{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01672409,0.0002042977,0.0003514348,0.0005173144,0.001192175,0.001506652,0.0006413962,0.0002031172,0.0001845035],"category_scores_gemma":[0.0004762366,0.0001453561,0.00007647838,0.0003814723,0.0007920768,0.0006190493,0.0002982004,0.002333903,0.000009268912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001400642,"about_ca_system_score_gemma":0.000242446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005064737,"about_ca_topic_score_gemma":0.005934289,"domain_scores_codex":[0.9933409,0.00299517,0.0008324513,0.0003237309,0.001250331,0.00125739],"domain_scores_gemma":[0.9975471,0.0009571772,0.000152522,0.0004599359,0.0004735542,0.0004097429],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001025045,0.0002739954,0.2888052,0.00006161864,0.00001763536,0.0000452286,0.001322054,0.002118577,0.6923805,0.0004644429,0.00003470329,0.01345093],"study_design_scores_gemma":[0.003987085,0.0002605893,0.1200737,0.0002518216,0.00001752607,0.00008305971,0.004912205,0.7701082,0.09688876,0.002521751,0.0003599448,0.000535315],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9975178,0.0001170795,0.0008569955,0.0006097721,0.0004823089,0.0003048559,0.00002674773,0.00003986404,0.00004459554],"genre_scores_gemma":[0.9988379,0.00004533515,0.0003870738,0.00001147112,0.0006103385,0.00002340234,0.0000328348,0.0000272226,0.00002441991],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7679896,"threshold_uncertainty_score":0.9999678,"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."}}