{"id":"W4399779241","doi":"10.1016/j.jag.2024.103960","title":"High-resolution mapping of tree species and associated uncertainty by combining aerial remote sensing data and convolutional neural networks ensemble","year":2024,"lang":"en","type":"article","venue":"International Journal of Applied Earth Observation and Geoinformation","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre de Géomatique du Québec; Université Laval; Ministère des Ressources naturelles et des Forêts; Ministry of Natural Resources and Wildlife","funders":"Alliance de recherche numérique du Canada","keywords":"Convolutional neural network; Geography; Remote sensing; Cartography; Aerial imagery; Artificial intelligence; Tree (set theory); Decision tree; Computer science; Pattern recognition (psychology); Data mining; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007974926,0.001033683,0.000441332,0.001007682,0.0002791234,0.0006050377,0.0007998015,0.0004010939,0.0005365126],"category_scores_gemma":[0.001256933,0.0002842335,0.0006250735,0.0008314271,0.0002605526,0.0008335467,0.0006506947,0.000689883,0.000170355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00134527,"about_ca_system_score_gemma":0.0008975365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1646575,"about_ca_topic_score_gemma":0.2143335,"domain_scores_codex":[0.9997715,0.00003294746,0.000009323706,0.00007669227,0.00006320446,0.00004636099],"domain_scores_gemma":[0.999554,0.0001131587,0.00004865113,0.00008321135,0.0001771043,0.00002393997],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009273463,0.0000776849,0.02357918,0.00003040143,0.0002344523,0.0001156013,0.00006514152,0.8471607,0.007916435,0.0004007925,0.001335799,0.1189911],"study_design_scores_gemma":[0.000001411847,0.000007844976,0.004369123,0.000003128844,0.00001639965,0.000008289613,0.00001627783,0.9938743,0.001259408,0.0002729084,0.0001654771,0.00000542635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7645901,0.0005854669,0.2282875,0.0002145442,0.00005555343,0.00005477155,0.001447441,0.00223533,0.002529316],"genre_scores_gemma":[0.968354,0.0001004931,0.02933069,0.00003452857,0.00001250537,0.00001443511,0.001339399,0.00003425536,0.0007797789],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1646575,"threshold_uncertainty_score":0.3273982,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01832187105968462,"score_gpt":0.2146875935738408,"score_spread":0.1963657225141561,"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."}}