{"id":"W2988297868","doi":"10.1016/j.scitotenv.2019.135160","title":"Application of deep learning in aquatic bioassessment: Towards automated identification of non-biting midges","year":2019,"lang":"en","type":"article","venue":"The Science of The Total Environment","topic":"Freshwater macroinvertebrate diversity and ecology","field":"Environmental Science","cited_by":52,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"Ministarstvo Prosvete, Nauke i Tehnološkog Razvoja","keywords":"Chironomidae; Identification (biology); Convolutional neural network; Artificial intelligence; Biomonitoring; Subfamily; Artificial neural network; Computer science; Process (computing); Pattern recognition (psychology); Ecology; 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":[0.0008883173,0.0007646453,0.000407047,0.0008583075,0.00032223,0.0008356367,0.0006869579,0.0009330853,0.001087185],"category_scores_gemma":[0.001301958,0.0002416683,0.0004307901,0.0006486452,0.0002468866,0.0006351604,0.001139831,0.0007680407,0.0007333031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000349688,"about_ca_system_score_gemma":0.0006549238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005780178,"about_ca_topic_score_gemma":0.01034559,"domain_scores_codex":[0.9996865,0.00007230142,0.0000149106,0.0001073537,0.00005609657,0.00006285023],"domain_scores_gemma":[0.9993617,0.0002639589,0.00006373311,0.00006366683,0.0001951262,0.00005176714],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001917042,0.0005026607,0.04580555,0.0001497716,0.0002030714,0.0001112693,0.0001898356,0.06612332,0.05076156,0.001299462,0.004659473,0.8300024],"study_design_scores_gemma":[0.00000741103,0.00008796743,0.01228949,0.00002784574,0.00003171669,0.00006326305,0.0000763703,0.9721808,0.01042028,0.002839558,0.001958788,0.00001648752],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4110937,0.001204093,0.5779322,0.0007289771,0.0001604319,0.00008769873,0.001381037,0.002830161,0.004581588],"genre_scores_gemma":[0.8085291,0.0002887655,0.1842772,0.0004411028,0.00005386693,0.00005807327,0.001142334,0.00007743077,0.00513206],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005780178,"threshold_uncertainty_score":0.01149309,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005276924716327885,"score_gpt":0.2039427800675198,"score_spread":0.1986658553511919,"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."}}