{"id":"W2341967148","doi":"10.2166/wqrj.2010.041","title":"Algae-based Biomonitoring: Predicting Diatom Reference Communities in Unpolluted Streams using Classification Trees, Random Forests, and Artificial Neural Networks","year":2010,"lang":"en","type":"article","venue":"Water Quality Research Journal","topic":"Diatoms and Algae Research","field":"Materials Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Trois-Rivières; Institut National de la Recherche Scientifique","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Diatom; Biomonitoring; STREAMS; Random forest; Environmental science; Artificial neural network; Ecology; Hydrology (agriculture); Geology; Machine learning; Computer science; Biology","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":[0.001128431,0.0006807275,0.0003478047,0.001504628,0.0003651329,0.0007059426,0.0004749265,0.0004164514,0.000208819],"category_scores_gemma":[0.001648833,0.0002188009,0.0004400868,0.0009876498,0.0002061884,0.0004449223,0.0002666314,0.0002901669,0.00007359969],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00167859,"about_ca_system_score_gemma":0.001280392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.2970931,"about_ca_topic_score_gemma":0.3331953,"domain_scores_codex":[0.9997992,0.00005076563,0.00001422901,0.00005751737,0.00004723067,0.00003116634],"domain_scores_gemma":[0.9994432,0.0002156607,0.00008376461,0.00001797949,0.0001924969,0.00004687352],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004501161,0.0003616404,0.546154,0.000111955,0.0002228513,0.00009402099,0.0001240264,0.3620336,0.007666985,0.0002851711,0.0005458388,0.08194982],"study_design_scores_gemma":[0.000008325839,0.00002934631,0.0694747,0.000007064222,0.00001914402,0.000009335156,0.00004150646,0.9290508,0.0011223,0.0001463207,0.00008215295,0.000009025915],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9802268,0.0001830438,0.01829203,0.00004147035,0.000005503155,0.00005376236,0.0005724832,0.0001068253,0.0005181466],"genre_scores_gemma":[0.9859836,0.00007490586,0.01320095,0.00001149756,0.000003659256,0.00002276444,0.0004901256,0.000004932663,0.0002075405],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2970931,"threshold_uncertainty_score":0.5907276,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2352638608475308,"score_gpt":0.4292144601339832,"score_spread":0.1939505992864524,"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."}}