{"id":"W2805524315","doi":"10.1371/journal.pone.0197386","title":"A bioavailable strontium isoscape for Western Europe: A machine learning approach","year":2018,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Archaeology and ancient environmental studies","field":"Earth and Planetary Sciences","cited_by":201,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"FP7 Ideas: European Research Council; Gillings School of Public Health; European Commission; University of Utah; University of North Carolina at Chapel Hill; National Science Foundation","keywords":"Kriging; Geospatial analysis; Random forest; Geolocation; Scale (ratio); Geostatistics; Spatial analysis; Regression; Regression analysis; Spatial ecology; Physical geography; Spatial variability; Environmental science; Computer science; Ecology; Geography; Machine learning; Cartography; Remote sensing; Statistics; Mathematics; 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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001379983,0.000096744,0.0001438265,0.00002576903,0.0003931272,0.00001025309,0.0001271836,0.00003191412,0.0008588991],"category_scores_gemma":[0.00002945155,0.00007831408,0.00002478048,0.00007744537,0.0003083827,0.00008715852,0.00003974552,0.00009497428,0.0008028634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000001898374,"about_ca_system_score_gemma":0.000005112277,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008572893,"about_ca_topic_score_gemma":0.0002618185,"domain_scores_codex":[0.9992233,0.00003607321,0.00009862635,0.0002298062,0.0001310027,0.0002811786],"domain_scores_gemma":[0.9997625,0.00003769313,0.00004269899,0.00008541376,0.00001582741,0.00005589868],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005994219,0.0001464486,0.9979643,0.00002673318,0.00007332888,8.371648e-7,0.000276401,0.0000440736,0.0002636501,0.00001164937,0.0001379526,0.0009946373],"study_design_scores_gemma":[0.001488574,0.003109871,0.8286301,0.00007077497,0.0002202951,0.000008584322,0.0003216066,0.09692845,0.003987264,0.000222291,0.06435677,0.0006554113],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9779197,0.001350311,0.00149586,0.0002556443,0.00005404295,0.0002871775,0.00007045469,0.00006644447,0.01850039],"genre_scores_gemma":[0.9771869,0.0001653731,0.008051267,0.0002056163,0.0001939706,0.000005352435,0.0001241135,0.000005201474,0.01406225],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1693342,"threshold_uncertainty_score":0.9999751,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04255513018093057,"score_gpt":0.1911000543002029,"score_spread":0.1485449241192723,"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."}}