{"id":"W4406389396","doi":"10.1016/j.ophoto.2025.100083","title":"A new unified framework for supervised 3D crown segmentation (TreeisoNet) using deep neural networks across airborne, UAV-borne, and terrestrial laser scans","year":2025,"lang":"en","type":"article","venue":"ISPRS Open Journal of Photogrammetry and Remote Sensing","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Natural Resources Canada; Canadian Forest Service","funders":"Office of Energy Research and Development","keywords":"Segmentation; Artificial intelligence; Crown (dentistry); Computer science; Artificial neural network; Remote sensing; Deep neural networks; Environmental science; Geology; Materials science","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":[],"consensus_categories":[],"category_scores_codex":[0.0007008493,0.0002552044,0.0004209055,0.00009865283,0.000643767,0.0006283626,0.000254722,0.0002082097,0.00001565185],"category_scores_gemma":[0.0001401477,0.0002265161,0.0001197719,0.0006347526,0.0002180667,0.0003399638,0.0002314598,0.000424165,6.259993e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001015912,"about_ca_system_score_gemma":0.00005014517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005782272,"about_ca_topic_score_gemma":0.001144435,"domain_scores_codex":[0.9982284,0.0001412484,0.0005976569,0.000381172,0.0002121539,0.0004393766],"domain_scores_gemma":[0.9987385,0.0003307147,0.0003702439,0.0002485099,0.00004372559,0.0002683305],"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":[0.0005734892,0.00002687783,0.0003585862,0.00001355218,0.00007932322,0.0000158651,0.0006366669,0.0140534,0.005514159,0.000008929926,0.0002055085,0.9785137],"study_design_scores_gemma":[0.002760843,0.0001660596,0.003138981,0.0002885609,0.0002060534,0.0002466288,0.001502196,0.9839457,0.004295269,0.001776471,0.001350758,0.0003225256],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3908454,0.0001427135,0.6076723,0.0003539596,0.0003444599,0.000467477,0.000002573682,0.00001093792,0.0001601607],"genre_scores_gemma":[0.6563062,0.00005454413,0.342979,0.0003703039,0.0001987071,6.938889e-8,0.000004963843,0.00002105691,0.00006512734],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9781911,"threshold_uncertainty_score":0.9237061,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02013734440904057,"score_gpt":0.3104982624809108,"score_spread":0.2903609180718702,"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."}}