{"id":"W4410876620","doi":"10.1016/j.cageo.2025.105964","title":"Lithological mapping using Spatially Constrained Bayesian Network (SCB-Net): A deep learning model for generating field-data-constrained predictions with uncertainty evaluation using remote sensing data","year":2025,"lang":"en","type":"article","venue":"Computers & Geosciences","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Natural Resources Canada; Institut National de la Recherche Scientifique","funders":"Commission Géologique du Canada; Natural Resources Canada","keywords":"Field (mathematics); Computer science; Bayesian probability; Bayesian network; Data mining; Remote sensing; Net (polyhedron); Deep learning; Machine learning; Artificial intelligence; Geology; Mathematics","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","sts"],"consensus_categories":[],"category_scores_codex":[0.003435145,0.000343588,0.0004133931,0.0001835908,0.001931257,0.0006964406,0.002267891,0.0001736204,0.000003900803],"category_scores_gemma":[0.001048646,0.0003040415,0.00006507411,0.001234164,0.0003953922,0.0008947626,0.001610002,0.0003637438,2.739091e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009913112,"about_ca_system_score_gemma":0.00103623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002245399,"about_ca_topic_score_gemma":0.0001413027,"domain_scores_codex":[0.9960929,0.0003297396,0.0006241107,0.001617406,0.0005244743,0.0008113985],"domain_scores_gemma":[0.9969382,0.0007380584,0.0004132767,0.001319681,0.0004556624,0.0001351114],"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":[0.00001096774,0.00001209965,0.000167759,0.00003325688,0.00003455136,0.000008764539,0.0003715869,0.8790432,0.0006653686,0.0002787301,0.00005049631,0.1193232],"study_design_scores_gemma":[0.0005109431,0.00008043508,0.00004402557,0.000364112,0.00007781618,0.0001109927,0.0002972275,0.9949396,0.00002864419,0.002986944,0.0002135878,0.0003457071],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01220154,0.0001145289,0.9846469,0.001045007,0.0006605954,0.0006622169,0.00001358362,0.00024615,0.0004095338],"genre_scores_gemma":[0.3950824,0.000003452583,0.60426,0.0003420856,0.0001841916,0.000001729364,0.000101103,0.000003507409,0.00002155678],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3828809,"threshold_uncertainty_score":0.9999412,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08212722614797328,"score_gpt":0.3109004186518579,"score_spread":0.2287731925038846,"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."}}