{"id":"W4409107791","doi":"10.3390/f16040616","title":"Using Citizen Science Data as Pre-Training for Semantic Segmentation of High-Resolution UAV Images for Natural Forests Post-Disturbance Assessment","year":2025,"lang":"en","type":"article","venue":"Forests","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ministère des Ressources naturelles et des Forêts (Québec); Université Laval","funders":"","keywords":"Disturbance (geology); Training (meteorology); Segmentation; Computer science; High resolution; Natural (archaeology); Citizen science; Remote sensing; Environmental science; Artificial intelligence; Computer vision; Environmental resource management; Geology; Geography; Biology; Geomorphology; Botany","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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":[0.0005231377,0.0001314663,0.0001632828,0.00008928518,0.000457843,0.0000744132,0.0005115829,0.00004359525,0.000007674421],"category_scores_gemma":[0.0002325083,0.0001250692,0.0000480634,0.0004051834,0.0003962674,0.0004557949,0.0002620891,0.00006895776,0.000002801024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002502747,"about_ca_system_score_gemma":0.0001559812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008646945,"about_ca_topic_score_gemma":0.0009718805,"domain_scores_codex":[0.9985481,0.0000207934,0.0002786894,0.0005147443,0.0003111322,0.0003265758],"domain_scores_gemma":[0.9989879,0.0001514894,0.0001795386,0.0005562985,0.00007473954,0.00005003457],"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":[0.000308779,0.0002633801,0.05568029,0.0003741274,0.00009103942,0.000001564539,0.001276839,0.045225,0.7937231,0.01128762,0.007141255,0.08462699],"study_design_scores_gemma":[0.0006306895,0.00008994949,0.6457874,0.0001128687,0.00006961445,0.000005352342,0.0001545406,0.3257088,0.01952242,0.007400228,0.0003474594,0.0001706953],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.742008,0.00003819253,0.2558746,0.0002995644,0.0002340264,0.0010283,0.0001227087,0.00003302784,0.000361552],"genre_scores_gemma":[0.888403,0.000002151347,0.1108955,0.00006286401,0.00003618921,0.00002319665,0.0002629034,0.00001141123,0.0003027904],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7742007,"threshold_uncertainty_score":0.5100175,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03124520730232976,"score_gpt":0.354520351508106,"score_spread":0.3232751442057762,"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."}}