{"id":"W6923759274","doi":"10.14288/1.0441475","title":"Extraction of Forest Road Information from CubeSat Imagery Using Convolutional Neural Networks","year":2024,"lang":"en","type":"article","venue":"Open Collections","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Convolutional neural network; Land cover; Road surface; Key (lock); Artificial neural network; Cover (algebra); Training (meteorology); Canopy; Routing (electronic design automation)","routes":{"ca_aff":false,"ca_fund":false,"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":[0.0001451391,0.001215557,0.0003824472,0.002045808,0.0002466292,0.000600357,0.0006565912,0.0005358852,0.001450014],"category_scores_gemma":[0.0006570676,0.0003715772,0.0008090505,0.001467948,0.0002294962,0.0007391911,0.0005294868,0.0005714894,0.001292457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005597915,"about_ca_system_score_gemma":0.0006641364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02849711,"about_ca_topic_score_gemma":0.04162678,"domain_scores_codex":[0.9998316,0.000008931062,0.000009212885,0.00005412906,0.00005431983,0.00004179855],"domain_scores_gemma":[0.9997899,0.00003744095,0.00003022161,0.00004116505,0.00009005778,0.00001115122],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000269995,0.0003956732,0.02099699,0.0001988431,0.000260007,0.0007482265,0.0001370854,0.3106255,0.05183563,0.001344815,0.01699266,0.5961946],"study_design_scores_gemma":[0.000007855582,0.0000306117,0.009421096,0.0000228433,0.00003425289,0.0001095249,0.00007164294,0.9754273,0.011321,0.00120177,0.002331709,0.00002052088],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6731336,0.001247411,0.2869189,0.000476372,0.000212801,0.0002660087,0.01528178,0.01374333,0.008719656],"genre_scores_gemma":[0.8363768,0.0004763552,0.1295993,0.0001367084,0.00005594172,0.0001094364,0.0293419,0.0001992315,0.003704175],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02849711,"threshold_uncertainty_score":0.05666244,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01348029876882046,"score_gpt":0.2541784598590456,"score_spread":0.2406981610902251,"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."}}