{"id":"W4407058238","doi":"10.1111/2041-210x.14503","title":"Benchmarking tree species classification from proximally sensed laser scanning data: Introducing the <scp>FOR</scp> ‐ <scp>species20K</scp> dataset","year":2025,"lang":"en","type":"article","venue":"Methods in Ecology and Evolution","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge; University of British Columbia","funders":"Narodowe Centrum Badań i Rozwoju; Norges Forskningsråd; Austrian Science Fund; Academy of Finland; UK Research and Innovation; Deutsche Forschungsgemeinschaft; European Cooperation in Science and Technology; European Commission","keywords":"Point cloud; Computer science; Benchmarking; Tree (set theory); Laser scanning; Remote sensing; Lidar; Robustness (evolution); Data mining; Artificial intelligence; Benchmark (surveying); Hyperspectral imaging; Machine learning; Cartography; Geography; Laser; Biology; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.002785643,0.0001693309,0.000230816,0.0001057465,0.0006360614,0.0000747786,0.0003944702,0.0001859512,0.00001373251],"category_scores_gemma":[0.003079908,0.0001451705,0.00003025033,0.0004747631,0.0004432398,0.0002566359,0.0003901971,0.0003123808,0.00001667834],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003485536,"about_ca_system_score_gemma":0.00004479218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004364455,"about_ca_topic_score_gemma":0.002309606,"domain_scores_codex":[0.9977691,0.0006328884,0.0003708537,0.0007435523,0.0001194369,0.0003641676],"domain_scores_gemma":[0.9948021,0.004135693,0.0001775588,0.0008211116,0.00001941382,0.00004412876],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002347638,0.0002721076,0.45904,0.00005187116,0.0001356761,0.000003721945,0.003095601,0.00549842,0.1284809,0.005100636,0.2825238,0.1157738],"study_design_scores_gemma":[0.0002598684,0.00002117902,0.755139,0.00001633794,0.0000543266,0.000003527007,0.001500009,0.07998991,0.0009978751,0.003892026,0.1580932,0.00003276168],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6584743,0.0002153663,0.3305118,0.001337578,0.000692364,0.000801898,0.000353389,0.00006142208,0.007551936],"genre_scores_gemma":[0.4687103,0.0001240815,0.525062,0.000554511,0.0004444078,0.00006311402,0.002825255,0.00002289863,0.002193422],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.296099,"threshold_uncertainty_score":0.591988,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03784902240824326,"score_gpt":0.3271312912864897,"score_spread":0.2892822688782464,"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."}}