{"id":"W3043859127","doi":"10.1139/juvs-2020-0014","title":"Individual tree species identification using Dense Convolutional Network (DenseNet) on multitemporal RGB images from UAV","year":2020,"lang":"en","type":"article","venue":"Journal of Unmanned Vehicle Systems","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"FPInnovations; York University","funders":"Canadian Forest Service; Natural Sciences and Engineering Research Council of Canada; U.S. Forest Service; FPInnovations; Natural Resources Canada; York University","keywords":"Convolutional neural network; Tree (set theory); Computer science; RGB color model; Artificial intelligence; Identification (biology); Remote sensing; Deep learning; Pattern recognition (psychology); Computer vision; Geography; Mathematics; Ecology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000469152,0.0001618721,0.0002822645,0.00004526473,0.000240226,0.0001686114,0.0002902687,0.00009113588,0.00007475833],"category_scores_gemma":[0.00007603848,0.0001450508,0.0001310252,0.0002878376,0.0001375897,0.0002389229,0.00006544108,0.0002604439,0.0002290436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001792541,"about_ca_system_score_gemma":0.0000341913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003050829,"about_ca_topic_score_gemma":0.00002053707,"domain_scores_codex":[0.9978775,0.0002046194,0.0007124617,0.0002550698,0.0007143899,0.0002359982],"domain_scores_gemma":[0.9986638,0.0001387425,0.0007250386,0.0002015673,0.00006200629,0.000208872],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0003516915,0.0002319571,0.06855184,0.00002590247,0.0002518079,0.0001027231,0.002038076,0.4536074,0.3983157,0.0002040497,0.07276537,0.003553428],"study_design_scores_gemma":[0.002243213,0.0004296556,0.6998286,0.000294133,0.0002364951,0.0001957532,0.001954157,0.25629,0.01028339,0.0004385354,0.02715053,0.0006555162],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9933423,0.0002428651,0.003897724,0.0011067,0.0004638974,0.0001893165,0.00004134877,0.00002823355,0.0006875634],"genre_scores_gemma":[0.9964469,0.00001247346,0.001715592,0.0001895822,0.001392452,6.75302e-7,0.00001782055,0.00002061463,0.0002038591],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6312768,"threshold_uncertainty_score":0.5915,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04105112691232429,"score_gpt":0.247920178101173,"score_spread":0.2068690511888487,"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."}}