{"id":"W4300167487","doi":"10.1111/2041-210x.13984","title":"imageseg: An R package for deep learning‐based image segmentation","year":2022,"lang":"en","type":"article","venue":"Methods in Ecology and Evolution","topic":"Forest ecology and management","field":"Environmental Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Bundesamt für Naturschutz; University of Western Australia; Deutsche Forschungsgemeinschaft; United States Agency for International Development; Commonwealth Scientific and Industrial Research Organisation; Bundesministerium für Bildung und Forschung","keywords":"Computer science; Artificial intelligence; Segmentation; Convolutional neural network; Understory; Canopy; Image segmentation; Biome; Pattern recognition (psychology); Pixel; Aerial image; Remote sensing; Image (mathematics); Ecology; Geography; Ecosystem","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002178751,0.00007849401,0.0001072307,0.0000775326,0.0004822257,0.000006925365,0.00009655052,0.00005812336,0.001391175],"category_scores_gemma":[0.0001426801,0.00008779882,0.00002471176,0.0001409442,0.0001639579,0.000176453,0.0001537965,0.0001778837,0.00001641475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003350795,"about_ca_system_score_gemma":0.000006966482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005974837,"about_ca_topic_score_gemma":0.0006387716,"domain_scores_codex":[0.998302,0.0009804156,0.0001470804,0.0002810992,0.00005879878,0.0002305502],"domain_scores_gemma":[0.9995854,0.000205394,0.000070313,0.0001009855,0.000004044241,0.00003380762],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004624729,0.0007025172,0.8408561,0.00004159699,0.00002317582,0.00001903854,0.001127754,0.06224603,0.05103479,0.005538368,0.001147396,0.03680074],"study_design_scores_gemma":[0.0008836747,0.0006742352,0.9021726,4.971391e-7,0.00001943748,0.000004322389,0.0006418173,0.0633014,0.0007800609,0.02930857,0.002091032,0.0001224024],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.333713,0.00002479186,0.6643807,0.0002941947,0.0002664753,0.0004553056,0.000002819196,0.00003426225,0.0008284091],"genre_scores_gemma":[0.6780778,0.000004642266,0.3206422,0.000287371,0.00001106409,0.0005281063,0.0000413664,0.000007854936,0.0003995648],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3443648,"threshold_uncertainty_score":0.9995217,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0133625119656006,"score_gpt":0.3268464777860573,"score_spread":0.3134839658204567,"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."}}