{"id":"W2807162864","doi":"10.1101/334854","title":"Applications for deep learning in ecology","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"University of Maryland Center for Environmental Science","keywords":"Deep learning; Artificial intelligence; Ecology; Computer science; Data science; Machine learning; Biology","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":[0.001330306,0.0008473013,0.0005648989,0.001968042,0.0004522074,0.00235353,0.001378973,0.001853755,0.01366103],"category_scores_gemma":[0.006744204,0.0003722463,0.000909799,0.002104459,0.001197495,0.002199541,0.003428812,0.002885918,0.003451168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001338492,"about_ca_system_score_gemma":0.0009794865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003340777,"about_ca_topic_score_gemma":0.003029907,"domain_scores_codex":[0.9994302,0.0002117317,0.00004440644,0.0001072696,0.0001683218,0.00003789933],"domain_scores_gemma":[0.9978358,0.001208572,0.0001223775,0.0002506908,0.000401385,0.0001811751],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007683405,0.00009840242,0.005850458,0.001114459,0.0002385843,0.0002678996,0.000228805,0.2103683,0.002780572,0.3748495,0.07239349,0.3317327],"study_design_scores_gemma":[0.00001557662,0.00001168568,0.0007749904,0.0002895354,0.00001820765,0.00008704037,0.00005801347,0.3701397,0.001234051,0.5524151,0.07493347,0.00002257878],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.008842953,0.01527581,0.9080727,0.02623699,0.001234744,0.00008381798,0.001997102,0.005419991,0.03283588],"genre_scores_gemma":[0.4244402,0.0192114,0.5225294,0.005094146,0.00187167,0.0004285383,0.003289632,0.001313521,0.0218215],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.01366103,"threshold_uncertainty_score":0.04570067,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01090250951055582,"score_gpt":0.2085295912609019,"score_spread":0.197627081750346,"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."}}