{"id":"W4408428670","doi":"10.5194/egusphere-egu25-13722","title":"Using convolutional neural networks to classify unexploded ordnance from multicomponent electromagnetic induction data  ","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Unexploded ordnance; Convolutional neural network; Electromagnetic induction; Artificial intelligence; Pattern recognition (psychology); Computer science; Artificial neural network; Machine learning; Engineering; Remote sensing; Geology; Electrical engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003964168,0.0008792304,0.0002635542,0.0006854737,0.000224359,0.0007235487,0.0008858049,0.0006968055,0.001242125],"category_scores_gemma":[0.001020993,0.0003000798,0.0003941618,0.0004943671,0.0003494401,0.0008057327,0.000517214,0.000702856,0.0005670321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008214947,"about_ca_system_score_gemma":0.0004847393,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01084227,"about_ca_topic_score_gemma":0.01488825,"domain_scores_codex":[0.9998351,0.00001472603,0.000006572576,0.00004911745,0.00005153477,0.00004291174],"domain_scores_gemma":[0.999651,0.0001107756,0.00004631823,0.00004063647,0.0001283284,0.00002291926],"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":[0.0003515986,0.0002984375,0.00838482,0.0001108252,0.0001363175,0.0003794103,0.000112145,0.4057984,0.09062219,0.003012739,0.006655934,0.4841372],"study_design_scores_gemma":[0.00000358049,0.00002714492,0.000954792,0.000006374288,0.000009823881,0.00001915533,0.00001328949,0.9865479,0.01091672,0.0007289402,0.0007651747,0.000006976912],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4453178,0.0009174077,0.5355862,0.0008455756,0.0003133058,0.0001114399,0.0008683638,0.004827095,0.01121277],"genre_scores_gemma":[0.7832199,0.0003988465,0.2019159,0.0004197712,0.00007643946,0.00007364344,0.002277166,0.0001700968,0.01144814],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01084227,"threshold_uncertainty_score":0.02155828,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1645093363069872,"score_gpt":0.3459184344335812,"score_spread":0.181409098126594,"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."}}