{"id":"W2615757794","doi":"10.1016/j.aei.2017.05.002","title":"A machine learning approach for characterizing soil contamination in the presence of physical site discontinuities and aggregated samples","year":2017,"lang":"en","type":"article","venue":"Advanced Engineering Informatics","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"Fonds de recherche du Québec – Nature et technologies","keywords":"Kriging; Classification of discontinuities; Probabilistic logic; Gaussian process; Soil science; Gaussian; Contamination; Representation (politics); Ground-penetrating radar; Regression; Environmental science; Computer science; Mathematics; Machine learning; Statistics; Chemistry","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000167794,0.0000771349,0.0001131476,0.00001982972,0.0001079813,0.00005352719,0.000132349,0.00001624943,5.890896e-7],"category_scores_gemma":[0.0003292476,0.00006032262,0.00001613155,0.00003070022,0.00006075733,0.0004235869,0.00007718534,0.00008331508,3.836554e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001381353,"about_ca_system_score_gemma":0.000001739257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006622933,"about_ca_topic_score_gemma":0.00001630055,"domain_scores_codex":[0.9995564,0.000005314285,0.0001601138,0.0000530145,0.000096895,0.0001282457],"domain_scores_gemma":[0.9995279,0.0001689996,0.000154347,0.0001261051,0.000006854685,0.00001578923],"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":[0.00002697502,0.00005092808,0.03706843,0.0006329447,0.00001767577,8.968459e-7,0.05489541,0.7536802,0.01863811,0.004839627,0.000004504009,0.1301443],"study_design_scores_gemma":[0.0002677671,0.00003384767,0.08239023,0.00005125762,0.000005197433,0.00000158725,0.0004804259,0.9153784,0.0005611118,0.00005716824,0.000694184,0.0000788101],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8615337,0.00001451653,0.1379123,0.0000139677,0.00001840673,0.0001863868,0.00001718729,0.0000118841,0.0002916162],"genre_scores_gemma":[0.9803742,0.00002974477,0.01949193,0.000008118661,0.000008651999,0.00003346888,0.00003008248,0.0000055265,0.00001825205],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1616983,"threshold_uncertainty_score":0.2459885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008854912202205634,"score_gpt":0.2158780016637448,"score_spread":0.2070230894615392,"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."}}