{"id":"W3181950296","doi":"10.3390/rs13142658","title":"Leveraging Deep Neural Networks to Map Caribou Lichen in High-Resolution Satellite Images Based on a Small-Scale, Noisy UAV-Derived Map","year":2021,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Natural Resources Canada; Queen's University","funders":"Natural Resources Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Lichen; Computer science; Remote sensing; Robustness (evolution); Scale (ratio); Artificial intelligence; Classifier (UML); Image resolution; Pattern recognition (psychology); Environmental science; Cartography; Geography; Ecology","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003170033,0.0004248435,0.0004414662,0.0003364923,0.000138281,0.000245158,0.0001315876,0.0002300442,0.000004968373],"category_scores_gemma":[0.0001389714,0.00051759,0.0001265808,0.000674462,0.00004810444,0.0001381944,0.00006778703,0.000609353,0.00005089218],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006413958,"about_ca_system_score_gemma":0.00003883378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003131346,"about_ca_topic_score_gemma":0.0005302046,"domain_scores_codex":[0.9974619,0.0002439052,0.0005409344,0.000674694,0.0003051336,0.000773395],"domain_scores_gemma":[0.9985653,0.0002128308,0.00008445551,0.0007561873,0.0001806942,0.0002005036],"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":[0.0000279678,0.000009956359,0.00003660306,0.00006535979,0.00001364174,0.0002155155,0.0002941963,0.6771321,0.1573465,0.000001130161,0.00006574651,0.1647912],"study_design_scores_gemma":[0.0005066982,0.00001980221,0.008175534,0.0003961013,0.00003073056,0.00003732457,0.0001060709,0.9566187,0.03315495,0.00002946652,0.0004400025,0.000484625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3600672,0.000500489,0.6352381,0.001831448,0.001100911,0.000319794,0.000002811341,0.0005097869,0.0004295025],"genre_scores_gemma":[0.8778073,0.00003030261,0.1209665,0.000537991,0.0003408839,1.020358e-7,0.0001144257,0.000137442,0.0000650752],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5177401,"threshold_uncertainty_score":0.9997275,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01428429290777947,"score_gpt":0.2132653537854501,"score_spread":0.1989810608776707,"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."}}