{"id":"W4382655276","doi":"10.1016/j.scitotenv.2023.165165","title":"Applying Machine Learning to investigate metal isotope variations at the watershed scale: A case study with lithium isotopes across the Yukon River Basin","year":2023,"lang":"en","type":"article","venue":"The Science of The Total Environment","topic":"Groundwater and Isotope Geochemistry","field":"Earth and Planetary Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University; University of Ottawa","funders":"","keywords":"Weathering; Lithology; Drainage basin; Geology; Structural basin; Glacial period; Bedrock; Physical geography; Elevation (ballistics); Watershed; Hydrology (agriculture); Earth science; Geochemistry; Geomorphology; Cartography; Machine learning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.000509903,0.000269528,0.0003518276,0.0008660417,0.000919534,0.0009193142,0.0007228501,0.0007993939,0.0004668258],"category_scores_gemma":[0.001036019,0.0001938332,0.0003572782,0.002148279,0.0006757215,0.0005724672,0.000613042,0.0002938877,0.00005296299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00229529,"about_ca_system_score_gemma":0.00172882,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.2853802,"about_ca_topic_score_gemma":0.4096823,"domain_scores_codex":[0.9997568,0.00008293381,0.00001712964,0.000054354,0.00003643442,0.00005230066],"domain_scores_gemma":[0.9994563,0.0002830298,0.00006537152,0.00004185006,0.0001267015,0.00002674733],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002658982,0.0005518682,0.8504733,0.0001127403,0.0002784305,0.002233548,0.001395122,0.07930072,0.01301471,0.001199291,0.0004513847,0.0507229],"study_design_scores_gemma":[0.00007185471,0.0002415718,0.5950987,0.00002842423,0.0001866802,0.0003014658,0.007431741,0.3849622,0.00790209,0.00207009,0.001657449,0.00004771957],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9987417,0.00002196678,0.0006223532,0.00005124047,8.064471e-7,0.00001224654,0.000073385,0.00001050428,0.0004657185],"genre_scores_gemma":[0.9979953,0.00002754064,0.001721276,0.00001085449,6.379084e-7,0.000005235936,0.00006047283,0.000002790569,0.000176084],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7146198,"threshold_uncertainty_score":0.5674382,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01281063792335481,"score_gpt":0.2087170213945359,"score_spread":0.1959063834711811,"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."}}