{"id":"W4412734594","doi":"10.1017/eds.2025.10013","title":"Tree semantic segmentation from aerial image time series","year":2025,"lang":"en","type":"article","venue":"Environmental Data Science","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute; Computer Research Institute of Montréal","funders":"","keywords":"Tree (set theory); Series (stratigraphy); Artificial intelligence; Computer science; Aerial image; Segmentation; Image (mathematics); Computer vision; Pattern recognition (psychology); Mathematics; Geology","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003141101,0.000147688,0.0001147958,0.00004769486,0.0005088574,0.0001523138,0.001172156,0.00003590989,0.002588625],"category_scores_gemma":[0.00003464748,0.0001429616,0.00002279609,0.0004019984,0.001652626,0.001738962,0.001382529,0.00008958045,0.004357927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002008164,"about_ca_system_score_gemma":0.00002398473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00048618,"about_ca_topic_score_gemma":0.00007365833,"domain_scores_codex":[0.9981894,0.00003649445,0.0002055341,0.0008037651,0.0004735869,0.0002911754],"domain_scores_gemma":[0.9985962,0.00003642543,0.00006648884,0.00120373,0.000001309366,0.00009584382],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0000100658,0.00006505172,0.002772945,7.739966e-7,0.000004410146,0.000002060829,0.0001084206,0.00002703445,0.964139,0.00002361559,0.007797516,0.0250491],"study_design_scores_gemma":[0.0009848963,0.00007836652,0.5441269,0.0000369525,0.0001029721,0.00001791379,0.0009544222,0.03095222,0.3568121,0.00228982,0.06285986,0.0007836071],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9388581,0.00003019397,0.005427734,0.0009968359,0.0003343505,0.0004174069,0.0004988869,0.0001004987,0.05333597],"genre_scores_gemma":[0.9565457,0.00004532348,0.03862978,0.0003214737,0.00006223571,0.000005157619,0.0009502778,0.00001275838,0.003427355],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6073269,"threshold_uncertainty_score":0.9983231,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007343167933572374,"score_gpt":0.2351329130290553,"score_spread":0.2277897450954829,"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."}}