248308,0.001440212,0.00005312151,0.00002567799,0.000002380785,0.000002849264,0.00000432481,0.0004818882],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8022209,"threshold_uncertainty_score":0.2572385,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02202681820592246,"score_gpt":0.2169065548453445,"score_spread":0.194879736639422,"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."}}