{"id":"W3208603523","doi":"10.1016/j.ecoinf.2021.101465","title":"Machine learning and SLIC for Tree Canopies segmentation in urban areas","year":2021,"lang":"en","type":"article","venue":"Ecological Informatics","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Fundação de Apoio ao Desenvolvimento do Ensino, Ciência e Tecnologia do Estado de Mato Grosso do Sul; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Universidade Federal de Mato Grosso do Sul; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Segmentation; Pattern recognition (psychology); Metric (unit); Tree (set theory); Cluster analysis; Classifier (UML); Deep learning; 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":[0.0001167584,0.00005411363,0.00007970465,0.0000136203,0.00009979848,0.0000309444,0.00003287889,0.00004326606,0.0001609027],"category_scores_gemma":[0.0001063406,0.00004499955,0.00001634301,0.0001045347,0.00004954344,0.00008328043,0.00005577437,0.00008061936,0.00003482406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006072356,"about_ca_system_score_gemma":0.000006049248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002623339,"about_ca_topic_score_gemma":0.0004359653,"domain_scores_codex":[0.9995574,0.0000185675,0.0001801399,0.0000635093,0.00006325387,0.0001171366],"domain_scores_gemma":[0.9997505,0.0001057567,0.00004886117,0.0000512519,0.00000548974,0.00003814103],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002851441,0.000323838,0.6953249,0.00008634203,0.00002311388,0.000009264138,0.01201074,0.008071776,0.004892469,0.002273994,0.003857837,0.2730972],"study_design_scores_gemma":[0.001121338,0.0002161548,0.5798262,0.00001503454,0.0000196051,0.00003390316,0.003654401,0.2831477,0.002457438,0.002856771,0.1263336,0.0003179131],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9754511,0.00002891197,0.003096359,0.0003770478,0.00002706384,0.0001939335,0.000003892603,0.00002936221,0.02079239],"genre_scores_gemma":[0.9757419,0.00004894722,0.02280516,0.0003178692,0.00001102769,0.00000990478,0.00005355902,0.000003248183,0.001008368],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2750759,"threshold_uncertainty_score":0.1835029,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01307247775790789,"score_gpt":0.2428168333133689,"score_spread":0.229744355555461,"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."}}