{"id":"W4390439895","doi":"10.1016/j.isprsjprs.2023.12.008","title":"Estimating tree species composition from airborne laser scanning data using point-based deep learning models","year":2023,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal; Natural Resources Canada; Canadian Forest Service; University of British Columbia","funders":"National Research Council Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Point cloud; Tree (set theory); Deep learning; Computer science; Forest inventory; Artificial intelligence; Remote sensing; Forest management; Environmental science; Geography; Mathematics; Agroforestry","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":[0.0008953475,0.0002082378,0.0003228878,0.0002100803,0.0005703385,0.0001841078,0.0002277406,0.0001004066,0.00002066898],"category_scores_gemma":[0.0001153285,0.0001929588,0.00009592428,0.0007483307,0.0002151777,0.0004267564,0.0002129576,0.0004896539,0.00001295623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001028145,"about_ca_system_score_gemma":0.00002205452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002245016,"about_ca_topic_score_gemma":0.0001484963,"domain_scores_codex":[0.9981482,0.000172942,0.0005198792,0.0003646257,0.0004414373,0.0003529352],"domain_scores_gemma":[0.9986563,0.00029562,0.0004610829,0.0003573078,0.0000461594,0.0001835216],"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":[0.0000370954,0.00001601323,0.0002158885,0.0000103846,0.00003380821,0.0001064855,0.00046472,0.3960503,0.1099689,5.784038e-7,0.00008217597,0.4930136],"study_design_scores_gemma":[0.0004564539,0.0000399354,0.001266926,0.0003052969,0.00009909358,0.0002366391,0.0007016331,0.9879416,0.007777982,0.0006292081,0.0003328682,0.0002123708],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5499647,0.00005554689,0.4491943,0.0001388553,0.0001490491,0.00006455766,0.00000503544,0.00004904919,0.000378919],"genre_scores_gemma":[0.703637,0.00001552084,0.2959915,0.00007973142,0.0001860518,5.629571e-9,0.0000449183,0.00002593068,0.00001934769],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5918913,"threshold_uncertainty_score":0.786863,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04352521556071483,"score_gpt":0.2739106212012879,"score_spread":0.2303854056405731,"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."}}