{"id":"W4407777246","doi":"10.20944/preprints202502.1656.v1","title":"Mapping Trails and Tracks in the Boreal Forest using LiDAR and Convolutional Neural Networks","year":2025,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Forest Service; Natural Sciences and Engineering Research Council of Canada; U.S. Forest Service; Alberta-Pacific Forest Industries; Alberta Biodiversity Monitoring Institute; Canadian Natural Resources Limited; Cenovus Energy; ConocoPhillips","keywords":"Convolutional neural network; Lidar; Taiga; Boreal; Remote sensing; Environmental science; Geography; Forestry; Computer science; Artificial intelligence; Archaeology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004133287,0.0005351653,0.0001673908,0.001884031,0.0005935885,0.0006738687,0.0005878239,0.0002451978,0.0005548777],"category_scores_gemma":[0.001106147,0.000198177,0.0002971769,0.001570189,0.0002575414,0.0004820838,0.0004657078,0.0002349695,0.0001804482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001822027,"about_ca_system_score_gemma":0.00192222,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.7606683,"about_ca_topic_score_gemma":0.8829401,"domain_scores_codex":[0.999707,0.00002486443,0.00001142079,0.00007996228,0.00007885046,0.00009774132],"domain_scores_gemma":[0.9995939,0.00007517984,0.000053338,0.00003377323,0.0001976785,0.00004607852],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005131866,0.0002440505,0.4530043,0.0002021167,0.000249072,0.0006620988,0.0006803087,0.1356253,0.01940233,0.0007793375,0.007960953,0.380677],"study_design_scores_gemma":[0.00003445245,0.00009037607,0.5257603,0.00006005653,0.0001061169,0.0002278034,0.001396936,0.4606094,0.005211277,0.001024473,0.005426012,0.000052759],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9821852,0.0004684121,0.009797378,0.0001480976,0.00002590329,0.00004643856,0.003164009,0.0005737364,0.003590918],"genre_scores_gemma":[0.9790629,0.0001934053,0.01548649,0.00002761355,0.000006766171,0.00001213136,0.003982746,0.00001997348,0.001208028],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7606683,"threshold_uncertainty_score":0.4814823,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07533521725627351,"score_gpt":0.3117506842045493,"score_spread":0.2364154669482758,"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."}}