{"id":"W4388823554","doi":"10.1371/journal.pone.0292839","title":"Dense neural network outperforms other machine learning models for scaling-up lichen cover maps in Eastern Canada","year":2023,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Lichen and fungal ecology","field":"Agricultural and Biological Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke; Natural Resources Canada; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Natural Resources Canada; Association of Canadian Universities for Northern Studies; University of Ottawa","keywords":"Lichen; Random forest; Artificial neural network; Convolutional neural network; Land cover; Deep learning; Computer science; Artificial intelligence; Remote sensing; Cartography; Environmental science; Geography; Land use; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009511948,0.00109364,0.0004227095,0.001280462,0.0009765741,0.001360899,0.001158416,0.0004839821,0.002091046],"category_scores_gemma":[0.003450259,0.0003206612,0.0006284332,0.00129369,0.000434995,0.001011479,0.0007000683,0.0007391548,0.0004989892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.009207699,"about_ca_system_score_gemma":0.008172431,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9404019,"about_ca_topic_score_gemma":0.9454026,"domain_scores_codex":[0.9996781,0.0000363482,0.00001680949,0.00008919311,0.00009144169,0.00008817332],"domain_scores_gemma":[0.9988637,0.0002266016,0.00005673285,0.00007806639,0.0007062805,0.00006871593],"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":[0.0002468283,0.0001623933,0.08569179,0.0001355931,0.0002535902,0.0001515638,0.0001361912,0.7080808,0.002092055,0.001288635,0.007557865,0.1942027],"study_design_scores_gemma":[0.00001327144,0.00002174531,0.01417306,0.00002417938,0.00003704028,0.00002003726,0.0001012216,0.9827142,0.0009280524,0.0005876585,0.001360172,0.00001932714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.919971,0.002145723,0.05307459,0.001508542,0.0001568787,0.0001772671,0.004538088,0.003713974,0.01471395],"genre_scores_gemma":[0.9704897,0.0004473513,0.02118795,0.0001456715,0.00001937572,0.00002690776,0.003203734,0.0001061253,0.004373304],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05959809,"threshold_uncertainty_score":0.1198981,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07285507267316912,"score_gpt":0.2086872914075367,"score_spread":0.1358322187343676,"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."}}