{"id":"W4320486209","doi":"10.1190/geo2022-0476.1","title":"Predictive lithology mapping using semisupervised learning: Practical insights using a case study from New South Wales, Australia","year":2023,"lang":"en","type":"article","venue":"Geophysics","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Golder Associates (Canada); Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada; Chevron","keywords":"Hyperparameter; Machine learning; Computer science; Overfitting; Artificial intelligence; Supervised learning; Boosting (machine learning); Bootstrapping (finance); Gradient boosting; Mathematics; Random forest; Artificial neural network","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002376925,0.0002907008,0.0003535551,0.000103195,0.0004405255,0.0001751425,0.0004124006,0.0001714093,0.00001855519],"category_scores_gemma":[0.000233171,0.0002930884,0.00009598742,0.001114199,0.00007078536,0.0004517643,0.000752283,0.0005992939,0.000114928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006609129,"about_ca_system_score_gemma":0.0002515029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00220582,"about_ca_topic_score_gemma":0.00001568881,"domain_scores_codex":[0.9976596,0.000284412,0.0003443356,0.0008231863,0.000319563,0.0005688574],"domain_scores_gemma":[0.9985704,0.0002524747,0.0002033621,0.0006115502,0.0001513673,0.0002108591],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001419671,0.001598206,0.1304475,0.0002463198,0.001335911,0.1051459,0.4940285,0.1631056,0.09624857,0.002119781,0.001213746,0.004367993],"study_design_scores_gemma":[0.001641223,0.0003113232,0.01014771,0.0001071067,0.0001625757,0.001653748,0.03547106,0.9310039,0.001220944,0.01631043,0.001045554,0.0009244725],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8880376,0.00001207157,0.1107609,0.0001481185,0.0002991672,0.0002611126,0.000003797139,0.000370105,0.0001071463],"genre_scores_gemma":[0.9823238,9.883598e-7,0.01628578,0.00004169277,0.0004438635,0.000007363075,0.00001839278,0.000009913128,0.0008681808],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7678983,"threshold_uncertainty_score":0.9999521,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1463271853032334,"score_gpt":0.3298840554064684,"score_spread":0.1835568701032351,"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."}}