{"id":"W3201334366","doi":"10.3390/drones5030099","title":"Leveraging AI to Estimate Caribou Lichen in UAV Orthomosaics from Ground Photo Datasets","year":2021,"lang":"en","type":"article","venue":"Drones","topic":"Lichen and fungal ecology","field":"Agricultural and Biological Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Natural Resources Canada","funders":"Environment and Climate Change Canada; University of Waterloo; Queen's University; Government of Canada; University of Ottawa","keywords":"Lichen; Vegetation (pathology); Convolutional neural network; Remote sensing; Artificial neural network; Environmental science; Random forest; Limiting; RGB color model; Cartography; Computer science; Artificial intelligence; Geography; Ecology; Engineering; Biology","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":[0.0001070591,0.0001107721,0.000180598,0.00000866239,0.00009650736,0.00007976286,0.0001792269,0.00008369996,0.0008457972],"category_scores_gemma":[0.00007152601,0.00005089228,0.00003490974,0.0002712576,0.00002008611,0.0001136594,0.0001882026,0.0001228555,0.0001246859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003023014,"about_ca_system_score_gemma":0.00001486599,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006209798,"about_ca_topic_score_gemma":0.03160594,"domain_scores_codex":[0.9990563,0.00006284453,0.0001663139,0.0003369153,0.0001019021,0.000275677],"domain_scores_gemma":[0.9996225,0.0001415186,0.00002752351,0.00008041368,0.00002784123,0.0001002176],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00007030025,0.0004092204,0.4855748,0.00001663152,0.00005648247,0.0007054177,0.001860691,0.0001115512,0.4396013,0.0008570944,0.01434906,0.05638745],"study_design_scores_gemma":[0.0001934554,0.00006834578,0.8174549,0.00002152756,0.00001252912,0.00001341309,0.0005024641,0.0002851036,0.006671561,0.001346554,0.1731521,0.0002779782],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9941944,0.0001539803,0.00001062098,0.004424932,0.0002119711,0.00008825621,0.0005396326,0.00003540841,0.0003407329],"genre_scores_gemma":[0.9937493,0.00001271953,0.0004491013,0.002964114,0.0001747674,0.0000166743,0.002441008,0.000001120187,0.0001912274],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4329298,"threshold_uncertainty_score":0.9860647,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0217454759731764,"score_gpt":0.2692744141739204,"score_spread":0.247528938200744,"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."}}