{"id":"W4407713018","doi":"10.1016/j.jhazmat.2025.137665","title":"Robust prediction of water arsenic levels downstream of gold mines affected by acid mine drainage using hybrid ensemble machine learning and soft computing","year":2025,"lang":"en","type":"article","venue":"Journal of Hazardous Materials","topic":"Mine drainage and remediation techniques","field":"Environmental Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia; Laurentian University","funders":"","keywords":"Acid mine drainage; Arsenic; Drainage; Downstream (manufacturing); Environmental science; Mining engineering; Engineering; Chemistry; Environmental chemistry; Ecology; Biology","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":[0.00093476,0.0006539088,0.0007565669,0.0008604611,0.0002686057,0.0006741642,0.0006123979,0.0005726642,0.0002908666],"category_scores_gemma":[0.001462591,0.0003070857,0.0008226861,0.0005911813,0.0001437936,0.0006504482,0.0005983821,0.0006324972,0.0001609931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004408937,"about_ca_system_score_gemma":0.0007598936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009454777,"about_ca_topic_score_gemma":0.01250064,"domain_scores_codex":[0.9997182,0.00007703225,0.00002027053,0.00007932229,0.00006998939,0.00003516372],"domain_scores_gemma":[0.9994661,0.0001765262,0.00007552902,0.00005774874,0.0001912464,0.00003286401],"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":[0.0001498921,0.0002172622,0.04330885,0.00005907069,0.0001840739,0.00008386723,0.00006089711,0.8541428,0.007210047,0.0003211941,0.0009669852,0.093295],"study_design_scores_gemma":[0.000002177805,0.00002961799,0.002893886,0.000002836901,0.0000106658,0.000005533846,0.00001152717,0.9958338,0.0009587965,0.0001440231,0.0001028759,0.000004270813],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8297759,0.0004164251,0.1664341,0.0002443179,0.00006681879,0.00005502059,0.0004111968,0.0007273139,0.001868837],"genre_scores_gemma":[0.9737979,0.00008107447,0.02494078,0.00003651324,0.00001466118,0.00002370548,0.0004423207,0.00001624371,0.0006468775],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009454777,"threshold_uncertainty_score":0.01879948,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01163346374681277,"score_gpt":0.2276435425829513,"score_spread":0.2160100788361386,"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."}}