{"id":"W4200442918","doi":"10.1101/2021.12.16.469125","title":"imageseg: an R package for deep learning-based image segmentation","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Forest ecology and management","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Bundesamt für Naturschutz; United States Agency for International Development; Commonwealth Scientific and Industrial Research Organisation; Bundesministerium für Bildung und Forschung; Leibniz-Gemeinschaft; Idea Wild","keywords":"Computer science; Understory; Convolutional neural network; Biome; Segmentation; Artificial intelligence; Workflow; Canopy; Aerial image; Pixel; Image segmentation; Deep learning; Machine learning; Pattern recognition (psychology); Remote sensing; Cartography; Ecology; Image (mathematics); Geography; Database","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002835129,0.004115701,0.002505561,0.002832324,0.000613903,0.00271986,0.004428325,0.001411657,0.0809773],"category_scores_gemma":[0.01206683,0.002481352,0.003207494,0.001983275,0.0009699825,0.002072734,0.003080074,0.003561624,0.06486392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0011537,"about_ca_system_score_gemma":0.003053883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00539148,"about_ca_topic_score_gemma":0.007164447,"domain_scores_codex":[0.9984481,0.0003104542,0.0001559221,0.0004915817,0.0004516489,0.0001421944],"domain_scores_gemma":[0.9968328,0.001783347,0.0003972228,0.0004145404,0.0004382184,0.0001338599],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005533384,0.00008321765,0.003772524,0.004280958,0.001463412,0.0004640477,0.0002597849,0.01697795,0.007477549,0.01116654,0.8523045,0.1011961],"study_design_scores_gemma":[0.0009830716,0.0002357419,0.009426456,0.001180862,0.0008567593,0.001154175,0.0001709622,0.1848689,0.03590366,0.06729241,0.697385,0.0005420074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.002989228,0.001341252,0.3433112,0.0005499879,0.0004106946,0.0004332611,0.1242931,0.5225088,0.004162459],"genre_scores_gemma":[0.03735096,0.001641331,0.5014296,0.001470319,0.0002033702,0.004430427,0.1655724,0.2780044,0.009897131],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.0809773,"threshold_uncertainty_score":0.270896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008421124002439412,"score_gpt":0.2208292270329047,"score_spread":0.2124081030304653,"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."}}