{"id":"W4412086110","doi":"10.1016/j.jconhyd.2025.104672","title":"Harnessing deep learning for fusion-based heavy metal contamination index prediction in groundwater","year":2025,"lang":"en","type":"article","venue":"Journal of Contaminant Hydrology","topic":"Geophysical Methods and Applications","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec en Abitibi-Témiscamingue","funders":"","keywords":"Groundwater; Environmental science; Contamination; Index (typography); Contaminated groundwater; Geology; Environmental remediation; Computer science; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003864102,0.0005769578,0.0006398021,0.0006050757,0.0002079842,0.0005455423,0.0006094978,0.0006373701,0.0006620258],"category_scores_gemma":[0.0007728895,0.0002424708,0.0005641639,0.0006225826,0.0002583461,0.0008533872,0.0009141589,0.0007167261,0.0003125368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003292582,"about_ca_system_score_gemma":0.0005242924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004941935,"about_ca_topic_score_gemma":0.005992153,"domain_scores_codex":[0.999864,0.00001792083,0.000007057017,0.00004134646,0.0000359338,0.00003381068],"domain_scores_gemma":[0.9997684,0.00008495132,0.00002903981,0.00002290744,0.00007638808,0.00001820248],"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":[0.0005316823,0.0004594355,0.01840601,0.0001459694,0.0002445607,0.0001818284,0.00009655876,0.5575787,0.04972647,0.002448852,0.003519795,0.3666601],"study_design_scores_gemma":[0.000002899155,0.00002178549,0.0007438741,0.000002129088,0.0000103305,0.00000752864,0.000005448205,0.9955466,0.002628755,0.0008801302,0.0001457545,0.000004710507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4067438,0.001309886,0.5853358,0.0006197758,0.0001774683,0.00003470315,0.0006668204,0.001926339,0.003185547],"genre_scores_gemma":[0.9725491,0.0002552672,0.02550235,0.0001003703,0.00004799846,0.00001626964,0.000446828,0.00002149593,0.001060206],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004941935,"threshold_uncertainty_score":0.009826362,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007874952239483606,"score_gpt":0.255346592497522,"score_spread":0.2474716402580383,"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."}}