{"id":"W4379157432","doi":"10.1007/s11053-023-10216-1","title":"Applications of Natural Language Processing to Geoscience Text Data and Prospectivity Modeling","year":2023,"lang":"en","type":"article","venue":"Natural Resources Research","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Geological Survey of Canada; Natural Resources Canada","funders":"Natural Resources Canada","keywords":"Prospectivity mapping; Mineral exploration; Computer science; Natural language processing; Naive Bayes classifier; Artificial intelligence; Word (group theory); Geology; Geophysics; Geomorphology; Mathematics; Support vector machine; Structural basin","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001927258,0.00008821827,0.0001230123,0.0002472494,0.0004048249,0.0002047897,0.002132978,0.00005198899,0.000002519979],"category_scores_gemma":[0.001220363,0.0000715507,0.00001577763,0.002714159,0.0001551695,0.0003635024,0.003115329,0.0005073238,0.00001653037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002462157,"about_ca_system_score_gemma":0.00006977545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001235297,"about_ca_topic_score_gemma":0.0000295762,"domain_scores_codex":[0.9978776,0.00007430366,0.000155555,0.0006638708,0.0007650981,0.0004635686],"domain_scores_gemma":[0.9984547,0.0002306297,0.00003756729,0.0008333435,0.0003364583,0.0001072278],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002430054,0.00004517669,0.001519904,0.0003235637,0.000008201505,0.00001859255,0.008584842,0.0008490981,0.05100956,0.001057508,0.0007144947,0.9358448],"study_design_scores_gemma":[0.00007084966,0.00001817611,0.001797627,0.00004405393,8.64201e-7,0.000008711079,0.0008489204,0.9863975,0.001300359,0.0007272805,0.008687218,0.00009843537],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9554061,0.004203998,0.02755242,0.006978902,0.00006417822,0.0007988479,0.00001727581,0.000308799,0.004669486],"genre_scores_gemma":[0.9924409,0.00001332678,0.004285717,0.00002743423,0.00005904699,0.00003500436,0.000008852523,0.000002233636,0.003127476],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9855484,"threshold_uncertainty_score":0.3963639,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06506131511485803,"score_gpt":0.3859891107978926,"score_spread":0.3209277956830345,"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."}}